Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-05-12T07:26:18.960359Z
Paper Citation Record · LEDGER
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
As of 6 August 2026, this Paper Citation Record lists 100 of 135 outbound references and 100 inbound Pith citation observations for arXiv:2507.19457.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-06T06:34:29.942622+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-06T05:08:41.113370Z
A source-named dated measurement, never combined with another source.
Source: pith, observed 2026-08-05T02:28:24.338817Z
Reference resolution
100 of 135 outbound references displayed
- verified exact2
- verified fuzzy63
- unresolved34
- parse uncertain0
- malformed identifier1
- metadata mismatch0
External citation measurements
0
pith, observed 2026-08-05T02:28:24.338817Z
Outbound references
Observation f637e4f4-df9e-4db7-b4a3-69f4b60cb9b4 · outbound
This paper cites Omar Khattab, Keshav Santhanam, Xiang Lisa Li, David Hall, Percy Liang, Christopher Potts, and Matei Zaharia.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Omar Khattab, Keshav Santhanam, Xiang Lisa Li, David Hall, Percy Liang, Christopher Potts, and Matei Zaharia
Reference 1
- Resolution
- verified exact
- doi, observed 2026-05-12T07:26:19.161837Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 0e1f390a-c5e7-4eec-972b-15c788d67bd9 · outbound
This paper cites White paper.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning White paper
Reference 2
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:20.433515Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 29cc6ace-ce29-43ad-a45e-470ab23d0c1d · outbound
This paper cites Optimizing instructions and demonstrations for multi-stage language model programs.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Optimizing instructions and demonstrations for multi-stage language model programs
Reference 3
- Resolution
- verified exact
- doi, observed 2026-05-12T07:26:19.143027Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 2fca562d-6822-4897-9cd0-0ceb890dbdbb · outbound
This paper cites constant with warmup learning.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning constant with warmup learning
Reference 4
- Resolution
- malformed identifier
- raw_fallback, observed 2026-05-12T07:26:19.175341Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation ce499ab0-0d82-4034-9f97-1c52c8e0ac77 · outbound
This paper cites - When queries contain location, dates, names, URLs, or other identifiable details, generalize or omit them in the LLM request.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning - When queries contain location, dates, names, URLs, or other identifiable details, generalize or omit them in the LLM request
Reference 5
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:19.195907Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation ca9379fe-b687-4bf3-8cf6-b0e2e7289e9b · outbound
This paper cites - Determine if the query involves translation, event recommendations, advice, summarization, or other tasks.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning - Determine if the query involves translation, event recommendations, advice, summarization, or other tasks
Reference 6
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:19.205116Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 7bca836c-15f8-4c0b-9818-8679a8dca434 · outbound
This paper cites - Retain the core informational or functional need so that the LLM can respond effectively.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning - Retain the core informational or functional need so that the LLM can respond effectively
Reference 7
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:19.228360Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 4e21420c-b064-4358-b3c5-f821e409ee5f · outbound
This paper cites - Request generalized or example-based information instead of specific user data.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning - Request generalized or example-based information instead of specific user data
Reference 8
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:19.239360Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation a058e4da-aed9-4330-8dc9-69ee8d21cc70 · outbound
This paper cites Input Format: - A user query string possibly containing private or sensitive information.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Input Format: - A user query string possibly containing private or sensitive information
Reference 9
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:19.255361Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation dd4d4c86-df03-4eba-8254-ee4f2d1695f1 · outbound
This paper cites - When the user query contains private, sensitive, or proprietary data, you must generalize, abstract, or omit these details.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning - When the user query contains private, sensitive, or proprietary data, you must generalize, abstract, or omit these details
Reference 10
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:19.264011Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 68cff882-debf-4d8d-a814-8d905e1aec1b · outbound
This paper cites - When reformulating, maintain the essential informational or functional need so that the external LLM can provide a useful, relevant response.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning - When reformulating, maintain the essential informational or functional need so that the external LLM can provide a useful, relevant response
Reference 11
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:19.282256Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 934fab54-8806-402f-9c27-a94438da065d · outbound
This paper cites - Retain appropriate detail and context to ensure relevance, but balance this carefully against privacy concerns.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning - Retain appropriate detail and context to ensure relevance, but balance this carefully against privacy concerns
Reference 12
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:19.290568Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation c4ec8c18-64bb-486f-b409-7ba06e91686b · outbound
This paper cites - Use general descriptions or hypothetical/example-based requests where appropriate.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning - Use general descriptions or hypothetical/example-based requests where appropriate
Reference 13
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:19.295795Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation f842cc23-046f-4c33-a105-dcea55e8b0be · outbound
This paper cites an interdisciplinary health minor.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning an interdisciplinary health minor
Reference 14
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:19.306588Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 10ab364f-5b8d-484f-aeaf-5be02aa064d5 · outbound
This paper cites 37 Accepted at ICLR 2026 (Oral).
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning 37 Accepted at ICLR 2026 (Oral)
Reference 15
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:19.312128Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 3d3ece8d-f877-412d-ab6c-735e96c4bf84 · outbound
This paper cites - Preserve the functional intent and thematic requirements (e.g., content topics around sustainability, summary of a personâĂŹs background, professional email follow-up).
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning - Preserve the functional intent and thematic requirements (e.g., content topics around sustainability, summary of a personâĂŹs background, professional email follow-up)
Reference 16
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:19.319360Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation f17a5c33-5688-479e-b8f3-a360af1f92aa · outbound
This paper cites - Avoid ambiguous or overly generic requests that might reduce relevance or usefulness.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning - Avoid ambiguous or overly generic requests that might reduce relevance or usefulness
Reference 17
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:19.327843Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 86c66fd5-de47-4560-a676-c8944a1e7f8c · outbound
This paper cites an unresolved cited work.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Unresolved cited work
Reference 18
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T07:26:19.332418Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 73d66354-d2c9-456e-9e08-b49448d7786a · outbound
This paper cites - Explain how the essential task was preserved despite abstraction.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning - Explain how the essential task was preserved despite abstraction
Reference 19
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:19.337120Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 5939a6eb-8bf6-411f-8256-2ae9f9e0f2c6 · outbound
This paper cites Never lightly obscure or partially redact; full abstraction is required.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Never lightly obscure or partially redact; full abstraction is required
Reference 20
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:19.344796Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 3cbb7c8e-259f-46e7-9c37-7daa2669bc17 · outbound
This paper cites an unresolved cited work.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Unresolved cited work
Reference 23
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T07:26:19.357361Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation c32192d0-be80-49c9-af4f-6a1291ed55a7 · outbound
This paper cites -`summary_1`is a concise summary of information from a document retrieved in the first hop, which partially addresses the question.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning -`summary_1`is a concise summary of information from a document retrieved in the first hop, which partially addresses the question
Reference 24
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:19.368082Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 9b9cb2d3-4f1f-4447-8824-d9d722fbc93b · outbound
This paper cites - The multi-hop retrieval system works in stages: - First hop: The original question returns some documents.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning - The multi-hop retrieval system works in stages: - First hop: The original question returns some documents
Reference 25
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:19.378372Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 5135412c-6acd-4b91-ad13-c9811a3377f2 · outbound
This paper cites Madeira archipelago population in 2011.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Madeira archipelago population in 2011
Reference 26
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:19.388818Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 2ae2a6a5-e397-4e18-9a51-9e1eaece7cf2 · outbound
This paper cites - Reframe the query to explicitly mention these broader or related entities connected to the original question.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning - Reframe the query to explicitly mention these broader or related entities connected to the original question
Reference 27
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:19.394983Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 56aaf268-5d73-426c-9c57-0dc2438a5bbc · outbound
This paper cites What entity or aspect does this summary hint at that could answer the original question but was not found yet?.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning What entity or aspect does this summary hint at that could answer the original question but was not found yet?
Reference 28
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:19.402640Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation c64d0f1d-3a05-4dba-ac7e-fe32baa9fc8e · outbound
This paper cites - Ensure the query relates logically to the original question while targeting the broader or complementary knowledge identified in`summary_1`.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning - Ensure the query relates logically to the original question while targeting the broader or complementary knowledge identified in`summary_1`
Reference 29
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:19.409355Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 0c7058b8-9a0b-41c3-b64e-83349040a01d · outbound
This paper cites an unresolved cited work.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Unresolved cited work
Reference 30
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T07:26:19.413730Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 118bd7ad-548d-4d69-9f02-2217996a1c4f · outbound
This paper cites - If one summary provides a fact that the other does not mention, carefully evaluate its plausibility.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning - If one summary provides a fact that the other does not mention, carefully evaluate its plausibility
Reference 31
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:19.421508Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 016df6c6-6040-4a27-99c7-d607c5be2bc7 · outbound
This paper cites - **Names and nicknames:** Provide only the specific nickname or name when asked, without extra phrasing.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning - **Names and nicknames:** Provide only the specific nickname or name when asked, without extra phrasing
Reference 32
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:19.430101Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 358483af-a370-4124-bb56-33867413805d · outbound
This paper cites - Avoid repeating or restating the question.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning - Avoid repeating or restating the question
Reference 33
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:19.436570Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 05bcb013-edd4-4414-867f-26d616b3f190 · outbound
This paper cites - For example, when a summary gives a year that conflicts with known release dates or factual details, prefer the verified date.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning - For example, when a summary gives a year that conflicts with known release dates or factual details, prefer the verified date
Reference 34
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:19.444063Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 219cda13-cc4b-4e53-a00a-11f3a2954770 · outbound
This paper cites Chiesa di Filippini Madonna di Galliera e Filippo Neri.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Chiesa di Filippini Madonna di Galliera e Filippo Neri
Reference 35
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:19.449026Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation b43e629d-561f-4c22-af16-281580763386 · outbound
This paper cites an unresolved cited work.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Unresolved cited work
Reference 36
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T07:26:19.454470Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation f3231016-7589-44fa-8477-d21755532e66 · outbound
This paper cites an unresolved cited work.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Unresolved cited work
Reference 37
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T07:26:19.461338Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 369cdf84-f682-4513-94ba-c660fff92036 · outbound
This paper cites an unresolved cited work.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Unresolved cited work
Reference 38
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T07:26:19.470825Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 88db2761-9dee-4458-b925-51031d3919e2 · outbound
This paper cites Children in Need 2006 |.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Children in Need 2006 |
Reference 39
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:19.479835Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation e0cc3802-6749-44d2-9ad9-23281762457b · outbound
This paper cites an unresolved cited work.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Unresolved cited work
Reference 40
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T07:26:19.491628Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation a74a1f82-f6ea-46c6-b335-d570b2343753 · outbound
This paper cites - Use explicit information from the summary (e.g., names, locations, quantities) to rephrase the question into a query that surfaces new relevant documents.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning - Use explicit information from the summary (e.g., names, locations, quantities) to rephrase the question into a query that surfaces new relevant documents
Reference 41
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:19.500085Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation b43130ea-90ba-4ec7-89f0-bd70a859eecf · outbound
This paper cites What is the headquarters location of [Company]?.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning What is the headquarters location of [Company]?
Reference 42
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:19.507749Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation cce2a077-907e-4be9-8bf3-e7a334fc9622 · outbound
This paper cites - Assuming the summary contains all necessary information for the second hop.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning - Assuming the summary contains all necessary information for the second hop
Reference 43
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:19.516629Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation e0292d69-8ff5-4d05-bfa1-6f0835b5bfc9 · outbound
This paper cites Medicare.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Medicare
Reference 44
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:19.526433Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 9729d0c4-7465-404e-89d9-dfb24b239c38 · outbound
This paper cites second Duke of Florence.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning second Duke of Florence
Reference 45
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:19.536397Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 753b66ee-40a6-49ba-959a-4de86c146f74 · outbound
This paper cites If summaries conflict, prioritize the one with explicit factual claims (e.g., numerical data, direct statements).
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning If summaries conflict, prioritize the one with explicit factual claims (e.g., numerical data, direct statements)
Reference 46
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:19.544716Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation da182c44-44e9-4f89-91d8-eafa76a75e8a · outbound
This paper cites Do not add context, explanations, or external knowledge beyond what is explicitly provided.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Do not add context, explanations, or external knowledge beyond what is explicitly provided
Reference 47
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:19.551510Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 1540ce11-c1f5-424f-8d8c-e03f8f8e7007 · outbound
This paper cites Path to Prosperity.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Path to Prosperity
Reference 48
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:19.556917Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 7dd15aa9-fdb1-4698-8ebf-7e8db8d3a446 · outbound
This paper cites Put on the Spot.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Put on the Spot
Reference 49
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:19.564497Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation eb1edb01-0bb5-4db7-8d6d-dec560ad2ccd · outbound
This paper cites an unresolved cited work.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Unresolved cited work
Reference 50
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T07:26:19.569990Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 1ab3d5d5-02b6-45ae-b4c2-4b5ae3618559 · outbound
This paper cites an unresolved cited work.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Unresolved cited work
Reference 51
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T07:26:19.575376Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 55a62367-0ef5-485b-9c22-4b19bee021f9 · outbound
This paper cites Billy Truax.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Billy Truax
Reference 52
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:19.581158Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation fbe6296d-b887-4996-9850-2e5d1e8571bf · outbound
This paper cites an unresolved cited work.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Unresolved cited work
Reference 53
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T07:26:19.585549Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation f0ed6b7e-d43f-4ea6-aeff-9a8afe59c533 · outbound
This paper cites an unresolved cited work.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Unresolved cited work
Reference 54
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T07:26:19.600364Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation d6ccedc2-fdb8-45cd-bf4a-6ee35178a8a6 · outbound
This paper cites Newcastle United.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Newcastle United
Reference 55
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:19.609277Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 786c76cf-156a-464c-b732-69f2af87d895 · outbound
This paper cites Stan Kroenke owns Sports Direct and Arsenal F.C.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Stan Kroenke owns Sports Direct and Arsenal F.C
Reference 56
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:19.620608Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 7efe6b90-4da4-4be7-80ba-3dfaccf68157 · outbound
This paper cites Project RAND.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Project RAND
Reference 57
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:19.630793Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 420a2221-c90d-47f0-9473-fbe199001c3f · outbound
This paper cites an unresolved cited work.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Unresolved cited work
Reference 58
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T07:26:19.638430Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 393823a1-186b-4484-90ea-ea3f968a67e7 · outbound
This paper cites an unresolved cited work.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Unresolved cited work
Reference 59
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T07:26:19.642760Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 2b757bbf-c4de-4a72-a65a-90ea3212a82c · outbound
This paper cites That's my answer.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning That's my answer
Reference 60
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:19.646771Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation cf4f04bc-a056-45e8-9c4a-e82c31c0cee4 · outbound
This paper cites - Specific length constraints (number of sentences, bullet points, word counts).
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning - Specific length constraints (number of sentences, bullet points, word counts)
Reference 61
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:19.664454Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation d80fdce7-63da-42c4-b28a-08b8968be6df · outbound
This paper cites - Do not prepend or append anything to the repeated text unless explicitly instructed.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning - Do not prepend or append anything to the repeated text unless explicitly instructed
Reference 62
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:19.683799Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation dd4ee58d-03d3-415f-a092-f16a3a5da09a · outbound
This paper cites - Using specified markdown bullet point styles (e.g., asterisks).
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning - Using specified markdown bullet point styles (e.g., asterisks)
Reference 63
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:19.708873Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation b7657fbb-c248-44d5-b30e-9bb21b5f89ac · outbound
This paper cites - Use domain knowledge and reliable calculations to ensure factual correctness in answers.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning - Use domain knowledge and reliable calculations to ensure factual correctness in answers
Reference 64
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:19.733857Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation b2fedac0-e052-4a85-901d-d64159720436 · outbound
This paper cites - Your final output must be the exact, ready-to-deliver response that meets all user instructions perfectly.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning - Your final output must be the exact, ready-to-deliver response that meets all user instructions perfectly
Reference 65
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:19.747504Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 1a036ed6-13d8-41bb-bdc9-cb76e8813006 · outbound
This paper cites Reasoning.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Reasoning
Reference 66
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:19.767694Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 9b884c6b-cf61-4bee-8132-f70ae38feede · outbound
This paper cites an unresolved cited work.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Unresolved cited work
Reference 67
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T07:26:19.787346Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 57efef26-a7f8-4f84-99b7-0926357d91e7 · outbound
This paper cites an unresolved cited work.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Unresolved cited work
Reference 68
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T07:26:19.795535Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 5e39e174-79c3-4ece-ac16-84635f1d7411 · outbound
This paper cites an unresolved cited work.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Unresolved cited work
Reference 69
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T07:26:19.801433Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 18f2390c-334e-4e25-9469-67678be2abf2 · outbound
This paper cites an unresolved cited work.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Unresolved cited work
Reference 70
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T07:26:19.806233Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation c89debba-ca83-42cf-b092-a633a593bb59 · outbound
This paper cites an unresolved cited work.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Unresolved cited work
Reference 71
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T07:26:19.813380Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 7b531d28-15df-4a03-b195-1cea4fb8f66d · outbound
This paper cites an unresolved cited work.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Unresolved cited work
Reference 72
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T07:26:19.820293Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 379efcab-0a82-4a37-8ac0-19d3145313d0 · outbound
This paper cites an unresolved cited work.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Unresolved cited work
Reference 73
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T07:26:19.827240Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation a6caa58f-4505-470e-9677-64d33647ceed · outbound
This paper cites an unresolved cited work.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Unresolved cited work
Reference 74
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T07:26:19.834354Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation e0bb9413-8228-4171-b3ff-5d09e22f83a0 · outbound
This paper cites an unresolved cited work.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Unresolved cited work
Reference 75
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T07:26:19.840355Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 6243a37d-2d4a-4342-8741-827fc42224df · outbound
This paper cites 62 Accepted at ICLR 2026 (Oral).
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning 62 Accepted at ICLR 2026 (Oral)
Reference 76
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:19.854363Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 621614a5-5adb-4183-9f19-94e6b4f1c35f · outbound
This paper cites an unresolved cited work.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Unresolved cited work
Reference 77
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T07:26:19.862359Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 09292322-4358-40a2-870b-47584c00dd42 · outbound
This paper cites an unresolved cited work.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Unresolved cited work
Reference 78
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T07:26:19.871706Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 5a572434-6c2f-4aa4-b967-3eebf58ecd2f · outbound
This paper cites - Include named entities, dates, roles, or other domain-specific identifiers directly mentioned in both claim and summary to improve retrieval effectiveness.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning - Include named entities, dates, roles, or other domain-specific identifiers directly mentioned in both claim and summary to improve retrieval effectiveness
Reference 79
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:19.890359Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 0af9c7ab-3d5d-4d6b-98af-351005754d9f · outbound
This paper cites an unresolved cited work.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Unresolved cited work
Reference 80
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T07:26:19.906510Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 03e8c207-8534-492b-93f9-343bf46b9f1f · outbound
This paper cites an unresolved cited work.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Unresolved cited work
Reference 81
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T07:26:20.015015Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation a12af079-d6ee-4ded-849e-bec48b776ef6 · outbound
This paper cites an unresolved cited work.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Unresolved cited work
Reference 82
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T07:26:20.028621Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 68e3b665-e7aa-47c4-95df-5371c419819a · outbound
This paper cites Bette" Davis, an actress with Welsh ancestry. reasoning: The claim states that the brother of Freddie Sessler was a restaurateur whose club was frequented by Ruth Elizabeth.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Bette" Davis, an actress with Welsh ancestry. reasoning: The claim states that the brother of Freddie Sessler was a restaurateur whose club was frequented by Ruth Elizabeth
Reference 83
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:20.035280Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 2229e030-2ff0-4194-89b1-032ea87d7562 · outbound
This paper cites an unresolved cited work.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Unresolved cited work
Reference 84
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T07:26:20.042098Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 7bbb8816-2bd4-485d-9292-cd40c25d6981 · outbound
This paper cites Your query must incorporate these clarifications (e.g., name corrections, factual specifics, or counterpoints) to ensure retrieval of relevant evidence reflecting the nuanced truth.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Your query must incorporate these clarifications (e.g., name corrections, factual specifics, or counterpoints) to ensure retrieval of relevant evidence reflecting the nuanced truth
Reference 85
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:20.051270Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 2a9808a4-90ad-4963-b904-9b5e9b40dd20 · outbound
This paper cites Was person X a politician in country Y during year Z?.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Was person X a politician in country Y during year Z?
Reference 86
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:20.060330Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 91eb3694-d750-4b5e-8f2e-b020484b8446 · outbound
This paper cites United Kingdom of the Netherlands between 1815 and 1830.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning United Kingdom of the Netherlands between 1815 and 1830
Reference 87
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:20.068509Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation d7c8016c-231d-4ab2-bbc4-1d3af0de6ead · outbound
This paper cites - Avoid overly broad or vague phrasing.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning - Avoid overly broad or vague phrasing
Reference 88
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:20.078344Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 3a35fae8-81c9-4e05-90b6-8f3549f67d32 · outbound
This paper cites Kora Kagaz.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Kora Kagaz
Reference 89
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:20.092354Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation d9f3f115-2907-48eb-8d8a-55f40cf86907 · outbound
This paper cites Don", "Bairaag.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Don", "Bairaag
Reference 90
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:20.100174Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 596c2123-0e34-43d6-b171-dccf974de9e9 · outbound
This paper cites 69 Accepted at ICLR 2026 (Oral).
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning 69 Accepted at ICLR 2026 (Oral)
Reference 91
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:20.107464Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 5588deff-a725-4905-a64c-fc5f3997c556 · outbound
This paper cites For example, highlight relevant names, works (films, albums, songs, books), attributes, dates, nicknames, or roles that clarify the claim's accuracy.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning For example, highlight relevant names, works (films, albums, songs, books), attributes, dates, nicknames, or roles that clarify the claim's accuracy
Reference 92
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:20.118350Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation bcf0f991-b380-4ff4-bd29-0f20ecbc8aeb · outbound
This paper cites an unresolved cited work.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Unresolved cited work
Reference 93
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T07:26:20.133363Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation ee56ac31-8213-4293-b28e-77436578b3a9 · outbound
This paper cites an unresolved cited work.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Unresolved cited work
Reference 94
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T07:26:20.153796Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 36144ffb-a026-4fd9-9c8d-cb86fada111f · outbound
This paper cites an unresolved cited work.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Unresolved cited work
Reference 95
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T07:26:20.160833Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 4f6749a9-4ac0-4ea2-9904-d693dad16b4f · outbound
This paper cites an unresolved cited work.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Unresolved cited work
Reference 96
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T07:26:20.165582Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 96bf5a03-4d4a-4738-96ae-e74c899732d7 · outbound
This paper cites Massimo Giordano.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Massimo Giordano
Reference 97
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:20.179041Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation eebd75ff-27d5-4e4d-b281-811a2703c9e2 · outbound
This paper cites his actual 15th-century timeline) or misattributions (e.g., *Hayy ibn Yaqdhan* by Ibn Tufail, not Ali Qushji).
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning his actual 15th-century timeline) or misattributions (e.g., *Hayy ibn Yaqdhan* by Ibn Tufail, not Ali Qushji)
Reference 98
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:20.187362Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation c513ceb3-a3b4-48e2-bb26-705c730713f5 · outbound
This paper cites the claim states X, but the summary notes Y is unverified.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning the claim states X, but the summary notes Y is unverified
Reference 99
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:20.191867Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 38afcf85-a338-427a-aefe-582313cdbbdf · outbound
This paper cites AnaÃŕs Nin.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning AnaÃŕs Nin
Reference 100
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T07:26:20.196068Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 5835ec21-d828-4f08-b3c1-e84d7fde1dbe · outbound
This paper cites an unresolved cited work.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Unresolved cited work
Reference 101
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T07:26:20.200148Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 115b94f0-3c12-4fac-ab58-4cdd7dd2f1d7 · outbound
This paper cites an unresolved cited work.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Unresolved cited work
Reference 102
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T07:26:20.204062Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Pith citing papers
Observation 2defe70b-80b0-4860-a69e-45ce02c138a7 · inbound
AirTrafficGen: Configurable Air Traffic Scenario Generation with Large Language Models cites this paper.
AirTrafficGen: Configurable Air Traffic Scenario Generation with Large Language Models GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 2025
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T05:08:41.113370Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7029828f-3886-4ae3-b3a0-a5365c0a6efc · inbound
Compiling Prompts, Not Crafting Them: A Reproducible Workflow for AI-Assisted Evidence Synthesis cites this paper.
Compiling Prompts, Not Crafting Them: A Reproducible Workflow for AI-Assisted Evidence Synthesis GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 21
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T17:13:54.245487Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f64526bd-69ce-4c5c-a835-3fbf4c59aa04 · inbound
Maestro: Joint Graph & Config Optimization for Reliable AI Agents cites this paper.
Maestro: Joint Graph & Config Optimization for Reliable AI Agents GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 1
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T05:59:49.930789Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7b23e664-d998-4f2a-ab22-36dcb94cf60e · inbound
LAD-VF: LLM-Automatic Differentiation Enables Fine-Tuning-Free Robot Planning from Formal Methods Feedback cites this paper.
LAD-VF: LLM-Automatic Differentiation Enables Fine-Tuning-Free Robot Planning from Formal Methods Feedback GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 31
- Resolution
- unresolved
- no resolver link, observed 2026-08-04T15:47:13.053845Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a6af7a28-1ba6-4a61-8b08-ae9b4ed7a5ea · inbound
Painless Activation Steering: An Automated, Lightweight Approach for Post-Training Large Language Models cites this paper.
Painless Activation Steering: An Automated, Lightweight Approach for Post-Training Large Language Models GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 1
- Resolution
- verified exact
- local_arxiv, observed 2026-05-21T21:45:40.610940Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 18c51a19-1bd5-49be-822e-28e2e73dd120 · inbound
ARM: Discovering Agentic Reasoning Modules for Generalizable Multi-Agent Systems cites this paper.
ARM: Discovering Agentic Reasoning Modules for Generalizable Multi-Agent Systems GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 1
- Resolution
- verified exact
- local_arxiv, observed 2026-05-21T20:50:36.647009Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation b1138970-d17a-4cf7-8172-906e63d12f21 · inbound
Idea2Plan: Exploring AI-Powered Research Planning cites this paper.
Idea2Plan: Exploring AI-Powered Research Planning GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 1998
- Resolution
- unresolved
- no resolver link, observed 2026-08-04T07:41:25.362375Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c15e697d-b5da-454d-844f-29aac968dfa4 · inbound
Reinforcement Learning Improves Traversal of Parametric Knowledge in LLMs cites this paper.
Reinforcement Learning Improves Traversal of Parametric Knowledge in LLMs GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 5
- Resolution
- unresolved
- no resolver link, observed 2026-08-03T23:27:34.572562Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3748527b-62ac-41eb-b264-d0d4509848f9 · inbound
REVISOR: Beyond Textual Reflection, Towards Multimodal Introspective Reasoning in Long-Form Video Understanding cites this paper.
REVISOR: Beyond Textual Reflection, Towards Multimodal Introspective Reasoning in Long-Form Video Understanding GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 1
- Resolution
- verified exact
- local_arxiv, observed 2026-05-17T22:20:22.950726Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation d0bcb039-1a59-4bc5-a1dc-13067998597e · inbound
Improving Language Agents through BREW: Bootstrapping expeRientially-learned Environmental knoWledge cites this paper.
Improving Language Agents through BREW: Bootstrapping expeRientially-learned Environmental knoWledge GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 1
- Resolution
- unresolved
- no resolver link, observed 2026-08-03T20:21:01.561279Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7f45d740-dc8d-477d-90d4-e01a752b21a4 · inbound
Agentic Learner with Grow-and-Refine Multimodal Semantic Memory cites this paper.
Agentic Learner with Grow-and-Refine Multimodal Semantic Memory GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 2
- Resolution
- verified exact
- local_arxiv, observed 2026-05-17T04:29:01.670409Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 0e6ede21-0aa6-4463-a441-73c07453587c · inbound
ContextLeak: Auditing Leakage in Private In-Context Learning Methods cites this paper.
ContextLeak: Auditing Leakage in Private In-Context Learning Methods GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 1
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-16T22:11:18.417973Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation d76ad317-d481-46b0-9bf7-c92cf7a63c05 · inbound
FEM-Bench: A Structured Scientific Reasoning Benchmark for Evaluating Code-Generating LLMs cites this paper.
FEM-Bench: A Structured Scientific Reasoning Benchmark for Evaluating Code-Generating LLMs GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 21
- Resolution
- unresolved
- no resolver link, observed 2026-08-03T14:21:29.109359Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b2fa3f8f-c75a-44ac-9054-c0cc0644b1fb · inbound
Learning to Configure Agentic AI Systems cites this paper.
Learning to Configure Agentic AI Systems GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 1
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-21T13:10:10.366202Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation d21ca62d-ffee-44c4-a6f6-3073c0cdfa60 · inbound
Learning to Configure Agentic AI Systems cites this paper.
Learning to Configure Agentic AI Systems GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 1
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-22T11:31:29.521490Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 06561b5c-5099-4bd5-9d9b-1d86c21c5736 · inbound
Vital Trace: Protocol-Constrained Patient-State Reasoning for Longitudinal Clinical Trajectories cites this paper.
Vital Trace: Protocol-Constrained Patient-State Reasoning for Longitudinal Clinical Trajectories GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 1
- Resolution
- unresolved
- no resolver link, observed 2026-08-02T23:44:42.739735Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1f5fb57d-6330-4b96-9b1b-aa8a15be7c24 · inbound
Model Context Protocol (MCP) Tool Descriptions Are Smelly! Towards Improving AI Agent Efficiency with Augmented MCP Tool Descriptions cites this paper.
Model Context Protocol (MCP) Tool Descriptions Are Smelly! Towards Improving AI Agent Efficiency with Augmented MCP Tool Descriptions GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 1
- Resolution
- unresolved
- no resolver link, observed 2026-08-02T23:04:27.582023Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 636e6893-c129-4c39-92e5-1d7814356e92 · inbound
Visual Persuasion: What Influences Decisions of Vision-Language Models? cites this paper.
Visual Persuasion: What Influences Decisions of Vision-Language Models? GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 2
- Resolution
- unresolved
- no resolver link, observed 2026-08-02T23:00:23.872130Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f15a8905-8872-441a-87bc-7f2580dfc07f · inbound
Framework of Thoughts: A Foundation Framework for Dynamic and Optimized Reasoning based on Chains, Trees, and Graphs cites this paper.
Framework of Thoughts: A Foundation Framework for Dynamic and Optimized Reasoning based on Chains, Trees, and Graphs GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 1
- Resolution
- unresolved
- no resolver link, observed 2026-08-02T22:33:33.861750Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 83a074f5-2df1-461d-9a63-4a6eadede682 · inbound
EvoSkill: Automated Skill Discovery for Multi-Agent Systems cites this paper.
EvoSkill: Automated Skill Discovery for Multi-Agent Systems GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 2
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-17T02:25:05.484147Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 960503e3-1c6d-446a-afeb-4cfe702425a0 · inbound
VeriInteresting: An Empirical Study of Model Prompt Interactions in Verilog Code Generation cites this paper.
VeriInteresting: An Empirical Study of Model Prompt Interactions in Verilog Code Generation GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 7
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-16T07:47:32.975917Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation b97683a4-9a49-48ad-9255-cd48a1a6d0df · inbound
DetPO: In-Context Learning with Multi-Modal LLMs for Few-Shot Object Detection cites this paper.
DetPO: In-Context Learning with Multi-Modal LLMs for Few-Shot Object Detection GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 2
- Resolution
- unresolved
- no resolver link, observed 2026-07-13T19:38:38.452093Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8565051a-8f62-49f4-a9ce-7da5eda6b0e7 · inbound
Meta-Harness: End-to-End Optimization of Model Harnesses cites this paper.
Meta-Harness: End-to-End Optimization of Model Harnesses GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 1
- Resolution
- verified exact
- local_arxiv, observed 2026-05-13T16:15:58.220703Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation dd14dada-e217-4a07-a23d-61907239af0e · inbound
Self-Optimizing Multi-Agent Systems for Deep Research cites this paper.
Self-Optimizing Multi-Agent Systems for Deep Research GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 1
- Resolution
- verified exact
- local_arxiv, observed 2026-05-13T18:18:06.477242Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation fcf2ba3c-5ccb-41c7-a104-71fc4dbc91a2 · inbound
Reflective Context Learning: Studying the Optimization Primitives of Context Space cites this paper.
Reflective Context Learning: Studying the Optimization Primitives of Context Space GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 1
- Resolution
- verified exact
- local_arxiv, observed 2026-05-13T20:33:16.969653Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation a6a1df23-9ce8-4f3b-86da-073803ce6f89 · inbound
Unlocking Prompt Infilling Capability for Diffusion Language Models cites this paper.
Unlocking Prompt Infilling Capability for Diffusion Language Models GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 1
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-13T17:33:02.512447Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation f321751c-bc81-4353-89d1-92aac741da5b · inbound
AI-Driven Research for Databases cites this paper.
AI-Driven Research for Databases GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 1
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T07:26:20.435474Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 17724478-dca1-45f1-9142-375988ed7842 · inbound
Automated Instruction Revision (AIR): A Structured Comparison of Task Adaptation Strategies for LLM cites this paper.
Automated Instruction Revision (AIR): A Structured Comparison of Task Adaptation Strategies for LLM GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 9
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T07:26:20.435474Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation d62ee929-6caf-45f5-ab0a-b708d632001f · inbound
ExecTune: Effective Steering of Black-Box LLMs with Guide Models cites this paper.
ExecTune: Effective Steering of Black-Box LLMs with Guide Models GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 3
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T07:26:20.435474Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation faa407f9-6753-4323-8871-fdc66971324a · inbound
Pioneer Agent: Continual Improvement of Small Language Models in Production cites this paper.
Pioneer Agent: Continual Improvement of Small Language Models in Production GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 2
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T07:26:20.435474Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 75894179-49eb-42f6-92b4-60b0858ce200 · inbound
M$^\star$: Every Task Deserves Its Own Memory Harness cites this paper.
M$^\star$: Every Task Deserves Its Own Memory Harness GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 1
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T07:26:20.435474Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 3b84bcf3-3ce6-4548-b10b-1c7845fc9c6e · inbound
M$^\star$: Every Task Deserves Its Own Memory Harness cites this paper.
M$^\star$: Every Task Deserves Its Own Memory Harness GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 1
- Resolution
- unresolved
- no resolver link, observed 2026-07-12T23:39:48.095337Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 883d40d1-d31b-4240-ac6b-2706fe47d250 · inbound
LLM-HYPER: Generative CTR Modeling for Cold-Start Ad Personalization via LLM-Based Hypernetworks cites this paper.
LLM-HYPER: Generative CTR Modeling for Cold-Start Ad Personalization via LLM-Based Hypernetworks GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 1
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T07:26:20.435474Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 1c7bd144-16de-48be-a68e-cd8215ad7373 · inbound
Agent-Aided Design for Dynamic CAD Models cites this paper.
Agent-Aided Design for Dynamic CAD Models GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 1
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T07:26:20.435474Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation e1a34f4d-dba1-45d5-9482-b1b1047cd240 · inbound
Harnessing Pre-Resolution Signals for Future Prediction Agents cites this paper.
Harnessing Pre-Resolution Signals for Future Prediction Agents GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 1
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T07:26:20.435474Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 82b0f1c1-8c8d-4f68-a88f-48f431475f1b · inbound
Harnessing Pre-Resolution Signals for Future Prediction Agents cites this paper.
Harnessing Pre-Resolution Signals for Future Prediction Agents GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 1
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T07:26:20.435474Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation ec4d044b-f41a-4544-8fe7-b667c7dc7752 · inbound
AdaExplore: Failure-Driven Adaptation and Diversity-Preserving Search for Efficient Kernel Generation cites this paper.
AdaExplore: Failure-Driven Adaptation and Diversity-Preserving Search for Efficient Kernel Generation GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 1
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T07:26:20.435474Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 1f7e0afb-d23e-4278-81c5-43b020e77efb · inbound
Co-evolving Agent Architectures and Interpretable Reasoning for Automated Optimization cites this paper.
Co-evolving Agent Architectures and Interpretable Reasoning for Automated Optimization GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 112
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T07:26:20.435474Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 0f73c1b7-2978-4c8e-b648-cbd9761ae0d1 · inbound
Prompt Optimization Enables Stable Algorithmic Collusion in LLM Agents cites this paper.
Prompt Optimization Enables Stable Algorithmic Collusion in LLM Agents GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 32
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T07:26:20.435474Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 6e4d32ba-24bc-45bd-934e-607289e37cb2 · inbound
How Far Are Video Models from True Multimodal Reasoning? cites this paper.
How Far Are Video Models from True Multimodal Reasoning? GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 1
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T07:26:20.435474Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 28b8052a-72ca-47b3-b205-632852f156ba · inbound
Evaluation-driven Scaling for Scientific Discovery cites this paper.
Evaluation-driven Scaling for Scientific Discovery GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 2
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T07:26:20.435474Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation c8a759ff-aa86-4572-9106-0b6aaa131433 · inbound
Supplement Generation Training for Enhancing Agentic Task Performance cites this paper.
Supplement Generation Training for Enhancing Agentic Task Performance GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 40
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T07:26:20.435474Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation a88ee554-6e48-435a-91d1-0e7010c59fa0 · inbound
PrismaDV: Automated Task-Aware Data Unit Test Generation cites this paper.
PrismaDV: Automated Task-Aware Data Unit Test Generation GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 2
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T07:26:20.435474Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 4a6856f1-20dd-47ce-b774-489369933259 · inbound
KISS Sorcar: A Stupidly-Simple General-Purpose and Software Engineering AI Assistant cites this paper.
KISS Sorcar: A Stupidly-Simple General-Purpose and Software Engineering AI Assistant GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 1
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T07:26:20.435474Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation f9987522-386f-4d86-9c09-2b334acd731a · inbound
KISS Sorcar: A Stupidly-Simple General-Purpose and Software Engineering AI Assistant cites this paper.
KISS Sorcar: A Stupidly-Simple General-Purpose and Software Engineering AI Assistant GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 1
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-01T09:05:36.452086Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 2dad7789-ff10-4130-baec-6e65f280931e · inbound
FitText: Evolving Agent Tool Ecologies via Memetic Retrieval cites this paper.
FitText: Evolving Agent Tool Ecologies via Memetic Retrieval GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 1
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T07:26:20.435474Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation e6493d93-f790-4a85-a533-c0a09e24c14b · inbound
FitText: Evolving Agent Tool Ecologies via Memetic Retrieval cites this paper.
FitText: Evolving Agent Tool Ecologies via Memetic Retrieval GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 2
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-01T00:45:12.442602Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation eb272716-1803-4394-a582-2f219bf251ca · inbound
FitText: Evolving Agent Tool Ecologies via Memetic Retrieval cites this paper.
FitText: Evolving Agent Tool Ecologies via Memetic Retrieval GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 2
- Resolution
- unresolved
- no resolver link, observed 2026-08-04T05:24:43.316701Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a2c60d01-527d-4fc6-8283-31d58bd5ebad · inbound
Back to the Beginning of Heuristic Design: Bridging Code and Knowledge with LLMs cites this paper.
Back to the Beginning of Heuristic Design: Bridging Code and Knowledge with LLMs GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 3
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T07:26:20.435474Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation d1c125eb-1c9b-4d57-926c-aa41596ad79b · inbound
SHARP: A Self-Evolving Human-Auditable Rubric Policy for Financial Trading Agents cites this paper.
SHARP: A Self-Evolving Human-Auditable Rubric Policy for Financial Trading Agents GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 8
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T07:26:20.435474Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation d8c03c93-f0a4-4046-81d4-d16731f04349 · inbound
A Reproducible Optimisation Protocol for Calibrating Prompt-Based Large Language Model Workflows in Evidence Synthesis cites this paper.
A Reproducible Optimisation Protocol for Calibrating Prompt-Based Large Language Model Workflows in Evidence Synthesis GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 3
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T07:26:20.435474Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation a0abad22-fd21-4e4a-afe0-ac8e0152cafb · inbound
SmellBench: Evaluating LLM Agents on Architectural Code Smell Repair cites this paper.
SmellBench: Evaluating LLM Agents on Architectural Code Smell Repair GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 1
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T07:26:20.435474Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 88786afa-c52a-4ca1-a9c6-bb4488c2c5cc · inbound
SmellBench: Evaluating LLM Agents on Architectural Code Smell Repair cites this paper.
SmellBench: Evaluating LLM Agents on Architectural Code Smell Repair GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 1
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-13T06:02:21.854852Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 6f030ce5-c356-44e1-b553-84a97a18a4d8 · inbound
PACEvolve++: Improving Test-time Learning for Evolutionary Search Agents cites this paper.
PACEvolve++: Improving Test-time Learning for Evolutionary Search Agents GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 1
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T07:26:20.435474Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 3999bbe4-6254-41a5-8cf1-168fc8df05b7 · inbound
CDS4RAG: Cyclic Dual-Sequential Hyperparameter Optimization for RAG cites this paper.
CDS4RAG: Cyclic Dual-Sequential Hyperparameter Optimization for RAG GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 1
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-12T08:31:26.584796Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation f278a6c3-474d-4675-b8d5-bdfb348ebd22 · inbound
FlashEvolve: Accelerating Agent Self-Evolution with Asynchronous Stage Orchestration cites this paper.
FlashEvolve: Accelerating Agent Self-Evolution with Asynchronous Stage Orchestration GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 2
- Resolution
- verified exact
- local_arxiv, observed 2026-05-12T07:51:43.244247Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 0af9473c-014b-4e9a-8337-41d34359f14b · inbound
SimWorld Studio: Automatic Environment Generation with Evolving Coding Agent for Embodied Agent Learning cites this paper.
SimWorld Studio: Automatic Environment Generation with Evolving Coding Agent for Embodied Agent Learning GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 1
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T07:26:20.435474Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation ad9301a6-c103-4100-9c71-a98eec2844a9 · inbound
SimWorld Studio: Automatic Environment Generation with Evolving Coding Agent for Embodied Agent Learning cites this paper.
SimWorld Studio: Automatic Environment Generation with Evolving Coding Agent for Embodied Agent Learning GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 1
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-14T21:32:59.528449Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 95e554ac-42b1-462c-bb15-548452e209ae · inbound
Continual Harness: Online Adaptation for Self-Improving Foundation Agents cites this paper.
Continual Harness: Online Adaptation for Self-Improving Foundation Agents GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 1
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T07:26:20.435474Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 4110332a-c378-4880-b686-c20bfc29fa00 · inbound
EGL-SCA: Structural Credit Assignment for Co-Evolving Instructions and Tools in Graph Reasoning Agents cites this paper.
EGL-SCA: Structural Credit Assignment for Co-Evolving Instructions and Tools in Graph Reasoning Agents GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 7
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T07:26:20.435474Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 27bdc9f7-3a88-4104-9416-f7083262fa83 · inbound
Evolving-RL: End-to-End Optimization of Experience-Driven Self-Evolving Capability within Agents cites this paper.
Evolving-RL: End-to-End Optimization of Experience-Driven Self-Evolving Capability within Agents GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 1
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T07:26:20.435474Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation e9a8124d-993c-4fbc-a7ba-cca36ce875dd · inbound
AssayBench: An Assay-Level Virtual Cell Benchmark for LLMs and Agents cites this paper.
AssayBench: An Assay-Level Virtual Cell Benchmark for LLMs and Agents GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 73
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T07:26:20.435474Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 2f2918f4-23ef-4900-ae60-34bd60d6dec2 · inbound
Shepherd: Enabling Programmable Meta-Agents via Reversible Agentic Execution Traces cites this paper.
Shepherd: Enabling Programmable Meta-Agents via Reversible Agentic Execution Traces GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 2
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T07:26:20.435474Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 57365df4-625d-4bf6-8279-510ffae605dd · inbound
Shepherd: Enabling Programmable Meta-Agents via Reversible Agentic Execution Traces cites this paper.
Shepherd: Enabling Programmable Meta-Agents via Reversible Agentic Execution Traces GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 2
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-06-30T22:25:06.848067Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 32aedda6-1f4f-4ad5-b72a-a898f1019f84 · inbound
Learning, Fast and Slow: Towards LLMs That Adapt Continually cites this paper.
Learning, Fast and Slow: Towards LLMs That Adapt Continually GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 2
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-13T05:07:18.423126Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation dc69152a-6191-4407-8e80-5c04635673bf · inbound
Learning, Fast and Slow: Towards LLMs That Adapt Continually cites this paper.
Learning, Fast and Slow: Towards LLMs That Adapt Continually GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 2
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-15T05:19:45.471682Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation ed620b98-14e0-4a56-9791-95ab86440d30 · inbound
REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations cites this paper.
REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 13
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-14T20:19:26.835172Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation a123dd06-e96b-43c9-b57b-154a7d10bc99 · inbound
Harnessing Agentic Evolution cites this paper.
Harnessing Agentic Evolution GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 1
- Resolution
- verified exact
- local_arxiv, observed 2026-05-14T17:57:32.855747Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 712561d2-c3ec-4132-bfe1-b2ddf0d14838 · inbound
GEAR: Genetic AutoResearch for Agentic Code Evolution cites this paper.
GEAR: Genetic AutoResearch for Agentic Code Evolution GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 1
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T06:25:07.736534Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 7a8db1c4-7ad1-4417-af2f-2f885d640c2c · inbound
Prompt Segmentation and Annotation Optimisation: Controlling LLM Behaviour via Optimised Segment-Level Annotations cites this paper.
Prompt Segmentation and Annotation Optimisation: Controlling LLM Behaviour via Optimised Segment-Level Annotations GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 1
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T01:33:27.797824Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 6a936216-a42d-4c78-8982-4b6992694229 · inbound
Hidden in Memory: Sleeper Memory Poisoning in LLM Agents cites this paper.
Hidden in Memory: Sleeper Memory Poisoning in LLM Agents GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 1
- Resolution
- malformed identifier
- local_arxiv, observed 2026-05-20T20:28:59.692285Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 93f235b7-4735-461c-b2d8-00b77929262f · inbound
Is One Score Enough? Rethinking the Evaluation of Sequentially Evolving LLM Memory cites this paper.
Is One Score Enough? Rethinking the Evaluation of Sequentially Evolving LLM Memory GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 1
- Resolution
- verified exact
- local_arxiv, observed 2026-05-19T16:47:40.522912Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 60bc2991-d292-4943-bf0e-5fb155db519b · inbound
Contexting as Recommendation: Evolutionary Collaborative Filtering for Context Engineering cites this paper.
Contexting as Recommendation: Evolutionary Collaborative Filtering for Context Engineering GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 3
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-20T19:08:54.383441Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 18efed18-f3ad-426f-bb6d-040d41862a93 · inbound
PQR: A Framework to Generate Diverse and Realistic User Queries that Elicit QA Agent Failures cites this paper.
PQR: A Framework to Generate Diverse and Realistic User Queries that Elicit QA Agent Failures GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 14
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-20T18:03:36.739830Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation dff08c2f-6cfb-4da3-b771-d3a2d7010794 · inbound
PluRule: A Benchmark for Moderating Pluralistic Communities on Social Media cites this paper.
PluRule: A Benchmark for Moderating Pluralistic Communities on Social Media GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 59
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-20T14:08:20.569771Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation ff6d6d18-74b5-476f-bb63-1c6fc777c865 · inbound
Code as Agent Harness cites this paper.
Code as Agent Harness GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 18
- Resolution
- verified exact
- local_arxiv, observed 2026-05-20T10:58:14.568744Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 8e0129ab-3083-475f-9eed-ec050eb24816 · inbound
Embedding by Elicitation: Dynamic Representations for Bayesian Optimization of System Prompts cites this paper.
Embedding by Elicitation: Dynamic Representations for Bayesian Optimization of System Prompts GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 21
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-20T10:23:11.985865Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation ed44b45c-4f53-4fd3-bb28-3acd419d7403 · inbound
PEEK: Context Map as an Orientation Cache for Long-Context LLM Agents cites this paper.
PEEK: Context Map as an Orientation Cache for Long-Context LLM Agents GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 3
- Resolution
- verified exact
- local_arxiv, observed 2026-05-20T05:53:04.700079Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation d3d74ca3-1c06-4c79-80d4-0170be1a3fdd · inbound
What Do Evolutionary Coding Agents Evolve? cites this paper.
What Do Evolutionary Coding Agents Evolve? GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 13
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-20T03:48:03.232342Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 79d232dd-4950-441c-a80b-a2ed430bb616 · inbound
SOLAR: A Self-Optimizing Open-Ended Autonomous Agent for Lifelong Learning and Continual Adaptation cites this paper.
SOLAR: A Self-Optimizing Open-Ended Autonomous Agent for Lifelong Learning and Continual Adaptation GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 53
- Resolution
- verified exact
- local_arxiv, observed 2026-05-21T11:24:08.712592Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation d0575f69-4592-4cdf-b54c-b1ac1b1a13f0 · inbound
Training Language Agents to Learn from Experience cites this paper.
Training Language Agents to Learn from Experience GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 1
- Resolution
- verified exact
- local_arxiv, observed 2026-05-21T07:14:02.609943Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation eb5c93aa-4af1-482b-a7cc-2fa88d56c02d · inbound
Declarative Data Services: Structured Agentic Discovery for Composing Data Systems cites this paper.
Declarative Data Services: Structured Agentic Discovery for Composing Data Systems GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 4
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-21T05:19:39.276308Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 0b6c890d-4ae0-4f86-9486-f8e4b0944fb6 · inbound
Declarative Data Services: Structured Agentic Discovery for Composing Data Systems cites this paper.
Declarative Data Services: Structured Agentic Discovery for Composing Data Systems GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 4
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-01T15:05:48.114745Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 6840fdb3-d9fd-4ddc-ba1f-daee2e2d7def · inbound
Predicting Performance of Symbolic and Prompt Programs with Examples cites this paper.
Predicting Performance of Symbolic and Prompt Programs with Examples GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 1
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-22T01:10:51.499617Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 28821d87-0fb4-4e4c-8d3e-dde5378d7a78 · inbound
Harnesses for Inference-Time Alignment over Execution Trajectories cites this paper.
Harnesses for Inference-Time Alignment over Execution Trajectories GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 45
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-22T01:04:32.016866Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 242e2530-399e-4fdf-8550-e532572f8579 · inbound
Residual Skill Optimization for Text-to-SQL Ensembles cites this paper.
Residual Skill Optimization for Text-to-SQL Ensembles GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 1
- Resolution
- verified exact
- local_arxiv, observed 2026-05-22T08:41:17.249550Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation f9f2421f-3c6c-4cf6-9f9c-61f2a2fb4631 · inbound
Adapting the Interface, Not the Model: Runtime Harness Adaptation for Deterministic LLM Agents cites this paper.
Adapting the Interface, Not the Model: Runtime Harness Adaptation for Deterministic LLM Agents GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 38
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-22T06:11:08.947674Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 7fff640f-62f5-4640-9a38-e133e5ca57f0 · inbound
Towards Direct Evaluation of Harness Optimizers via Priority Ranking cites this paper.
Towards Direct Evaluation of Harness Optimizers via Priority Ranking GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 15
- Resolution
- verified exact
- local_arxiv, observed 2026-05-22T06:14:40.339685Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation ceb62dcb-1401-4889-bac7-aa7d4bf61bdf · inbound
Evolutionary Multi-Task Optimization for LLM-Guided Program Discovery cites this paper.
Evolutionary Multi-Task Optimization for LLM-Guided Program Discovery GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 16
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-22T06:51:11.307969Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 99940870-e7cb-40c1-b7a7-91d2472b8323 · inbound
MOSS: Self-Evolution through Source-Level Rewriting in Autonomous Agent Systems cites this paper.
MOSS: Self-Evolution through Source-Level Rewriting in Autonomous Agent Systems GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 2
- Resolution
- verified exact
- local_arxiv, observed 2026-05-22T04:51:05.767775Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 3eb0c9d1-7ab4-42c4-917b-d982a956cbf9 · inbound
MOSS: Self-Evolution through Source-Level Rewriting in Autonomous Agent Systems cites this paper.
MOSS: Self-Evolution through Source-Level Rewriting in Autonomous Agent Systems GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 2
- Resolution
- verified exact
- local_arxiv, observed 2026-06-30T16:54:59.236822Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation b861d70b-05ea-43ce-8cdf-c8c9dd776ec6 · inbound
PACE: Two-Timescale Self-Evolution for Small Language Model Agents cites this paper.
PACE: Two-Timescale Self-Evolution for Small Language Model Agents GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 31
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-25T05:45:23.387791Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation c9b9ce02-316c-428d-b56d-4cefa1c5920a · inbound
SkillOpt: Executive Strategy for Self-Evolving Agent Skills cites this paper.
SkillOpt: Executive Strategy for Self-Evolving Agent Skills GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 13
- Resolution
- verified exact
- local_arxiv, observed 2026-05-25T03:55:21.092765Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation cad71035-c7e0-468d-b142-120a3d1e443e · inbound
SkillOpt: Executive Strategy for Self-Evolving Agent Skills cites this paper.
SkillOpt: Executive Strategy for Self-Evolving Agent Skills GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 13
- Resolution
- verified exact
- local_arxiv, observed 2026-06-30T16:35:12.857708Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 0d49c2a3-e52d-47bf-a8eb-945c8e3c4137 · inbound
Beyond Final Answers: Auditing Trajectory-Level Hallucinations in Multi-Agent Industrial Workflows cites this paper.
Beyond Final Answers: Auditing Trajectory-Level Hallucinations in Multi-Agent Industrial Workflows GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 1
- Resolution
- verified exact
- local_arxiv, observed 2026-06-30T15:44:48.486216Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation a5f4fbf7-d06f-4e7f-9505-18c7aa1ebd3f · inbound
SEAL: Synergistic Co-Evolution of Agents and Learning Environments cites this paper.
SEAL: Synergistic Co-Evolution of Agents and Learning Environments GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 32
- Resolution
- verified exact
- local_arxiv, observed 2026-06-30T13:44:40.919429Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation a924884d-3884-41ea-b85e-4c66deba8814 · inbound
Governed Evolution of Agent Runtimes through Executable Operational Cognition cites this paper.
Governed Evolution of Agent Runtimes through Executable Operational Cognition GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 7
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-06-29T16:33:39.498774Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation b9400af9-754e-49d0-886f-10d7df5003c0 · inbound
CORE: Contrastive Reflection Enables Rapid Improvements in Reasoning cites this paper.
CORE: Contrastive Reflection Enables Rapid Improvements in Reasoning GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 3
- Resolution
- verified exact
- local_arxiv, observed 2026-06-29T11:53:23.806385Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 45564cd7-23b6-48c1-bc0a-f8c1cc80492d · inbound
Learnable Assessment Skills for LLM-based Automated Scoring: Rubric Construction via Iterative Optimization cites this paper.
Learnable Assessment Skills for LLM-based Automated Scoring: Rubric Construction via Iterative Optimization GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 16
- Resolution
- verified exact
- local_arxiv, observed 2026-06-29T08:13:15.513859Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation b47d4bca-a4aa-4598-a968-ccfb0a1a8864 · inbound
Evolve as a Team: Collaborative Self-Evolution for LLM-based Multi-Agent Systems cites this paper.
Evolve as a Team: Collaborative Self-Evolution for LLM-based Multi-Agent Systems GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Reference 1
- Resolution
- verified exact
- local_arxiv, observed 2026-06-29T00:12:50.169301Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.