Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-06-28T01:41:32.686349Z
Paper Citation Record · LEDGER
As of 4 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 3 inbound Pith citation observations for arXiv:2606.05922.
A citation records a reference. It does not transfer a finding from one paper to another.
Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-06-28T01:41:32.686349Z
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-04T06:34:03.388597+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-02T07:01:21.515063Z
A source-named dated measurement, never combined with another source.
Source: cited_works
41 of 41 outbound references displayed
External citation measurements
No source-named external measurement is stored.
Observation ebdbb5be-f447-4acd-ab0e-212b6ac70a40 · outbound
Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?
Reference 1
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 55465106-bec4-4720-b2aa-cf645776df6d · outbound
Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference Sleep-time Compute: Beyond Inference Scaling at Test-time
Reference 2
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 81bd0093-ad73-469f-b285-a91e5e428d88 · outbound
Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference MemGPT: Towards LLMs as Operating Systems
Reference 3
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation c4b80b1b-cd54-4997-acac-9dfa8e35ff11 · outbound
Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference Can LLMs Refuse Questions They Do Not Know? Measuring Knowledge-Aware Refusal in Factual Tasks
Reference 4
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation fac77919-24f2-46e5-8b08-16280283123d · outbound
Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference Unresolved cited work
Reference 5
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2f14be69-7239-4561-aef7-71241ea69dc2 · outbound
Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference Unresolved cited work
Reference 6
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 76880001-5e73-4159-93bf-9097a5cf795b · outbound
Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference For code repair tasks, modify files directly under ,→task/repo/
Reference 7
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e51f5a6c-b4c3-427f-bb6f-7df3ad4e2475 · outbound
Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference difficulty
Reference 8
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3c59a992-6b5b-4496-8865-35a44fec20e7 · outbound
Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference Unresolved cited work
Reference 9
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 94a1f7a9-ae9a-4a5a-8ee8-7df56500492e · outbound
Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference Unresolved cited work
Reference 10
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 73a0a751-dfc7-4979-8879-5073c75c5686 · outbound
Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference Unresolved cited work
Reference 11
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9781ba40-00df-4200-9db7-649fc391d526 · outbound
Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference task_id":
Reference 12
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f47b22d5-27a6-44f8-86cd-7fb95b9517cc · outbound
Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference Unresolved cited work
Reference 13
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 75b0bd7e-5cb7-4114-ad05-237b82e7d95e · outbound
Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference Higher severity means the diagnosis should influence optimization ,→more strongly
Reference 14
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4456d7ec-93d4-4ee4-8610-f1fb4cf366a6 · outbound
Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference Unresolved cited work
Reference 15
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c09d3f5a-306f-4279-b9d2-fbcb0f4c8b89 · outbound
Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference Unresolved cited work
Reference 16
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 33e676f8-8f37-454a-80ec-6a6c0aaf0704 · outbound
Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference Unresolved cited work
Reference 17
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d215bdd0-fcd8-451d-8c9a-2960acb3694a · outbound
Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference 15 When done, send the changes and your rationale as your final message
Reference 18
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c983a1b6-c3e9-4872-9447-47d4bbe2879d · outbound
Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference Unresolved cited work
Reference 19
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 17181835-c2a0-4f2e-ba15-2bb5967d65bc · outbound
Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference value": <integer in [-10, 10]>,
Reference 20
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e4704a67-5568-4db0-9699-cbc5089d38ee · outbound
Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference Unresolved cited work
Reference 21
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f1bd639c-c7e6-4bed-86d7-d093df49e0fd · outbound
Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference Unresolved cited work
Reference 22
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1756988e-2e4c-45c6-b1a3-7b4f6db6f3e5 · outbound
Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference Unresolved cited work
Reference 23
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8245a833-48d1-4c09-b11c-75e37fb4c636 · outbound
Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference Prefer adapting proven behavior over guessing
Reference 24
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0d222104-32c3-41d8-91f0-f241bb727475 · outbound
Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference Follow stored data back to user-visible artifacts, config values back to their runtime representation, and wrappers back to the implementation that actually executes
Reference 25
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4c306f52-79b3-4610-896c-250126facfa0 · outbound
Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference Keep generated files, caches, temporary smoke tests, and local environment output out of the submitted diff
Reference 26
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 40993b36-6015-4c42-b52f-37cfc94ec7af · outbound
Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference Syntax checks are not enough: run at least one focused smoke that calls every new public route/function/method and covers each explicit failure/edge condition in the prompt
Reference 27
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 36346fe2-0b28-4529-b65d-751183dc660b · outbound
Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference 0"‘ and ‘
Reference 28
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8f3ed524-facb-411e-8707-97efce58b87d · outbound
Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference Unresolved cited work
Reference 29
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 93b73c34-8847-42ac-802a-666af04295e1 · outbound
Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference It avoids quoting failures and leaves a useful command trail in ,→‘/host-ws‘
Reference 30
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a7e8c3b6-2200-4a3f-80c6-b282b764639a · outbound
Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference Readable
Reference 31
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 08c43fb2-73ca-4388-8e5f-701ad6d8745f · outbound
Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference by ,→making queries
Reference 32
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation edec6ede-d5d3-4b0f-9252-f97164a65e0f · outbound
Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference Unresolved cited work
Reference 33
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation fe36f422-2f2e-4f91-ae4e-86a9617d682b · outbound
Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference Avoid dumping the ,→full ‘are.py list‘ output unless the catalog is missing or corrupt
Reference 34
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b322b816-c386-479b-8034-1b2eea1a4d26 · outbound
Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference today",
Reference 35
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9d8dc803-ea5e-4e71-837f-85a15f6e51d3 · outbound
Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference Unresolved cited work
Reference 36
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d6a5e2e7-96dc-426c-977e-18cea20325de · outbound
Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference Then email X that the cab was ordered
Reference 37
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 902cb904-7aa3-488d-9eb7-96c77ef603a5 · outbound
Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference Unresolved cited work
Reference 38
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c9c4054c-3c62-40ee-894d-e208319185f2 · outbound
Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference Unresolved cited work
Reference 39
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8edf3340-1e64-4429-986c-a4ef35ba9633 · outbound
Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference Complete unambiguous parts, report the ,→unresolved blocker to the user through AgentUserInterface, and do not ,→perform the ambiguous write
Reference 40
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6ea461d8-7b80-4086-b25d-1cf7e4655f05 · outbound
Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference reply at 2024-10-15 ,→07:04:00; add to cart at 07:04:30
Reference 41
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation cd97c3a0-7275-4ffe-8e6e-69d66e708e9d · inbound
Learning to Control LLM Agent Harnesses with Offline Reinforcement Learning Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference
Reference 4
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 75082944-7ea8-4635-a2f9-65ab8894e5ce · inbound
Phantom Guardrails: When Self-Improving Agent Harnesses Fix Failures That Never Happened Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference
Reference 15
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7a06ea2b-ee63-443c-846c-5f6bdc34c492 · inbound
Why Git Is the Memory Solution for the Agentic Development Lifecycle Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference
Reference 2
Source-reported events for the cited work
Unavailable: canonical work link unavailable.