Paper Citation Record · LEDGER

GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks

As of 19 August 2026, this Paper Citation Record lists 36 of 36 outbound references and 0 inbound Pith citation observations for arXiv:2608.03764.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2608.03764 v1

Coverage vector

measured 36 of 36 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T13:09:08.945549Z

measured 36 of 36 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

36 of 36 outbound references displayed

verified exact6
verified fuzzy16
unresolved14
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation f18c76b0-c63b-49c9-a1cd-f674f1596b8a · outbound

This paper cites A survey of self-evolving agents: What, when, how, and where to evolve on the path to artificial super intelligence.Transactions on Machine Learning Research, 2026.

GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks A survey of self-evolving agents: What, when, how, and where to evolve on the path to artificial super intelligence.Transactions on Machine Learning Research, 2026

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:09:13.404964Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 323bfd6f-ea54-47e9-ac69-82a1372d9fb0 · outbound

This paper cites A comprehensive survey of continual learning: Theory, method and application.IEEE Transactions on Pattern Analysis and Machine Intelligence, 46:5362–5383, 2024.

GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks A comprehensive survey of continual learning: Theory, method and application.IEEE Transactions on Pattern Analysis and Machine Intelligence, 46:5362–5383, 2024

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:09:13.187967Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 1181aecd-ac95-4f6c-a8f9-eadee7eb2edf · outbound

This paper cites Reflexion: Language 10 agents with verbal reinforcement learning.

GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks Reflexion: Language 10 agents with verbal reinforcement learning

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:09:12.995487Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation fcbed200-7f4a-4a32-b7ea-16b99f87d0d8 · outbound

This paper cites ExpeL: LLM agents are experiential learners.

GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks ExpeL: LLM agents are experiential learners

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:09:12.812322Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation dd4e9245-4fe1-43c6-956b-3a4fb1d012ac · outbound

This paper cites G¨ odel machines: Fully self-referential optimal universal self-improvers.

GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks G¨ odel machines: Fully self-referential optimal universal self-improvers

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:09:12.636324Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 14365f4e-6c3d-4859-88e1-193e66514baf · outbound

This paper cites Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents.

GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-05T13:09:06.410037Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e58e4473-b390-4895-91ea-d33b71e320b1 · outbound

This paper cites EdgeBench: Unveiling Scaling Laws of Learning from Real-World Environments.

GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks EdgeBench: Unveiling Scaling Laws of Learning from Real-World Environments

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-08-05T13:09:10.439914Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b973ed99-b7d1-436c-ad94-e6aae7b54064 · outbound

This paper cites SkillFlow:Benchmarking Lifelong Skill Discovery and Evolution for Autonomous Agents.

GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks SkillFlow:Benchmarking Lifelong Skill Discovery and Evolution for Autonomous Agents

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-05T13:09:06.622558Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f7172b8-3e07-4067-818d-4c13b2c0a6df · outbound

This paper cites SEA-Eval: A Benchmark for Evaluating Self-Evolving Agents Beyond Episodic Assessment.

GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks SEA-Eval: A Benchmark for Evaluating Self-Evolving Agents Beyond Episodic Assessment

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-05T13:09:06.712982Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7bba5e16-9abd-448f-9f42-095f16815c49 · outbound

This paper cites EvoAgentBench: Benchmarking Agent Self-Evolution via Ability Transfer.

GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks EvoAgentBench: Benchmarking Agent Self-Evolution via Ability Transfer

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-08-05T13:09:10.241179Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0bff3dce-b501-4881-8b3c-7e55c52d112a · outbound

This paper cites BenchTrace: A Benchmark for Testing Reflection Ability and Controlled Evolution in LLM Agents.

GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks BenchTrace: A Benchmark for Testing Reflection Ability and Controlled Evolution in LLM Agents

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-08-05T13:09:10.035784Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b890d3ec-6d7e-4343-9ca9-a8ffe333cb3c · outbound

This paper cites Jimenez, John Yang, Alexander Wettig, Shunyu Yao, Kexin Pei, Ofir Press, and Karthik R.

GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks Jimenez, John Yang, Alexander Wettig, Shunyu Yao, Kexin Pei, Ofir Press, and Karthik R

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:09:12.444324Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 9f14d8b9-53a5-414a-8c41-9eeb6008326e · outbound

This paper cites Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces.

GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-05T13:09:07.068377Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00f87561-2eb7-4b66-b1b7-906fecd4cf7b · outbound

This paper cites Kim, Patrick Chao, Samuel Miserendino, Gildas Chabot, David Li, Michael Sharman, Alexandra Barr, Amelia Glaese, and Jerry Tworek.

GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks Kim, Patrick Chao, Samuel Miserendino, Gildas Chabot, David Li, Michael Sharman, Alexandra Barr, Amelia Glaese, and Jerry Tworek

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:09:12.267688Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation dea83764-8c4c-4cdf-91a4-e9634c9da93c · outbound

This paper cites SOP-Bench: Complex industrial SOPs for evaluating LLM agents.CoRR, abs/2506.08119, 2025.

GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks SOP-Bench: Complex industrial SOPs for evaluating LLM agents.CoRR, abs/2506.08119, 2025

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-05T13:09:07.219151Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d38aca4-dcf1-4b29-a09e-2df355d7f387 · outbound

This paper cites JobBench: Aligning agent work with human will.CoRR, 2026.

GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks JobBench: Aligning agent work with human will.CoRR, 2026

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:09:12.087003Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b54a4f99-b720-4dd9-8b09-1b45e80194d1 · outbound

This paper cites LiveBench: A challenging, contamination-limited LLM benchmark.

GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks LiveBench: A challenging, contamination-limited LLM benchmark

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:09:11.905290Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation d3d0c413-acb6-4dc0-9ffa-a2d08416ec68 · outbound

This paper cites AntiLeakBench: Preventing data contamination by automatically constructing benchmarks with updated real-world knowledge.

GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks AntiLeakBench: Preventing data contamination by automatically constructing benchmarks with updated real-world knowledge

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:09:11.681345Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 02b81de1-9fb0-4369-a57c-d9e5093eda5e · outbound

This paper cites Benchmarking large language models under data contamination: A survey from static to dynamic evaluation.

GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks Benchmarking large language models under data contamination: A survey from static to dynamic evaluation

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:09:11.503412Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 466b1304-ad71-412e-afaa-f12d86c8e29f · outbound

This paper cites Voyager: An open-ended embodied agent with large language models.Transactions on Machine Learning Research, 2024.

GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks Voyager: An open-ended embodied agent with large language models.Transactions on Machine Learning Research, 2024

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-05T13:09:07.681368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 432c6128-8d9b-467c-aa7e-f636ec66fb39 · outbound

This paper cites GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning.

GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-05T13:09:07.776106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b224103-8426-4d03-94a3-98f4b0c21057 · outbound

This paper cites RSIBench-Data: Benchmarking Data-Centric Research for Recursive Self-Improvement.

GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks RSIBench-Data: Benchmarking Data-Centric Research for Recursive Self-Improvement

Reference 22

Resolution: verified exact; local_arxiv, observed 2026-08-05T13:09:09.800507Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation c020f1da-c0bf-453c-9e38-3b5777b6d402 · outbound

This paper cites LLMigrate: Transforming "Lazy" Large Language Models into Efficient Source Code Migrators.

GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks LLMigrate: Transforming "Lazy" Large Language Models into Efficient Source Code Migrators

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-05T13:09:07.958750Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ddaf9f13-1905-4dc5-8f81-6bc041788c33 · outbound

This paper cites Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al.

GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:09:11.316441Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7a5f93ed-3540-4308-b8cd-f2696d2e7fb1 · outbound

This paper cites Reward Is Enough: LLMs Are In-Context Reinforcement Learners.

GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks Reward Is Enough: LLMs Are In-Context Reinforcement Learners

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-05T13:09:08.132427Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42494414-8e2c-40b5-8a79-e309ce44dc0a · outbound

This paper cites SaaS-Bench: Can Computer-Use Agents Leverage Real-World SaaS to Solve Professional Workflows?.

GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks SaaS-Bench: Can Computer-Use Agents Leverage Real-World SaaS to Solve Professional Workflows?

Reference 26

Resolution: verified exact; local_arxiv, observed 2026-08-05T13:09:09.574586Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 73bf45cd-9e53-4a20-993e-0d8569b9efd5 · outbound

This paper cites $\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment.

GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks $\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-05T13:09:08.293502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8e6ed68-1157-4b7b-923c-3502c1b24722 · outbound

This paper cites CHI-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows?.

GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks CHI-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows?

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-08-05T13:09:09.387826Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation d33b646e-a2ec-41a9-8144-9e8dea90379c · outbound

This paper cites MedAgentBench: A Realistic Virtual EHR Environment to Benchmark Medical LLM Agents.

GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks MedAgentBench: A Realistic Virtual EHR Environment to Benchmark Medical LLM Agents

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-05T13:09:08.491553Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61c8d1c8-f899-4566-9e1c-5e74ed2fafb2 · outbound

This paper cites Pollard, Alistair Johnson, Edward Choi, Yugang Jia, and Jong Ha Lee.

GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks Pollard, Alistair Johnson, Edward Choi, Yugang Jia, and Jong Ha Lee

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-05T13:09:08.590394Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3e56211-5923-4e10-ae1c-c9a8c05b391c · outbound

This paper cites Harvey LAB: The legal agent benchmark.

GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks Harvey LAB: The legal agent benchmark

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:09:11.114346Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 9fb19912-667d-41b2-ae54-ad01b4e6a465 · outbound

This paper cites SpreadsheetBench: Towards challenging real world spreadsheet manipulation.

GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks SpreadsheetBench: Towards challenging real world spreadsheet manipulation

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:09:10.949683Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8ad928f2-3a8f-4e0d-82bf-0e40e05a660a · outbound

This paper cites InfiAgent-DABench: Evaluating agents on data analysis tasks.

GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks InfiAgent-DABench: Evaluating agents on data analysis tasks

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:09:10.769801Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation d0420d3e-d12a-4e27-afe8-3df81dc3b39d · outbound

This paper cites BIRD-INTERACT: Re-imagining text-to-SQL evaluation for large language models via lens of dynamic interactions.CoRR, abs/2510.05318, 2025.

GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks BIRD-INTERACT: Re-imagining text-to-SQL evaluation for large language models via lens of dynamic interactions.CoRR, abs/2510.05318, 2025

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-05T13:09:08.848101Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 927f1840-81d4-4634-84c2-ddc6ccafb9b2 · outbound

This paper cites LiveSQLBench: A dynamic and contamination-free benchmark for evaluating LLMs on real-world text-to-SQL tasks.https://github.com/bird-bench/livesqlbench, 2025.

GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks LiveSQLBench: A dynamic and contamination-free benchmark for evaluating LLMs on real-world text-to-SQL tasks.https://github.com/bird-bench/livesqlbench, 2025

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:09:10.620259Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 092207ef-8fef-46f4-ad6b-2ef6e2675dbe · outbound

This paper cites WorkBench: a Benchmark Dataset for Agents in a Realistic Workplace Setting.

GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks WorkBench: a Benchmark Dataset for Agents in a Realistic Workplace Setting

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-05T13:09:08.945549Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.