Paper Citation Record · LEDGER

SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision

As of 20 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 6 inbound Pith citation observations for arXiv:2606.01139.

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

pith.paper-citation-record.v1
2606.01139 v3

Coverage vector

measured 41 of 41 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-28T17:37:31.081762Z

measured 47 of 47 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 6 of 6 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T22:04:21.458110Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-09T03:45:55.375586Z

Reference resolution

41 of 41 outbound references displayed

verified exact16
verified fuzzy0
unresolved18
parse uncertain0
malformed identifier0
metadata mismatch7

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation bfcf1ca0-0a17-4800-bc2a-8a6964d2489f · outbound

This paper cites 2025 , howpublished =.

SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision 2025 , howpublished =

Reference 1

Resolution: unresolved; no resolver link, observed 2026-06-28T17:37:31.081762Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4bcf7427-235a-4520-b885-5e5a58077f8d · outbound

This paper cites A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications.

SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-06-28T17:42:24.801841Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 6b824e7b-30d1-4873-94c7-f7fbb5645786 · outbound

This paper cites SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks.

SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-06-28T17:42:24.831662Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 16ef4a56-d1aa-4ef2-a573-3b94f9c0c03b · outbound

This paper cites How Well Do Agentic Skills Work in the Wild: Benchmarking LLM Skill Usage in Realistic Settings.

SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision How Well Do Agentic Skills Work in the Wild: Benchmarking LLM Skill Usage in Realistic Settings

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-06-28T17:42:24.799127Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3f7fc867-0e93-455d-9c38-1e4a7300c400 · outbound

This paper cites Swe-skills-bench: Do agent skills actually help in real-world software engineering?.

SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision Swe-skills-bench: Do agent skills actually help in real-world software engineering?

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-06-28T17:42:24.816729Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 9fb18ced-734b-41be-803d-fad0f5e24d30 · outbound

This paper cites SkillX: Automatically Constructing Skill Knowledge Bases for Agents.

SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision SkillX: Automatically Constructing Skill Knowledge Bases for Agents

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-06-28T17:42:24.822524Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 518d93b5-eb29-4323-beec-e3da66e4c463 · outbound

This paper cites SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning.

SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-06-28T17:42:24.821822Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b5c8730b-9e81-4701-b55a-045d1a32d7dd · outbound

This paper cites Skill-Pro: Learning Reusable Skills from Experience via Non-Parametric PPO for LLM Agents.

SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision Skill-Pro: Learning Reusable Skills from Experience via Non-Parametric PPO for LLM Agents

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-06-28T17:42:24.840642Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 629c160b-1735-4b3b-a20b-cf3d12a0e123 · outbound

This paper cites MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents.

SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-06-28T17:42:24.820120Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 35d027ed-39e6-46ed-8da9-e4950b59d5ba · outbound

This paper cites SkillClaw: Let Skills Evolve Collectively with Agentic Evolver.

SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision SkillClaw: Let Skills Evolve Collectively with Agentic Evolver

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-06-28T17:42:24.838931Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 50482ff2-531b-4f92-9561-68bd7aeaf82c · outbound

This paper cites Autoskill: Experience-driven lifelong learning via skill self-evolution.

SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision Autoskill: Experience-driven lifelong learning via skill self-evolution

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-06-28T17:42:24.838199Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 7aa26e82-72cc-4820-ace5-77b380655e57 · outbound

This paper cites EvoSkill: Automated Skill Discovery for Multi-Agent Systems.

SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision EvoSkill: Automated Skill Discovery for Multi-Agent Systems

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-06-28T17:42:24.815251Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 0fa6c7d1-4613-4bcc-af31-a7994ac33fce · outbound

This paper cites 2026 , eprint =.

SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision 2026 , eprint =

Reference 13

Resolution: unresolved; no resolver link, observed 2026-06-28T17:37:31.081762Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03c4cd4a-55f0-4425-aae4-b785eed53040 · outbound

This paper cites Qwen3 Technical Report.

SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision Qwen3 Technical Report

Reference 14

Resolution: metadata mismatch; local_arxiv, observed 2026-06-28T17:42:24.824192Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation a6f9e634-f82e-4068-88ec-7881a5277258 · outbound

This paper cites Kimi K2: Open Agentic Intelligence.

SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision Kimi K2: Open Agentic Intelligence

Reference 15

Resolution: metadata mismatch; local_arxiv, observed 2026-06-28T17:42:24.841373Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 53d0d04a-ab5d-4384-a208-acf617eaaa1b · outbound

This paper cites 2026 , month =.

SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision 2026 , month =

Reference 16

Resolution: unresolved; no resolver link, observed 2026-06-28T17:37:31.081762Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ceb459b8-7aee-4637-b1c2-e106450e6c15 · outbound

This paper cites OpenAI GPT-5 System Card.

SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision OpenAI GPT-5 System Card

Reference 17

Resolution: metadata mismatch; local_arxiv, observed 2026-06-28T17:42:24.846322Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c55c7949-4894-4ed1-afd2-8ea153dc71c8 · outbound

This paper cites 2026 , howpublished =.

SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision 2026 , howpublished =

Reference 18

Resolution: unresolved; no resolver link, observed 2026-06-28T17:37:31.081762Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be3c8c19-4884-4989-a0e9-1684f9ea2d06 · outbound

This paper cites ALFWorld: Aligning Text and Embodied Environments for Interactive Learning.

SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision ALFWorld: Aligning Text and Embodied Environments for Interactive Learning

Reference 19

Resolution: metadata mismatch; local_arxiv, observed 2026-06-28T17:42:24.819427Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 5c648665-3df1-4517-98b4-606e3bd9aa54 · outbound

This paper cites 2026 , eprint =.

SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision 2026 , eprint =

Reference 20

Resolution: unresolved; no resolver link, observed 2026-06-28T17:37:31.081762Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10c824cd-99df-4f83-a778-b57c6683c688 · outbound

This paper cites Agentvista: Evaluating multimodal agents in ultra- challenging realistic visual scenarios.arXiv preprint arXiv:2602.23166.

SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision Agentvista: Evaluating multimodal agents in ultra- challenging realistic visual scenarios.arXiv preprint arXiv:2602.23166

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-06-28T17:42:24.790410Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f68cadb1-9afe-42b8-a97b-1b56fd76af19 · outbound

This paper cites 10 Guoqing Ma, Jia Zhu, Hanghui Guo, Weijie Shi, Yue Cui, Jiawei Shen, Zilong Li, and Yidan Liang.

SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision 10 Guoqing Ma, Jia Zhu, Hanghui Guo, Weijie Shi, Yue Cui, Jiawei Shen, Zilong Li, and Yidan Liang

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-06-28T17:42:24.832473Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 0d9f9188-648e-4519-95fb-e4a7f4d6076e · outbound

This paper cites 2025 , eprint =.

SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision 2025 , eprint =

Reference 23

Resolution: unresolved; no resolver link, observed 2026-06-28T17:37:31.081762Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af95bc4e-b454-402a-9fde-122656f71564 · outbound

This paper cites 2025 , eprint =.

SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision 2025 , eprint =

Reference 24

Resolution: unresolved; no resolver link, observed 2026-06-28T17:37:31.081762Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57f5fa6b-613c-4735-a6a2-d74d8032bbf6 · outbound

This paper cites 2025 , eprint =.

SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision 2025 , eprint =

Reference 25

Resolution: unresolved; no resolver link, observed 2026-06-28T17:37:31.081762Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35b23ff5-0b50-4b10-a887-7d8b857a4e8a · outbound

This paper cites Proceedings of the AAAI Conference on Artificial Intelligence , volume =.

SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision Proceedings of the AAAI Conference on Artificial Intelligence , volume =

Reference 26

Resolution: unresolved; no resolver link, observed 2026-06-28T17:37:31.081762Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eced21fe-ad98-494f-8987-3c9e9fc0d060 · outbound

This paper cites DeepSeek-V3 Technical Report.

SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision DeepSeek-V3 Technical Report

Reference 27

Resolution: metadata mismatch; local_arxiv, observed 2026-06-28T17:42:24.802773Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 274952b7-81ad-4730-9d30-175a2f0b8ecf · outbound

This paper cites 2025 , eprint =.

SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision 2025 , eprint =

Reference 28

Resolution: unresolved; no resolver link, observed 2026-06-28T17:37:31.081762Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49f2244f-6401-4d52-8d9c-93478f7ac09b · outbound

This paper cites Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing , pages =.

SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing , pages =

Reference 29

Resolution: unresolved; no resolver link, observed 2026-06-28T17:37:31.081762Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a82f869b-56c6-4b09-97bf-617ccd6aec33 · outbound

This paper cites Advances in Neural Information Processing Systems , volume =.

SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision Advances in Neural Information Processing Systems , volume =

Reference 30

Resolution: unresolved; no resolver link, observed 2026-06-28T17:37:31.081762Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f2a0958-ef88-4ce9-a4f7-4381f53db483 · outbound

This paper cites 2026 , eprint =.

SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision 2026 , eprint =

Reference 31

Resolution: unresolved; no resolver link, observed 2026-06-28T17:37:31.081762Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5753032-1f86-466f-9cbe-3cde288cb9a4 · outbound

This paper cites MemGPT: Towards LLMs as Operating Systems.

SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision MemGPT: Towards LLMs as Operating Systems

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-06-28T17:42:24.826842Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation d3badcb9-fd1a-4c3a-bd29-f5fca7878990 · outbound

This paper cites MemoryBank: Enhancing Large Language Models with Long-Term Memory.

SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision MemoryBank: Enhancing Large Language Models with Long-Term Memory

Reference 33

Resolution: metadata mismatch; local_arxiv, observed 2026-06-28T17:42:24.808366Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 50aa82fb-c4c2-465a-b44a-f7e840d823a5 · outbound

This paper cites G\"odel Agent: A Self-Referential Agent Framework for Recursive Self-Improvement.

SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision G\"odel Agent: A Self-Referential Agent Framework for Recursive Self-Improvement

Reference 34

Resolution: metadata mismatch; arxiv_id, observed 2026-06-28T17:42:24.835258Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b668890d-5ffb-436a-876d-a2c4463c0a73 · outbound

This paper cites doi:10.48550/arXiv.2510.24505 , url =.

SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision doi:10.48550/arXiv.2510.24505 , url =

Reference 35

Resolution: verified exact; arxiv_id, observed 2026-06-28T17:42:24.828181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 25083457-01b7-40e9-8cea-d86a33805a4f · outbound

This paper cites 2025 , eprint =.

SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision 2025 , eprint =

Reference 36

Resolution: unresolved; no resolver link, observed 2026-06-28T17:37:31.081762Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d54ea70-1bc1-455f-8ba2-ffa73ef97c66 · outbound

This paper cites 2025 , eprint =.

SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision 2025 , eprint =

Reference 37

Resolution: unresolved; no resolver link, observed 2026-06-28T17:37:31.081762Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3ed50a2-9f3f-4266-ae91-15844d83e50d · outbound

This paper cites 2025 , eprint =.

SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision 2025 , eprint =

Reference 38

Resolution: unresolved; no resolver link, observed 2026-06-28T17:37:31.081762Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9811e835-499a-47c1-b28e-bd19318e05b2 · outbound

This paper cites XSkill: Continual Learning from Experience and Skills in Multimodal Agents.

SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision XSkill: Continual Learning from Experience and Skills in Multimodal Agents

Reference 39

Resolution: verified exact; arxiv_id, observed 2026-07-02T02:17:26.572211Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1ed76602-0515-4f29-aca6-1d130f94787f · outbound

This paper cites 2026 , eprint =.

SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision 2026 , eprint =

Reference 40

Resolution: unresolved; no resolver link, observed 2026-06-28T17:37:31.081762Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee0d449e-77b1-4835-8256-b72d9c563cbb · outbound

This paper cites 2026 , eprint =.

SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision 2026 , eprint =

Reference 41

Resolution: unresolved; no resolver link, observed 2026-06-28T17:37:31.081762Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 57d0a835-f9ce-48f8-a932-00ec0a3f9521 · inbound

Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loops cites this paper.

Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loops SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision

Reference 75

Resolution: verified exact; local_arxiv, observed 2026-07-09T03:45:55.376945Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 9521f4d7-2342-4664-8f4d-1a88f3503ef3 · inbound

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills cites this paper.

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-01T04:28:46.657137Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83b1e150-c507-487e-bffa-8acb8ae2a665 · inbound

Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds cites this paper.

Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-05T04:26:29.316067Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62a3a2b6-d3a9-4617-95f5-b5edce64e164 · inbound

SkillTV-Bench: Benchmarking How Well Judges Perform on Skill-Augmented Agentic Execution cites this paper.

SkillTV-Bench: Benchmarking How Well Judges Perform on Skill-Augmented Agentic Execution SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-08T10:20:42.055705Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f91e7c95-822a-4a1c-a71a-0ca97d9739ef · inbound

SkillZip: Evaluation-Free Skill Compression for Self-Evolving Agents by Discovering Reusable Structure cites this paper.

SkillZip: Evaluation-Free Skill Compression for Self-Evolving Agents by Discovering Reusable Structure SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-12T10:46:16.563633Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c01c65cf-4d9c-4ebd-b850-5a3b098d4d6d · inbound

Practice Makes Unsafe: Skill Misevolution in Self-Improving LLM Agents cites this paper.

Practice Makes Unsafe: Skill Misevolution in Self-Improving LLM Agents SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T22:04:21.458110Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.