Co-Evolving Skill Generation and Policy Optimization | Paper Citation Record

Observation 87283b5b-078c-4e8d-be7b-1daf5bfc13ce · outbound

This paper cites Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering.

Co-Evolving Skill Generation and Policy Optimization Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-07-02T22:57:25.897250Z

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 638b214c-087f-4744-b9ce-c933abdeb97f · outbound

This paper cites Memento-skills: Let agents design agents.

Co-Evolving Skill Generation and Policy Optimization Memento-skills: Let agents design agents

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-07-02T22:47:26.451969Z

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 a7182a07-895d-418b-8882-1874d3f53b4c · outbound

This paper cites Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents.

Co-Evolving Skill Generation and Policy Optimization Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-07-02T22:57:25.841643Z

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 0d0cbeb4-d1ea-4e5f-869e-d0ab8c28e771 · outbound

This paper cites AEL: Agent Evolving Learning for Open-Ended Environments.

Co-Evolving Skill Generation and Policy Optimization AEL: Agent Evolving Learning for Open-Ended Environments

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-07-02T22:57:25.884218Z

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 76d76fec-c167-4b3f-9fb7-5296f2031039 · outbound

This paper cites Arunkumar, G.

Co-Evolving Skill Generation and Policy Optimization Arunkumar, G

Reference 5

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T22:47:26.424854Z

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 f5b1c40d-9b05-4f54-b95d-ebeb54d0a35e · outbound

This paper cites The Landscape of Agentic Reinforcement Learning for LLMs: A Survey.

Co-Evolving Skill Generation and Policy Optimization The Landscape of Agentic Reinforcement Learning for LLMs: A Survey

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-07-02T22:47:26.427426Z

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 0497ade2-9dfe-4459-8852-8bb12cc15391 · outbound

This paper cites Agentic large language models, a survey.Journal of Artificial Intelligence Research, 84, 2025.

Co-Evolving Skill Generation and Policy Optimization Agentic large language models, a survey.Journal of Artificial Intelligence Research, 84, 2025

Reference 7

Resolution: unresolved; no resolver link, observed 2026-06-27T18:37:00.015083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8be65db4-28ea-48bf-982b-fca614b9bafc · outbound

This paper cites Agentic Reasoning for Large Language Models.

Co-Evolving Skill Generation and Policy Optimization Agentic Reasoning for Large Language Models

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-07-02T22:47:26.432494Z

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 d1a10e44-d33a-427c-8c03-0bbaf2d76db8 · outbound

This paper cites Think Deep, Not Just Long: Measuring LLM Reasoning Effort via Deep-Thinking Tokens.

Co-Evolving Skill Generation and Policy Optimization Think Deep, Not Just Long: Measuring LLM Reasoning Effort via Deep-Thinking Tokens

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-07-07T03:18:12.196403Z

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 b1c34d4c-78c4-43c6-878a-8fce6eec9efa · outbound

This paper cites Brain-inspired graph multi- agent systems for llm reasoning,.

Co-Evolving Skill Generation and Policy Optimization Brain-inspired graph multi- agent systems for llm reasoning,

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-07-02T22:47:26.421959Z

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 90411c73-9e43-4b14-b4dd-32e7726d1c9a · outbound

This paper cites One Interaction Is Worth a Thousand Guesses: Benchmarking the Interactive Capabilities of Deep Research Agents.

Co-Evolving Skill Generation and Policy Optimization One Interaction Is Worth a Thousand Guesses: Benchmarking the Interactive Capabilities of Deep Research Agents

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-07-02T22:47:26.435251Z

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 89b83765-680a-46f7-99a9-d882e543677b · outbound

This paper cites arXiv:2602.18998 (2026).

Co-Evolving Skill Generation and Policy Optimization arXiv:2602.18998 (2026)

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-07-02T22:57:25.892666Z

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 68da68c9-854a-459a-ba3e-270e619acb1b · outbound

This paper cites Agentic reasoning: A streamlined framework for enhancing llm reasoning with agentic tools.

Co-Evolving Skill Generation and Policy Optimization Agentic reasoning: A streamlined framework for enhancing llm reasoning with agentic tools

Reference 13

Resolution: unresolved; no resolver link, observed 2026-06-27T18:37:00.015083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16ee237f-0240-42ad-9f34-91489e651eb3 · outbound

This paper cites LLM-based Agentic Reasoning Frameworks: A Survey from Methods to Scenarios.

Co-Evolving Skill Generation and Policy Optimization LLM-based Agentic Reasoning Frameworks: A Survey from Methods to Scenarios

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-07-02T22:57:25.899087Z

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 57afa478-200c-4c24-a405-40d2ad93c06e · outbound

This paper cites Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forward.

Co-Evolving Skill Generation and Policy Optimization Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forward

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-07-02T22:57:25.876462Z

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 85cba283-49fb-438a-a9d3-bc994d2c039e · outbound

This paper cites SoK: Agentic Skills -- Beyond Tool Use in LLM Agents.

Co-Evolving Skill Generation and Policy Optimization SoK: Agentic Skills -- Beyond Tool Use in LLM Agents

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-07-02T22:57:25.836483Z

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 14eee291-7dab-4fbf-9a2e-cdfdb0209697 · outbound

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

Co-Evolving Skill Generation and Policy Optimization SkillX: Automatically Constructing Skill Knowledge Bases for Agents

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-07-02T22:57:25.853843Z

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 e647e662-9de1-42a9-9dfe-d168bdaa51d2 · outbound

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

Co-Evolving Skill Generation and Policy Optimization SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-07-02T22:57:25.850746Z

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 05dcb7c0-96c8-4bcb-888d-f4afca18a68c · outbound

This paper cites Tooltree: Efficient llm agent tool planning via dual-feedback monte carlo tree search and bidirectional pruning.

Co-Evolving Skill Generation and Policy Optimization Tooltree: Efficient llm agent tool planning via dual-feedback monte carlo tree search and bidirectional pruning

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-07-02T22:57:25.840525Z

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 b5c9c2ff-84b8-48a9-bb4f-ba78743248be · outbound

This paper cites Agentic Tool Use in Large Language Models.

Co-Evolving Skill Generation and Policy Optimization Agentic Tool Use in Large Language Models

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-07-02T22:57:25.824054Z

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 ed9f1dee-1e6e-4a63-8d81-9c960b78a778 · outbound

This paper cites arXiv preprint , year =.

Co-Evolving Skill Generation and Policy Optimization arXiv preprint , year =

Reference 21

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T22:57:25.890044Z

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 54e3a7a8-b2d5-46fa-b0f2-dff021b7812b · outbound

This paper cites an unresolved cited work.

Co-Evolving Skill Generation and Policy Optimization Unresolved cited work

Reference 22

Resolution: unresolved; no resolver link, observed 2026-06-27T18:37:00.015083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc31ce23-ccac-4721-b49b-127489c56fe4 · outbound

This paper cites CAS- CADE: Cumulative agentic skill creation through autonomous development and evolution.

Co-Evolving Skill Generation and Policy Optimization CAS- CADE: Cumulative agentic skill creation through autonomous development and evolution

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-07-02T22:57:25.834911Z

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 325bec0c-3a15-4f56-91aa-7b14ab9159da · outbound

This paper cites SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skills.

Co-Evolving Skill Generation and Policy Optimization SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skills

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-07-02T22:57:25.851525Z

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 f519e037-47cb-4232-93ec-7bcf3a0b64f0 · outbound

This paper cites Automated Skill Discovery for Language Agents through Exploration and Iterative Feedback.

Co-Evolving Skill Generation and Policy Optimization Automated Skill Discovery for Language Agents through Exploration and Iterative Feedback

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-07-02T22:57:25.856666Z

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 37f93bd7-0806-4ebd-b779-d35f1b75ac20 · outbound

This paper cites Proposer-agent-evaluator (pae): Autonomous skill discovery for foundation model internet agents.

Co-Evolving Skill Generation and Policy Optimization Proposer-agent-evaluator (pae): Autonomous skill discovery for foundation model internet agents

Reference 26

Resolution: unresolved; no resolver link, observed 2026-06-27T18:37:00.015083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eeeba68a-3cfd-4114-aa41-032163ffaf83 · outbound

This paper cites Memp: Exploring Agent Procedural Memory.

Co-Evolving Skill Generation and Policy Optimization Memp: Exploring Agent Procedural Memory

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-07-02T22:47:26.438012Z

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 0d90c69c-de88-4c3e-b763-96f3c8733781 · outbound

This paper cites Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution.

Co-Evolving Skill Generation and Policy Optimization Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-07-02T22:57:25.817912Z

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 2ca10401-ff03-4fdf-9869-f16180eb46d0 · outbound

This paper cites Meta Context Engineer- ing via Agentic Skill Evolution, February 2026.https://arxiv.org/abs/2601.21557.

Co-Evolving Skill Generation and Policy Optimization Meta Context Engineer- ing via Agentic Skill Evolution, February 2026.https://arxiv.org/abs/2601.21557

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-07-02T22:57:25.906423Z

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 744d9e5e-7c9f-4e9e-9484-f09d527eebc6 · outbound

This paper cites SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization.

Co-Evolving Skill Generation and Policy Optimization SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization

Reference 30

Resolution: verified exact; local_arxiv, observed 2026-07-02T22:57:25.880988Z

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 7deaae6e-99eb-4aad-b5ef-4e2392a88cf6 · outbound

This paper cites Dynamic Dual-Granularity Skill Bank for Agentic RL.

Co-Evolving Skill Generation and Policy Optimization Dynamic Dual-Granularity Skill Bank for Agentic RL

Reference 31

Resolution: verified exact; local_arxiv, observed 2026-07-02T22:57:25.894872Z

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 8a421fcc-bf46-49f7-ae95-a1b50906259f · outbound

This paper cites Voyager: An Open-Ended Embodied Agent with Large Language Models.

Co-Evolving Skill Generation and Policy Optimization Voyager: An Open-Ended Embodied Agent with Large Language Models

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-07-02T22:57:25.826927Z

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 b719c3d5-d8ab-40ae-ac4a-d5cda4723c48 · outbound

This paper cites Skillact: Using skill abstractions improves llm agents.

Co-Evolving Skill Generation and Policy Optimization Skillact: Using skill abstractions improves llm agents

Reference 33

Resolution: unresolved; no resolver link, observed 2026-06-27T18:37:00.015083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c42ef35-cb9c-409d-9caa-89719d3b8d7e · outbound

This paper cites Inducing Programmatic Skills for Agentic Tasks.

Co-Evolving Skill Generation and Policy Optimization Inducing Programmatic Skills for Agentic Tasks

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-07-02T22:47:26.441022Z

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 1ba98e6f-a887-4a81-933d-b8eee3dc8955 · outbound

This paper cites Agent skills from the perspective of procedural memory: A survey.Authorea Preprints, 2026.

Co-Evolving Skill Generation and Policy Optimization Agent skills from the perspective of procedural memory: A survey.Authorea Preprints, 2026

Reference 35

Resolution: unresolved; no resolver link, observed 2026-06-27T18:37:00.015083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e68be63c-88a4-4e21-b367-9d7217c0f6b9 · outbound

This paper cites Experience Compression Spectrum: Unifying Memory, Skills, and Rules in LLM Agents.

Co-Evolving Skill Generation and Policy Optimization Experience Compression Spectrum: Unifying Memory, Skills, and Rules in LLM Agents

Reference 36

Resolution: verified exact; local_arxiv, observed 2026-07-02T22:57:25.839040Z

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 d062d8a4-04bc-4c49-85a0-2825b2cb9cad · outbound

This paper cites Automating skill acquisition through large-scale mining of open-source agentic repositories: A framework for multi-agent procedural knowledge extraction.

Co-Evolving Skill Generation and Policy Optimization Automating skill acquisition through large-scale mining of open-source agentic repositories: A framework for multi-agent procedural knowledge extraction

Reference 37

Resolution: verified exact; arxiv_id, observed 2026-07-02T22:57:25.873879Z

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 dcf9c615-0ad7-4c20-8730-d3d04af93226 · outbound

This paper cites SKILLFOUNDRY: Building Self-Evolving Agent Skill Libraries from Heterogeneous Scientific Resources.

Co-Evolving Skill Generation and Policy Optimization SKILLFOUNDRY: Building Self-Evolving Agent Skill Libraries from Heterogeneous Scientific Resources

Reference 38

Resolution: verified exact; local_arxiv, observed 2026-07-02T22:57:25.903852Z

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 3cc258b4-1d36-4cfc-a613-e57d83e97bb6 · outbound

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

Co-Evolving Skill Generation and Policy Optimization Autoskill: Experience-driven lifelong learning via skill self-evolution

Reference 39

Resolution: verified exact; arxiv_id, observed 2026-07-02T22:57:25.859355Z

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 dc25d14d-789c-43ba-8341-3bc55a6f7c60 · outbound

This paper cites Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills.

Co-Evolving Skill Generation and Policy Optimization Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills

Reference 40

Resolution: verified exact; local_arxiv, observed 2026-07-02T22:57:25.894014Z

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 7984dccf-c9dd-4962-8f93-a7bf6651068e · outbound

This paper cites Reinforcement Learning for Self-Improving Agent with Skill Library.

Co-Evolving Skill Generation and Policy Optimization Reinforcement Learning for Self-Improving Agent with Skill Library

Reference 41

Resolution: verified exact; local_arxiv, observed 2026-07-02T22:47:26.443531Z

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 3a2fc74d-8077-4fb6-8813-a65f968861c7 · outbound

This paper cites Arise: Agent reasoning with intrinsic skill evolution in hierarchical reinforcement learning.

Co-Evolving Skill Generation and Policy Optimization Arise: Agent reasoning with intrinsic skill evolution in hierarchical reinforcement learning

Reference 42

Resolution: verified exact; arxiv_id, observed 2026-07-02T22:57:25.862516Z

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 1f58cbe1-ae32-40d0-8ecf-ab1507d6ccd1 · outbound

This paper cites CoEvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification.

Co-Evolving Skill Generation and Policy Optimization CoEvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification

Reference 43

Resolution: verified exact; local_arxiv, observed 2026-07-02T22:57:25.901517Z

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 63b4c900-7527-4b2f-8f13-65129af8004e · outbound

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

Co-Evolving Skill Generation and Policy Optimization SkillClaw: Let Skills Evolve Collectively with Agentic Evolver

Reference 44

Resolution: verified exact; local_arxiv, observed 2026-07-02T22:57:25.830923Z

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 600aaf1c-be28-41ff-8ac2-792c42c3f4b2 · outbound

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

Co-Evolving Skill Generation and Policy Optimization SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks

Reference 45

Resolution: verified exact; local_arxiv, observed 2026-07-02T22:57:25.878550Z

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 004a7c61-0a79-441a-9ffb-62bc2fd2846c · outbound

This paper cites SkillLearnBench: Benchmarking Continual Learning Methods for Agent Skill Generation on Real-World Tasks.

Co-Evolving Skill Generation and Policy Optimization SkillLearnBench: Benchmarking Continual Learning Methods for Agent Skill Generation on Real-World Tasks

Reference 46

Resolution: verified exact; local_arxiv, observed 2026-07-02T22:47:26.440552Z

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 48386583-dbbb-4203-814d-6928691314a9 · outbound

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

Co-Evolving Skill Generation and Policy Optimization How Well Do Agentic Skills Work in the Wild: Benchmarking LLM Skill Usage in Realistic Settings

Reference 47

Resolution: verified exact; local_arxiv, observed 2026-07-02T22:57:25.849136Z

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 a1255679-a3c9-425d-99e2-91210c1e4572 · outbound

This paper cites Skilltester: Benchmarking utility and security of agent skills.

Co-Evolving Skill Generation and Policy Optimization Skilltester: Benchmarking utility and security of agent skills

Reference 48

Resolution: verified exact; arxiv_id, observed 2026-07-02T22:47:26.457806Z

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 59a2cabd-dc1b-4498-b3ae-41a918821918 · outbound

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

Co-Evolving Skill Generation and Policy Optimization SkillFlow:Benchmarking Lifelong Skill Discovery and Evolution for Autonomous Agents

Reference 49

Resolution: verified exact; local_arxiv, observed 2026-07-02T22:47:26.460447Z

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 d08258a8-df2e-4639-ac6a-e3f2b12b5e61 · outbound

This paper cites Welcome to the era of experience.Google AI, 1:11, 2025.

Co-Evolving Skill Generation and Policy Optimization Welcome to the era of experience.Google AI, 1:11, 2025

Reference 50

Resolution: unresolved; no resolver link, observed 2026-06-27T18:37:00.015083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd293901-17f6-4896-b9cc-d6087f836954 · outbound

This paper cites Memory for autonomous llm agents: Mechanisms, evaluation, and emerging frontiers.

Co-Evolving Skill Generation and Policy Optimization Memory for autonomous llm agents: Mechanisms, evaluation, and emerging frontiers

Reference 51

Resolution: verified exact; arxiv_id, observed 2026-07-02T22:47:26.449273Z

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 cc670e79-6e3e-4094-a0c4-a1ebd6290b17 · outbound

This paper cites Memento: Fine-tuning LLM Agents without Fine-tuning LLMs.

Co-Evolving Skill Generation and Policy Optimization Memento: Fine-tuning LLM Agents without Fine-tuning LLMs

Reference 52

Resolution: verified exact; arxiv_id, observed 2026-07-02T22:57:25.867397Z

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 b44203e5-9781-40bf-b35f-be9e65c24968 · outbound

This paper cites Scaling agent learning via experience synthesis.

Co-Evolving Skill Generation and Policy Optimization Scaling agent learning via experience synthesis

Reference 53

Resolution: verified exact; arxiv_id, observed 2026-07-02T22:57:25.904457Z

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 3a71f265-0b05-4144-be95-d1611ff72898 · outbound

This paper cites Agent Learning via Early Experience.

Co-Evolving Skill Generation and Policy Optimization Agent Learning via Early Experience

Reference 54

Resolution: verified exact; local_arxiv, observed 2026-07-02T22:57:25.878799Z

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 a5e360c6-d55c-426a-85c8-ea046b3da241 · outbound

This paper cites MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory.

Co-Evolving Skill Generation and Policy Optimization MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory

Reference 55

Resolution: verified exact; local_arxiv, observed 2026-07-02T22:57:25.899564Z

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 4c6afe53-99af-4150-b9d3-2959a043f709 · outbound

This paper cites Trajectory-informed memory generation for self-improving agent systems.

Co-Evolving Skill Generation and Policy Optimization Trajectory-informed memory generation for self-improving agent systems

Reference 56

Resolution: verified exact; arxiv_id, observed 2026-07-02T22:57:25.887645Z

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 a5db41fc-e95d-4093-b10e-50799bead76e · outbound

This paper cites ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory.

Co-Evolving Skill Generation and Policy Optimization ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory

Reference 57

Resolution: verified exact; local_arxiv, observed 2026-07-02T22:57:25.910403Z

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 05e77c32-6688-4ac0-aeff-e9378f78f76f · outbound

This paper cites R2d2: Remembering, replaying and dynamic decision making with a reflective agentic memory.

Co-Evolving Skill Generation and Policy Optimization R2d2: Remembering, replaying and dynamic decision making with a reflective agentic memory

Reference 58

Resolution: unresolved; no resolver link, observed 2026-06-27T18:37:00.015083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24ce572e-c007-471f-8b30-94f42ad805d2 · outbound

This paper cites Dynamic cheatsheet: Test-time learning with adaptive memory.

Co-Evolving Skill Generation and Policy Optimization Dynamic cheatsheet: Test-time learning with adaptive memory

Reference 59

Resolution: unresolved; no resolver link, observed 2026-06-27T18:37:00.015083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed5a25d2-4d6f-49a6-89ec-81ce22cd7023 · outbound

This paper cites Flex: Continuous agent evolution via forward learning from experience.

Co-Evolving Skill Generation and Policy Optimization Flex: Continuous agent evolution via forward learning from experience

Reference 60

Resolution: verified exact; arxiv_id, observed 2026-07-02T22:57:25.776640Z

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 d4072ae0-91a9-4c30-b42b-3f320d3ec772 · outbound

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

Co-Evolving Skill Generation and Policy Optimization Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents

Reference 61

Resolution: verified exact; local_arxiv, observed 2026-07-02T22:57:25.828262Z

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 9c57175e-7d8f-47db-9a70-d85c37009f51 · outbound

This paper cites Legomem: Modular procedural memory for multi-agent llm systems for workflow automation.

Co-Evolving Skill Generation and Policy Optimization Legomem: Modular procedural memory for multi-agent llm systems for workflow automation

Reference 62

Resolution: verified exact; arxiv_id, observed 2026-07-02T22:57:25.837741Z

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 5b8faa6b-4820-41d3-bea7-a7fa4983d446 · outbound

This paper cites Agent kb: Leveraging cross-domain experience for agentic problem solving.

Co-Evolving Skill Generation and Policy Optimization Agent kb: Leveraging cross-domain experience for agentic problem solving

Reference 63

Resolution: verified exact; arxiv_id, observed 2026-07-02T22:57:25.907637Z

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 f0fe70a6-bcd7-432b-95d9-ee64fd3b2e0e · outbound

This paper cites G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems.

Co-Evolving Skill Generation and Policy Optimization G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems

Reference 64

Resolution: verified exact; arxiv_id, observed 2026-07-02T22:47:26.421753Z

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 81f77580-c744-4f1a-95c8-82f1823fb822 · outbound

This paper cites EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecycle.

Co-Evolving Skill Generation and Policy Optimization EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecycle

Reference 65

Resolution: verified exact; local_arxiv, observed 2026-07-02T22:47:26.424338Z

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 838d8488-37bb-4416-af6b-c11213ffba73 · outbound

This paper cites Graph-based agent memory: Taxonomy, techniques, and applications.

Co-Evolving Skill Generation and Policy Optimization Graph-based agent memory: Taxonomy, techniques, and applications

Reference 66

Resolution: verified exact; arxiv_id, observed 2026-07-02T22:57:25.845493Z

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 1934cf68-119b-4c96-95c2-1cd1d79aea29 · outbound

This paper cites MemEvolve: Meta-Evolution of Agent Memory Systems.

Co-Evolving Skill Generation and Policy Optimization MemEvolve: Meta-Evolution of Agent Memory Systems

Reference 67

Resolution: verified exact; local_arxiv, observed 2026-07-02T22:57:25.890807Z

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 8d55a5ce-5ba9-4013-9431-9584deaa2662 · outbound

This paper cites Agentevolver: Towards efficient self-evolving agent system.

Co-Evolving Skill Generation and Policy Optimization Agentevolver: Towards efficient self-evolving agent system

Reference 68

Resolution: verified exact; arxiv_id, observed 2026-07-02T22:47:26.454755Z

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 8b5c4b91-481f-4016-804d-6b844681a852 · outbound

This paper cites Building self-evolving agents via experience-driven lifelong learning: A framework and benchmark.

Co-Evolving Skill Generation and Policy Optimization Building self-evolving agents via experience-driven lifelong learning: A framework and benchmark

Reference 69

Resolution: verified exact; arxiv_id, observed 2026-07-02T22:47:26.449485Z

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 987f4751-8af1-4d9d-9111-2a728b5bbf26 · outbound

This paper cites Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning.

Co-Evolving Skill Generation and Policy Optimization Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning

Reference 70

Resolution: verified exact; local_arxiv, observed 2026-07-02T22:57:25.901885Z

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 c858693e-e2d5-4671-b494-3ad29d1ddd0c · outbound

This paper cites Adaptive Memory Crystallization for Autonomous AI Agent Learning in Dynamic Environments.

Co-Evolving Skill Generation and Policy Optimization Adaptive Memory Crystallization for Autonomous AI Agent Learning in Dynamic Environments

Reference 71

Resolution: verified exact; local_arxiv, observed 2026-07-02T22:47:26.413524Z

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 8560c48b-187d-43bd-a22a-43e1a5f0de09 · outbound

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

Co-Evolving Skill Generation and Policy Optimization ALFWorld: Aligning Text and Embodied Environments for Interactive Learning

Reference 72

Resolution: verified exact; local_arxiv, observed 2026-07-02T22:47:26.416212Z

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 3cec899c-61a7-4953-a26d-fb19336f1751 · outbound

This paper cites Webshop: Towards scalable real-world web interaction with grounded language agents.Advances in Neural Information Processing Systems, 35:20744–20757, 2022.

Co-Evolving Skill Generation and Policy Optimization Webshop: Towards scalable real-world web interaction with grounded language agents.Advances in Neural Information Processing Systems, 35:20744–20757, 2022

Reference 73

Resolution: unresolved; no resolver link, observed 2026-06-27T18:37:00.015083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 194a0efe-d2d0-4622-8392-25a94e9e0617 · outbound

This paper cites Qwen3 Technical Report.

Co-Evolving Skill Generation and Policy Optimization Qwen3 Technical Report

Reference 74

Resolution: verified exact; local_arxiv, observed 2026-07-02T22:47:26.429860Z

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 07bcbd80-c110-4399-90e7-0132421a4958 · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

Co-Evolving Skill Generation and Policy Optimization DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 75

Resolution: verified exact; local_arxiv, observed 2026-07-02T22:47:26.443218Z

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 42349223-83ac-4946-a1e6-3342dd2fcbd8 · outbound

This paper cites The surprising effectiveness of negative reinforcement in llm reasoning.arXiv preprint arXiv:2506.01347.

Co-Evolving Skill Generation and Policy Optimization The surprising effectiveness of negative reinforcement in llm reasoning.arXiv preprint arXiv:2506.01347

Reference 76

Resolution: verified exact; arxiv_id, observed 2026-07-02T22:47:26.426988Z

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 4ab0146b-dcbc-4e50-9d96-a814996eb7d1 · outbound

This paper cites Natural questions: a benchmark for question answering research.Transactions of the Association for Computational Linguistics, 7:453–466, 2019.

Co-Evolving Skill Generation and Policy Optimization Natural questions: a benchmark for question answering research.Transactions of the Association for Computational Linguistics, 7:453–466, 2019

Reference 77

Resolution: unresolved; no resolver link, observed 2026-06-27T18:37:00.015083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd5e89d8-8b27-44f1-bc96-f2302069de34 · outbound

This paper cites Triviaqa: A large scale distantly supervised challenge dataset for reading comprehension.

Co-Evolving Skill Generation and Policy Optimization Triviaqa: A large scale distantly supervised challenge dataset for reading comprehension

Reference 78

Resolution: unresolved; no resolver link, observed 2026-06-27T18:37:00.015083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae7693b3-c8b7-4137-930a-2a8a59b385fe · outbound

This paper cites When not to trust language models: Investigating effectiveness of parametric and non-parametric memories.

Co-Evolving Skill Generation and Policy Optimization When not to trust language models: Investigating effectiveness of parametric and non-parametric memories

Reference 79

Resolution: unresolved; no resolver link, observed 2026-06-27T18:37:00.015083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 801c0f63-9afa-4f4b-ad94-e8d52133ed60 · outbound

This paper cites Hotpotqa: A dataset for diverse, explainable multi-hop question answering.

Co-Evolving Skill Generation and Policy Optimization Hotpotqa: A dataset for diverse, explainable multi-hop question answering

Reference 80

Resolution: unresolved; no resolver link, observed 2026-06-27T18:37:00.015083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1bc986e8-6f15-47fd-8abc-00cd3cb2434e · outbound

This paper cites Constructing a multi-hop qa dataset for comprehensive evaluation of reasoning steps.

Co-Evolving Skill Generation and Policy Optimization Constructing a multi-hop qa dataset for comprehensive evaluation of reasoning steps

Reference 81

Resolution: unresolved; no resolver link, observed 2026-06-27T18:37:00.015083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d04772b8-43f2-4702-b346-6f8d16b35b3d · outbound

This paper cites Musique: Multi-hop questions via single-hop question composition.Transactions of the Association for Computational Linguistics, 10:539–554, 2022.

Co-Evolving Skill Generation and Policy Optimization Musique: Multi-hop questions via single-hop question composition.Transactions of the Association for Computational Linguistics, 10:539–554, 2022

Reference 82

Resolution: unresolved; no resolver link, observed 2026-06-27T18:37:00.015083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce80d306-3640-4842-81c4-ca6fef390c23 · outbound

This paper cites Measuring and narrowing the compositionality gap in language models.

Co-Evolving Skill Generation and Policy Optimization Measuring and narrowing the compositionality gap in language models

Reference 83

Resolution: unresolved; no resolver link, observed 2026-06-27T18:37:00.015083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8af126c3-526c-4b8e-817a-37f560c4602d · outbound

This paper cites Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities.

Co-Evolving Skill Generation and Policy Optimization Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Reference 84

Resolution: verified exact; local_arxiv, observed 2026-07-02T22:47:26.429486Z

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 6009b2cf-53a8-4e43-a23f-e0faac7ac119 · outbound

This paper cites ReAct: Synergizing Reasoning and Acting in Language Models.

Co-Evolving Skill Generation and Policy Optimization ReAct: Synergizing Reasoning and Acting in Language Models

Reference 85

Resolution: verified exact; local_arxiv, observed 2026-07-02T22:47:26.432235Z

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 ae2ea331-8cbb-4e54-a599-8aa4334fc6c1 · outbound

This paper cites Reflexion: Language agents with verbal reinforcement learning.Advances in neural information processing systems, 36:8634–8652, 2023.

Co-Evolving Skill Generation and Policy Optimization Reflexion: Language agents with verbal reinforcement learning.Advances in neural information processing systems, 36:8634–8652, 2023

Reference 86

Resolution: unresolved; no resolver link, observed 2026-06-27T18:37:00.015083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0a149d7-9968-4fa6-8131-d788eec6be4d · outbound

This paper cites Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory.

Co-Evolving Skill Generation and Policy Optimization Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory

Reference 87

Resolution: verified exact; local_arxiv, observed 2026-07-02T22:47:26.446146Z

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 f940e363-7245-4592-b44f-e2ee9638a819 · outbound

This paper cites Expel: Llm agents are experiential learners.

Co-Evolving Skill Generation and Policy Optimization Expel: Llm agents are experiential learners

Reference 88

Resolution: unresolved; no resolver link, observed 2026-06-27T18:37:00.015083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6cbc82e2-1e9c-4321-b6ca-3c2c303f78aa · outbound

This paper cites Back to basics: Revisiting reinforce-style optimization for learning from human feedback in llms.

Co-Evolving Skill Generation and Policy Optimization Back to basics: Revisiting reinforce-style optimization for learning from human feedback in llms

Reference 89

Resolution: unresolved; no resolver link, observed 2026-06-27T18:37:00.015083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0901fb9c-d856-4d7b-9198-fb19603db4d6 · outbound

This paper cites SimpleMem: Efficient Lifelong Memory for LLM Agents.

Co-Evolving Skill Generation and Policy Optimization SimpleMem: Efficient Lifelong Memory for LLM Agents

Reference 90

Resolution: verified exact; local_arxiv, observed 2026-07-02T22:47:26.435624Z

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 8c140f9f-5923-49fb-992a-73b8cdbd086e · outbound

This paper cites Search-o1: Agentic search-enhanced large reasoning models.

Co-Evolving Skill Generation and Policy Optimization Search-o1: Agentic search-enhanced large reasoning models

Reference 91

Resolution: unresolved; no resolver link, observed 2026-06-27T18:37:00.015083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b11de2d0-1b76-4da9-b8f7-3e8f9e911bbb · outbound

This paper cites Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning.

Co-Evolving Skill Generation and Policy Optimization Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning

Reference 92

Resolution: verified exact; local_arxiv, observed 2026-07-02T22:57:25.842847Z

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 9dc86ad0-4ac1-4ba5-9ff1-3600745d6288 · outbound

This paper cites ZeroSearch: Incentivize the Search Capability of LLMs without Searching.

Co-Evolving Skill Generation and Policy Optimization ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 93

Resolution: verified exact; local_arxiv, observed 2026-07-02T22:57:25.864373Z

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 ffaea00e-6581-4880-a5f1-68dd30ab359c · outbound

This paper cites StepSearch: Igniting LLMs Search Ability via Step-Wise Proximal Policy Optimization.

Co-Evolving Skill Generation and Policy Optimization StepSearch: Igniting LLMs Search Ability via Step-Wise Proximal Policy Optimization

Reference 94

Resolution: verified exact; arxiv_id, observed 2026-07-02T22:57:25.881525Z

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 ac9f0a0b-3ab0-49aa-a391-3851bf17818b · outbound

This paper cites Group-in-Group Policy Optimization for LLM Agent Training.

Co-Evolving Skill Generation and Policy Optimization Group-in-Group Policy Optimization for LLM Agent Training

Reference 95

Resolution: verified exact; local_arxiv, observed 2026-07-02T22:57:25.896537Z

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 889cc33b-1ce3-4984-829d-c17a53a6fbaf · outbound

This paper cites Text Embeddings by Weakly-Supervised Contrastive Pre-training.

Co-Evolving Skill Generation and Policy Optimization Text Embeddings by Weakly-Supervised Contrastive Pre-training

Reference 96

Resolution: verified exact; local_arxiv, observed 2026-07-02T22:57:25.861682Z

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.

Coverage vector

Reference resolution

Outbound references

Pith citing papers