← Skill-Based Self-Evolution Methods for LLM Agents
Page History
Every revision of this knowledge page since it was created on October 20, 2026. Each entry shows what kind of change was made, how the page grew or shrank, and the source articles that drove it — so the paper's memory is inspectable, not taken on faith.
Page createdOctober 20, 2026 (+1,703 chars)
- From Trajectories to Differentiated Skills: Cognitive Differentiation for Self-Improving Agents
- Harness-Delta Attribution: Dissecting Gains From Harness Evolution
- Darwin-Claw: Environment-Adaptive Experience Consolidation for Recursively Self-Evolving Agents
- SkillBrowser: Selective Skill Exposure for Scalable Skill-Using Agents