Page History
Every revision of this knowledge page since it was created on October 9, 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.
Updated from new reportingOctober 22, 2026 (+964 chars)
Updated from new reportingOctober 16, 2026 (+888 chars)
Updated from new reportingOctober 15, 2026 (+2,840 chars)
- Small but Mighty: Test Suites as Improvement Signals for Self-Evolving Agents
- SpecForge: Recursive Self-Improvement for Coding Agents via Behavioral Specifications
- Heterogeneous Agentic Coevolution
- Imitation Holds a Key to Evolution: Localized Repair and Verified Skill Acquisition for Adaptive Agents
- Harness^2: Recursive Agent Harnessing for an Open World
Updated from new reportingOctober 15, 2026 (+775 chars)
Page createdOctober 9, 2026 (+2,109 chars)
- The Harness as the Only Mutable Surface: Compliance-Bounded Self-Evolution of LLM Agents in Credit Pipelines, with a Measured Admission Gate
- SynCo: Data Synthesis Co-Training for Self-Evolving LLMs via Multi-Agent Reinforcement Learning
- Verification and Self-Improvement in Agentic AI: Foundations and Limits
- EvoSim: Learning to Model, Modeling to Learn