MetaSkill-Evolve: Recursive Self-Improvement of LLM Agents via Two-Timescale Meta-Skill Evolution
Recent LLM agents tackle increasingly long-horizon, open-ended tasks, and external skills, reusable procedural knowledge supplied to the agent, further extend this capability. However, a fixed, hand-authored skill is rarely optimal, and cannot adapt to the diversity of tasks an agent encounters. Self-improving agents address this by rewriting their own skill files from execution traces, yielding meaningful gains on challenging benchmarks. Yet such self-evolution remains non-recursive: it improves only the task skill (what the agent does) while the improvement procedure (how it improves) is aut
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 64%AgentToolkit/altk-evolve →
- PossiblePossibly related (embedding) · 58%zjunlp/SkillX →
- PossiblePossibly related (embedding) · 58%AgentCore-8B →
- PossiblePossibly related (embedding) · 57%activeloopai/hivemind →
- PossiblePossibly related (embedding) · 57%MemTensor/MemOS →
- LinkedLinked via arxiv author · 85%Zefeng Wang →
“MetaSkill-Evolve: Recursive Self-Improvement of LLM Agents via Two-Timescale Meta-Skill Evolution”
- LinkedLinked via arxiv author · 85%Minxi Yan →
“MetaSkill-Evolve: Recursive Self-Improvement of LLM Agents via Two-Timescale Meta-Skill Evolution”
- LinkedLinked via arxiv author · 85%Jinhe Bi →
“MetaSkill-Evolve: Recursive Self-Improvement of LLM Agents via Two-Timescale Meta-Skill Evolution”