agent/papers/items/2026-2607-05297-metaskill-evolve-recursive-self-improvement-of-llm-agents-via-two-timescale-meta.md

Paper: MetaSkill-Evolve: Recursive Self-Improvement of LLM Agents via Two-Timescale Meta-Skill Evolution

---

type: paper title: "MetaSkill-Evolve: Recursive Self-Improvement of LLM Agents via Two-Timescale Meta-Skill Evolution" authors: Zefeng Wang, Minxi Yan, Jinhe Bi, Sikuan Yan, Volker Tresp, Yunpu Ma year: 2026 venue: arXiv url: https://arxiv.org/abs/2607.05297 code_url: source: arxiv collected_at: 2026-07-08 published_at: 2026-07-06 updated_at: 2026-07-06 status: queued relevance: high topics:

• agent-evaluation
• planning
• reasoning
• workflow-agent methods:

benchmarks:

models:

datasets:

• cs.AI related_concepts:

related_jobs:

related_experiments:

related_projects:

collection_score: 17 collection_queries: agent-evaluation, llm-agent

One-line Takeaway

Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.

Why Collected

• matched queries: agent-evaluation, llm-agent
• inferred topics: agent-evaluation, planning, reasoning, workflow-agent
• arXiv categories: cs.AI
• collection score: 17

Review Checklist

• Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
• Does it include a benchmark, dataset, code, or reproducible experimental setup?
• Should it be promoted from queued to skimmed or summarized?

Links

• arXiv: https://arxiv.org/abs/2607.05297