MMG2Skill: Can Agents Distill In-the-Wild Guides into Self-Evolving Skills?

• URL: http://arxiv.org/abs/2606.01993v1
• Date: Mon, 01 Jun 2026 09:50:40 GMT
• Title: MMG2Skill: Can Agents Distill In-the-Wild Guides into Self-Evolving Skills?
• Abstract summary: MMG2Skill is a framework for converting in-the-wild guides into agent-executable skills.<n>MMG2Skill consistently outperforms vanilla baseline agents in every model-domain setting.
• Score: 36.863282825853645
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Abundant procedural knowledge on the Web holds great potential for helping agents solve long-horizon tasks. However, such knowledge is often multimodal, heterogeneous, noisy, and implicitly assumes human executors, making it difficult to use directly as the skills required by agents. To bridge the gap between human-oriented guides and agent-executable skills, we formalize this problem as guide-to-skill learning: converting in-the-wild guides into executable skills and continuously improving them from trajectories observable to the agent. To evaluate the capability of existing agents on this task, we introduce MMG2Skill-Bench, the first benchmark designed for this problem. We further propose MMG2Skill, a closed-loop framework that compiles guides into editable skills, conditions a fixed vision-language model (VLM) agent on these skills during execution, and revises the skills from trajectory-level root-cause feedback without using benchmark scores. Across GUI control, open-ended gameplay, and strategic card play with six VLM backbones, MMG2Skill consistently outperforms vanilla baseline agents in every model-domain setting, achieving macro-average gains of +12.8 to +25.3 percentage points across backbones. Ablation studies show that directly prompting agents with raw guides can degrade performance, while both structured skill construction and trajectory-driven revision are necessary for the observed improvements. On success-inferable tasks, analyzer-based early stopping further prevents late-stage performance regressions and saves 25%-53% of attempts when the success signal is properly calibrated.

Related papers

• Rethinking Self-Evolution: A Constrained Exploration-Exploitation Process for Mitigating Skill Overfitting [20.811638832981178]
  Large language model (LLM) agents need to accumulate and reuse experience from past interactions.<n>Data-driven skill optimization is prone to overfitting to the limited trajectories collected from real environments.<n>We propose SkillBoost, a three-stage framework that mitigates both risks.
  arXiv  Detail & Related papers  (2026-07-29T09:05:40Z)
• MetaSkill-Evolve: Recursive Self-Improvement of LLM Agents via Two-Timescale Meta-Skill Evolution [24.78476085778134]
  Self-improving agents address this by rewriting their own skill files from execution traces, yielding meaningful gains on challenging benchmarks.<n>We introduce MetaSkill-Evolve, a two-timescale framework that makes agentic skill improvement recursive.<n>Task skills evolve on a fast loop while the meta-skill evolves on a slower one under the same pipeline applied to itself.<n>With all five pipeline agents sharing a single frozen backbone, MetaSkill-Evolve outperforms no-skill, static-skill, and single-level evolution baselines.
  arXiv  Detail & Related papers  (2026-07-06T16:40:23Z)
• SkillComposer: Learning to Evolve Agent Skills for Specification and Generalization [99.18305770138677]
  Agent skills are reusable strategies that guide agent reasoning and action.<n>Current skill construction methods treat the problem as one-shot extraction.<n>We introduce SkillComposer, a framework that decomposes skill construction into three learnable operations.
  arXiv  Detail & Related papers  (2026-06-04T12:16:08Z)
• Skill is Not One-Size-Fits-All: Model-Aware Skill Alignment for LLM Agents [9.144810798419975]
  LLM agents increasingly retrieve externally curated skills-procedural instructions retrieved at decision time to improve performance on long-horizon interactive tasks.<n>We propose MASA Model-Aware Skill Alignment, a framework that adapts skills to each target backbone without modifying agent weights.<n> MASA consistently achieves the best overall performance, with gains of up to 25.8 points over the strongest baseline.
  arXiv  Detail & Related papers  (2026-05-29T01:34:42Z)
• Harnessing LLM Agents with Skill Programs [58.356514745548026]
  We introduce HASP, a new framework that upgrades skills into executable Program Functions (PFs)<n>PFs act as executable guardrails that activate on failure-prone states and modify the next action or inject corrective context.<n> HASP drives substantial gains compared to both training-free and training-based methods on web-search, math reasoning, and coding tasks.
  arXiv  Detail & Related papers  (2026-05-18T01:35:11Z)
• Skill-R1: Agent Skill Evolution via Reinforcement Learning [84.35984979949502]
  Skill-R1 is a reinforcement learning framework for instance-level recurrent skill optimization from verifiable rewards.<n>It preserves black-box compatibility with both open- and closed-source models while making adaptation substantially cheaper than model-level updates.
  arXiv  Detail & Related papers  (2026-05-10T06:19:15Z)
• SkillGen: Verified Inference-Time Agent Skill Synthesis [60.927977774369516]
  SkillGen is a framework that synthesizes a single auditable skill from trajectories generated by a base agent.<n>It identifies reusable success patterns, recurring failure modes, and behaviors that appear in nearby successes but are missing from failures.<n>A key novelty in SkillGen is that we model agent skills as interventions to empirically verify the net effect of skills on the overall performance.
  arXiv  Detail & Related papers  (2026-05-09T19:24:11Z)
• SkillOS: Learning Skill Curation for Self-Evolving Agents [67.94374107466957]
  We propose SkillOS, an experience-driven RL training recipe for learning skill curation in self-evolving agents.<n>SkillOS pairs a frozen agent executor that retrieves and applies skills with a trainable skill curator that updates an external SkillRepo from accumulated experience.<n>We show that SkillOS consistently outperforms memory-free and strong memory-based baselines in both effectiveness and efficiency.
  arXiv  Detail & Related papers  (2026-05-07T17:31:50Z)
• Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills [21.971456179996093]
  We introduce Trace2Skill, a framework that mirrors how human experts author skills.<n>Instead of reacting sequentially to individual trajectories, Trace2Skill dispatches a parallel fleet of sub-agents to analyze a diverse pool of executions.<n>It extracts trajectory-specific lessons and hierarchically consolidates them into a unified, conflict-free skill directory via inductive reasoning.
  arXiv  Detail & Related papers  (2026-03-26T08:26:38Z)
• EvoSkill: Automated Skill Discovery for Multi-Agent Systems [6.319876096746374]
  We introduce textbfEvoSkill, a self-evolving framework that automatically discovers and refines agent skills.<n>EvoSkill analyzes execution failures, proposes new skills or edits to existing ones, and materializes them into structured, reusable skill folders.<n>We evaluate EvoSkill on two benchmarks: OfficeQA, a grounded reasoning benchmark over U.S. Treasury data, and SealQA, a noisy retrieval benchmark.
  arXiv  Detail & Related papers  (2026-03-03T09:07:22Z)
• K^2-Agent: Co-Evolving Know-What and Know-How for Hierarchical Mobile Device Control [73.50217471850658]
  K2-Agent is a hierarchical framework that models human-like cognition by knowing and co-evolving declarative (what) and procedural (how) knowledge for planning and execution.<n>On the challenging AndroidWorld benchmark, K2-Agent achieves a 76.1% success rate using only raw and open-source backbones.
  arXiv  Detail & Related papers  (2026-02-28T14:33:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.