proomt

Search

Search posts, papers, and topics

All posts

Hugging Face Daily PapersBofan Chen, Boxuan Zhang, Fei Tang1 min readpaperadvanced

Reflect, Revise, Reuse: Training-Free Skill Evolution for GUI Agents

Read on arxiv.org

Summary

EvoSkill‑GUI lets GUI agents revise their procedural skills on‑the‑fly without extra training by using a reflect‑revise‑reuse loop that edits skill packages during execution. The approach yields up to +16.2% improvement on MobileWorld and similar gains on AndroidWorld and OSWorld, and the evolved skills transfer to related tasks.

  • Skills are stored as multi‑file packages (plan, metadata, recovery rules) that can be edited by the executor at runtime.
  • A strict critic runs in isolation to diagnose failures and suggest precise edits, preserving information safety.
  • Across MobileWorld, AndroidWorld, and OSWorld, EvoSkill‑GUI improves base models by up to 16.2% without any additional training.
  • Evolved skill libraries remain useful for new tasks, avoiding the need to rebuild skills from scratch.

Engineers building GUI automation or assistant agents can get adaptive, higher‑performing skills without costly retraining cycles.

7/10
machine learninggui agentsml infratraining free

Related reading

  2. COBRA-Skills: Contextual Bandit-Guided Evolution for Agent Skill Optimization

    COBRA‑Skills uses a contextual‑bandit loop to selectively evaluate and evolve LLM agent skills, achieving better performance with roughly half the evaluation cost of prior methods. The framework works with limited examples and remains robust across different agent setups and even when the target model creates its own skills.

    Hugging Face Daily Papersarxiv.org1 minpaper

  3. Designer-RSI: Evolving Procedural Memory from User Traffic for Agentic Graphic Design

    The paper introduces Designer‑RSI, a continual‑adaptation system that couples a frozen design‑software‑controlling LLM with an external procedural memory of natural‑language design skills. Over five adaptation rounds on real user briefs, the memory grows from 76 to 139 procedures and lifts execution success from 72.7% to 99.3%, showing that skill accumulation and selective replay can dramatically…

    Hugging Face Daily Papersarxiv.org1 minpaper

  5. Grounded Skill Synthesis from Code at Scale for Agentic Intelligence

    Code2Skill is an automated pipeline that mines popular GitHub repositories to extract verifiable, implementation‑anchored procedural “skills”. It builds a bank of ~1 M skill records (atomic ops, workflows, patterns) with provenance metadata, verifies each via blind reconstruction, and shows that augmenting LLM‑based agents with these skills yields an average 11.7% performance lift across 72 proto…

    Hugging Face Daily Papersarxiv.org1 minpaper

  6. How to upskill enterprise AI builders by using daily micro habits

    Google Cloud Consulting proposes a four‑pillar micro‑learning framework for enterprise AI upskilling: 5‑minute browser‑based exercises, pre‑configured sandboxes, daily streaks, and delivering runnable code each session. A pilot (Advent of Agents) showed >150k participants, 859k code runs, and a 31% daily return rate, suggesting short, frictionless tasks improve engagement versus traditional bootc…

    Google Cloud Bloggoogle.com3 min