Hugging Face Daily PapersRui Sun, Zhi Zheng, Zhenkun WangSep 18, 20261 min readpaperadvanced

GraphSkillEvo: Evolutionary Optimization of Graph-Structured Agent Skills

Summary

GraphSkillEvo encodes LLM agent skills as directed graphs and applies population‑based evolution (mutation, crossover) to optimise them. Across five benchmarks it beats the SkillOpt baseline, gaining up to 4% accuracy on GPT‑5.4‑nano.

Skills are modelled as graphs: nodes hold step instructions, edges capture context‑dependent transitions.
Mutation and crossover operators evolve skill graphs, expanding the search beyond LLM self‑refinement.
Experiments on five agent benchmarks show +4.01% accuracy on GPT‑5.4‑nano and +1.76% on GPT‑5.4 versus SkillOpt.
Open‑source implementation released for reproducibility.

Engineers building LLM agents can adopt graph‑structured skills and evolutionary search to obtain more reliable, less redundant workflows.

8/10

llm machine learning agents evolutionary algorithms graph structures

Related reading

COBRA-Skills: Contextual Bandit-Guided Evolution for Agent Skill Optimization arxiv.org
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.orgPingchen Lu, Xiangyi Wang, Xiang Li12d1 minpaper
Reflect, Revise, Reuse: Training-Free Skill Evolution for GUI Agents arxiv.org
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.
Hugging Face Daily Papersarxiv.orgBofan Chen, Boxuan Zhang, Fei Tang7d1 minpaper
EvolveTrade: Experience-Driven Policy Refinement for Self-Evolving LLM Trading Agents arxiv.org
EvolveTrade is a framework for self-evolving LLM trading agents that refines their tool-use policies (system prompts) based on past performance. It demonstrates improved Sharpe Ratio and Cumulative Return compared to agents with static policies across various market regimes.
Hugging Face Daily Papersarxiv.orgSehee Kim, Yumin Choi, Minki Kang7d1 minpaper
ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement arxiv.org
ModularRSI proposes a contrastive, modular approach to evolve agent harnesses by independently updating five functional modules and aggregating evidence across 2,000 benchmark‑disjoint tasks. Experiments on TB2.0 and SWE‑Bench Verified show consistent gains on unseen tasks and cross‑model transfer.
Hugging Face Daily Papersarxiv.orgSiwei Wu, Jincheng Ren, Yizhi Li8d1 minpaper
Grounded Skill Synthesis from Code at Scale for Agentic Intelligence arxiv.org
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.orgYongqi Tong, Pan Wang, Hang Wang18d1 minpaper
CERA-MoA: Co-Evolving Routing Mechanisms with Continually Learning LLM Agents arxiv.org
CERA-MoA proposes a reinforcement‑learning loop where a router and a set of LLM agents are trained together. A “familiarity” estimator reads mid‑layer hidden states to predict each agent’s competence on a query, letting the router activate only a minimal subset of agents that meet a cumulative confidence threshold. The system also feeds targeted training examples to agents based on their evolving…
Hugging Face Daily Papersarxiv.orgJiaxuan Jiang, Liyuan He, Zhixuan Fang6d1 minpaper

GraphSkillEvo: Evolutionary Optimization of Graph-Structured Agent Skills

Summary

Related reading

COBRA-Skills: Contextual Bandit-Guided Evolution for Agent Skill Optimizationarxiv.org

Reflect, Revise, Reuse: Training-Free Skill Evolution for GUI Agentsarxiv.org

EvolveTrade: Experience-Driven Policy Refinement for Self-Evolving LLM Trading Agentsarxiv.org

ModularRSI: Modular and Generalizable Recursive Harness Self-Improvementarxiv.org

Grounded Skill Synthesis from Code at Scale for Agentic Intelligencearxiv.org

CERA-MoA: Co-Evolving Routing Mechanisms with Continually Learning LLM Agentsarxiv.org

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

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

EvolveTrade: Experience-Driven Policy Refinement for Self-Evolving LLM Trading Agents arxiv.org

ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement arxiv.org

Grounded Skill Synthesis from Code at Scale for Agentic Intelligence arxiv.org

CERA-MoA: Co-Evolving Routing Mechanisms with Continually Learning LLM Agents arxiv.org