arXiv:2605.08693v3 Announce Type: replace Abstract: Skills provide an effective mechanism for improving LLM agents on complex tasks, yet in existing agent frameworks, their creation, refinement, and...
arXiv:2606. 14239v1 Announce Type: new Abstract: Agent skills are structured procedural packages that guide frozen LLM agents in specialized workflows.
arXiv:2606. 01993v1 Announce Type: cross Abstract: Abundant procedural knowledge on the Web holds great potential for helping agents solve long-horizon tasks.
arXiv:2609.36746v1 Announce Type: new Abstract: Agent skills provide a lightweight mechanism for self-evolving agents to accumulate reusable procedural knowledge without updating model parameters. Ho...
The paper introduces SGUID, a method that selects a compact subset of skills for distillation in large language models. It shows that fewer than 25% of retrieved skills are useful for on‑policy distillation and that distilling only the selected skills can match or surpass full‑bank distillation while using up to 11× fewer skills. SGUID also enables stable model‑skill co‑evolution by iteratively curating new skill banks from updated model rollouts.
arXiv:2605.17734v2 Announce Type: replace Abstract: Equipping LLM agents with reusable skills derived from past experience has become a popular and successful approach for tackling complex and long-h...
arXiv:2606. 01311v1 Announce Type: cross Abstract: Large language model (LLM) agents increasingly rely on reusable external skills to solve long-horizon interactive tasks.
arXiv:2608.22610v1 Announce Type: new Abstract: Agent skills, structured artifacts distilled from interaction trajectories and dynamically reused from skill banks, have become a central mechanism for...
arXiv:2606. 11543v1 Announce Type: new Abstract: Agent Skills augment large language model (LLM) agents with procedural knowledge at inference time, but current benchmarks rarely distinguish what a Skill says from how it is organized.
SkillGym is an automatic pipeline that generates verifiable environments for training skill-use agents. It crawls internet skills, filters for reproducible workflows, and uses a builder‑reviewer process to create difficulty‑controlled tasks with reference solutions and verifiers. The system builds 6.8k environments, collects 19k successful trajectories, and fine‑tunes LLMs from 2B to 122B parameters, improving performance and skill invocation rates.
arXiv:2610.10088v1 Announce Type: cross Abstract: Self-evolving agents distill task-solving experience into skills for future reuse, but these skills can encode incorrect procedures or non-transferab...
TRACE (TRAjectory-Contrastive Evolution) is a self‑evolving skill bank that improves the consistency and limit‑awareness of large‑language‑model agents without changing the model weights. By iteratively refining modular skills based on successful and failed trajectories, TRACE raises consistent performance (Pass^3) on the CAR‑bench in‑car assistant tasks from 59.9 % to 94.5 % on GPT‑5.5 and achieves first place on the hidden set with GPT‑5.6‑Sol. The approach demonstrates that a skill‑based, self‑evolution loop can convert a model’s potential into stable, reliable behavior.