SkillMaster: Toward Autonomous Skill Mastery in LLM Agents

• URL: http://arxiv.org/abs/2605.08693v2
• Date: Tue, 12 May 2026 07:27:47 GMT
• Title: SkillMaster: Toward Autonomous Skill Mastery in LLM Agents
• Abstract summary: We propose SkillMaster, a training framework that teaches agents to create new skills, refine existing skills, and select accumulated skills during task solving.<n>First, we train agents through trajectory-informed skill review, teaching agents to propose, update, or retain skills based on evidence from completed episodes.<n>Second, each candidate skill edit is designed to be evaluated by its counterfactual utility on related probe tasks, providing a direct learning signal for training skill-editing decisions.<n>Third, we introduce DualAdv-GRPO, which separately estimates advantages for task-solving actions and skill-editing decisions, stabilizing joint training across task solving and
• Score: 27.651128308229378
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Skills provide an effective mechanism for improving LLM agents on complex tasks, yet in existing agent frameworks, their creation, refinement, and selection are typically governed by external teachers, hand-designed rules, or auxiliary modules. As a result, skills remain external resources to be invoked, rather than capabilities that agents can develop, adapt, and internalize through experience. To endow LLM agents with autonomous skill mastery, we propose SkillMaster, a training framework that teaches agents to create new skills, refine existing skills, and select accumulated skills during task solving. This capability is achieved through three key designs. First, we train agents through trajectory-informed skill review, teaching agents to propose, update, or retain skills based on evidence from completed episodes. Second, each candidate skill edit is designed to be evaluated by its counterfactual utility on related probe tasks, providing a direct learning signal for training skill-editing decisions. Third, we introduce DualAdv-GRPO, which separately estimates advantages for task-solving actions and skill-editing decisions, stabilizing joint training across task solving and skill management. Experiments on ALFWorld and WebShop show that SkillMaster improves the overall success rate over state-of-the-art baselines by 8.8% and 9.3%, respectively, achieving the best performance among all compared methods. Further analysis reveals a marked shift in agent capability: agents trained with SkillMaster can identify skill failures, refine procedural knowledge from trajectory evidence, and transfer improvements to future tasks with limited skill-bank edits. Overall, SkillMaster moves LLM agents beyond mere skill use toward self-improving agents capable of developing, adapting, and applying their own skill repertoires.

Related papers

• SkillForge: Evolving Verifiable Skills for Reinforcement Learning Agents [17.565432600589414]
  Large language model (LLM) agents are trained with reinforcement learning (RL) for complex decision-making tasks.<n>Recent skill-based approaches, such as SkillRL, attempt to address this issue by extracting skills from raw trajectories.<n>We propose SkillForge, a framework for continuous skill evolution that enables skills to be verified and refined through environment interaction.
  arXiv  Detail & Related papers  (2026-08-25T15:52:10Z)
• Progressive Agent Skill Generation via Reinforcement Learning [29.782307460602876]
  We propose Skill-$$, a reinforcement learning method for progressively generating high-quality agent skills.<n>Specifically, we formulate skill generation as a sequential editing process that decomposes skill construction into individually evaluable edits.<n>Experiments show that Skill-$$ generates more effective skills than methods based on pipeline-style consolidation.
  arXiv  Detail & Related papers  (2026-08-03T04:14:59Z)
• SkillCoach: Self-Evolving Rubrics for Evaluating and Enhancing Agentic Skill-Use [21.05387636058484]
  SkillCoach is a self-evolving framework for evaluating and enhancing agentic skill-use.<n>It derives skill-grounded process rubrics from real rollouts and evaluates trajectories along four dimensions.<n>It keeps the external verifier as a separate outcome signal, allowing process quality to be distinguished from accidental task success.
  arXiv  Detail & Related papers  (2026-07-02T08:28:51Z)
• Generative Skill Composition for LLM Agents [58.47191648555256]
  LLM agents benefit from skills for solving complex tasks.<n>As skill libraries grow, selecting an appropriate skill composition has emerged as a central bottleneck.<n>We propose SkillComposer, which instantiates structured skill composition as task-conditioned skill sequence prediction.
  arXiv  Detail & Related papers  (2026-06-30T17:53:09Z)
• 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)
• SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision [41.562357872885826]
  We propose SkillRevise, an execution-grounded framework designed to iteratively refine agent skills.<n>SkillRevise diagnoses skill defects from execution evidence, retrieves relevant repair principles from a general memory, and applies execution-anchored edits.<n>It substantially outperforms one-shot baselines, improving the base agent's success rate on SkillsBench from 36.05% to 61.63%.
  arXiv  Detail & Related papers  (2026-05-31T10:19:13Z)
• 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)
• From Context to Skills: Can Language Models Learn from Context Skillfully? [56.5857437218136]
  Ctx2Skill is a self-evolving framework that autonomously discovers, refines, and selects context-specific skills.<n>It can be plugged into any language model to obtain better context learning capability.
  arXiv  Detail & Related papers  (2026-04-30T09:53:15Z)
• Skill Retrieval Augmentation for Agentic AI [28.71123853744993]
  In existing agent systems, the dominant strategy for incorporating skills is to enumerate available skills within the context window.<n>This paper formulates Skill Retrieval Augmentation (SRA), a new paradigm in which agents dynamically retrieve, incorporate, and apply relevant skills from large external skill corpora on demand.<n>SRA-Bench is the first benchmark for evaluation of the full SRA pipeline, covering skill retrieval, skill incorporation, and end-task execution.
  arXiv  Detail & Related papers  (2026-04-27T15:19:59Z)
• How Well Do Agentic Skills Work in the Wild: Benchmarking LLM Skill Usage in Realistic Settings [29.3744517703302]
  We study the first comprehensive study of skill utility under progressively challenging realistic settings.<n>Our findings reveal that performance gains degrade consistently as settings become more realistic.<n>We show that query-specific refinement substantially recovers lost performance when the initial skills are of reasonable relevance and quality.
  arXiv  Detail & Related papers  (2026-04-06T00:10:30Z)
• EvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification [85.3692584167951]
  Anthropic proposes the concept of skills for LLM agents to tackle multi-step professional tasks.<n>A tool is a single, self-contained function, whereas a skill is a structured bundle of interdependent multi-file artifacts.<n>EvoSkills is a self-evolving skills framework that enables agents to autonomously construct complex, multi-file skill packages.
  arXiv  Detail & Related papers  (2026-04-02T06:43:20Z)
• Dynamic Dual-Granularity Skill Bank for Agentic RL [34.161117844675324]
  D2Skill is a dynamic dual-granularity skill bank for agentic reinforcement learning.<n>It organizes reusable experience into task skills for high-level guidance and step skills for fine-grained decision support and error correction.
  arXiv  Detail & Related papers  (2026-03-30T17:32:11Z)
• MaestroMotif: Skill Design from Artificial Intelligence Feedback [67.17724089381056]
  MaestroMotif is a method for AI-assisted skill design, which yields high-performing and adaptable agents.<n>We present MaestroMotif, a method for AI-assisted skill design, which yields high-performing and adaptable agents.
  arXiv  Detail & Related papers  (2024-12-11T16:59:31Z)
• Discovering Generalizable Skills via Automated Generation of Diverse Tasks [82.16392072211337]
  We propose a method to discover generalizable skills via automated generation of a diverse set of tasks. As opposed to prior work on unsupervised discovery of skills, our method pairs each skill with a unique task produced by a trainable task generator. A task discriminator defined on the robot behaviors in the generated tasks is jointly trained to estimate the evidence lower bound of the diversity objective. The learned skills can then be composed in a hierarchical reinforcement learning algorithm to solve unseen target tasks.
  arXiv  Detail & Related papers  (2021-06-26T03:41:51Z)

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.