SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution

Hugging Face Daily Papers Papers

Summary

SkillsVote is a governance framework for long-horizon LLM agents that manages reusable skills through structured collection, recommendation, and evolution, improving performance on Terminal-Bench 2.0 and SWE-Bench Pro without model updates.

Long-horizon LLM agents leave traces that could become reusable experience, but raw trajectories are noisy and hard to govern. We treat Agent Skills as an experience schema that couples executable scripts, with non-executable guidance on procedures. Yet open skill ecosystems contain redundant, uneven, environment-sensitive artifacts, and indiscriminate updates can pollute future context. We present SkillsVote, a lifecycle-governance framework for Agent Skills from collection and recommendation to evolution. SkillsVote profiles a million-scale open-source corpus for environment requirements, quality, and verifiability, then synthesizes tasks for verifiable skills. Before execution, SkillsVote performs agentic library search over structured skill library to expose instructional skill context. After execution, it decomposes trajectories into skill-linked subtasks, attributes outcomes to skill use, agent exploration, environment, and result signals, and admits only successful reusable discoveries to evidence-gated updates. In our evaluation, offline evolution improves GPT-5.2 on Terminal-Bench 2.0 by up to 7.9 pp, while online evolution improves SWE-Bench Pro by up to 2.6 pp. Overall, governed external skill libraries can improve frozen agents without model updates when systems control exposure, credit, and preservation.
Original Article
View Cached Full Text

Cached at: 05/19/26, 06:30 AM

Paper page - SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution

Source: https://huggingface.co/papers/2605.18401

Abstract

SkillsVote is a governance framework for long-horizon LLM agents that manages reusable skills through structured collection, recommendation, and evolution processes.

Long-horizon LLM agents leave traces that could become reusable experience, but raw trajectories are noisy and hard to govern. We treatAgent Skillsas anexperience schemathat couplesexecutable scripts, with non-executable guidance on procedures. Yet openskill ecosystemscontain redundant, uneven, environment-sensitive artifacts, and indiscriminate updates can pollute future context. We present SkillsVote, alifecycle-governance frameworkforAgent Skillsfrom collection and recommendation to evolution. SkillsVote profiles a million-scale open-source corpus forenvironment requirements, quality, andverifiability, then synthesizes tasks for verifiable skills. Before execution, SkillsVote performsagentic library searchover structured skill library to expose instructional skill context. After execution, it decomposes trajectories into skill-linked subtasks, attributes outcomes to skill use, agent exploration, environment, and result signals, and admits only successful reusable discoveries toevidence-gated updates. In our evaluation, offline evolution improves GPT-5.2 onTerminal-Bench 2.0by up to 7.9 pp, while online evolution improvesSWE-Bench Proby up to 2.6 pp. Overall, governed external skill libraries can improve frozen agents without model updates when systems control exposure, credit, and preservation.

View arXiv pageView PDFProject pageGitHubAdd to collection

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2605.18401 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2605.18401 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2605.18401 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

SkillFlow:Benchmarking Lifelong Skill Discovery and Evolution for Autonomous Agents

Hugging Face Daily Papers

SkillFlow introduces a benchmark of 166 tasks across 20 families for evaluating autonomous agents' ability to discover, repair, and maintain skills over time through a lifelong learning protocol. Experiments reveal a substantial capability gap among leading models, with Claude Opus 4.6 improving significantly while others show limited or negative gains from skill evolution.

SkillOS: Learning Skill Curation for Self-Evolving Agents

Hugging Face Daily Papers

This paper introduces SkillOS, a reinforcement learning framework that enables LLM agents to learn long-term skill curation policies for self-evolution, improving performance and generalization across tasks.

SkillFlow: Flow-Driven Recursive Skill Evolution for Agentic Orchestration

arXiv cs.AI

SkillFlow proposes a flow-driven recursive skill evolution framework for LLM-based agentic orchestration, using Tempered Trajectory Balance to prevent strategy collapse and provide transparent credit assignment. Experiments on 14 datasets show significant improvements over baselines in QA, math, code, and decision-making tasks.

SkillOpt: Executive Strategy for Self-Evolving Agent Skills

Hugging Face Daily Papers

SkillOpt introduces a systematic text-space optimizer for agent skills that trains skills as external agent state with stable updates and zero deployment inference overhead, achieving superior performance across multiple benchmarks and execution environments.