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

Page: https://stenobird.com/podcast/daily-paper-cast-7079649/skillsvote-lifecycle-governance-of-agent-skills-from-collection-recommendation-to-evolution
Text version: https://stenobird.com/podcast/daily-paper-cast-7079649/skillsvote-lifecycle-governance-of-agent-skills-from-collection-recommendation-to-evolution.md
Podcast: [Daily Paper Cast](https://stenobird.com/podcast/daily-paper-cast-7079649)
Published: 2026-05-20T04:14:15+00:00
Episode link: https://share.transistor.fm/s/6a5c9833
Audio file: https://media.transistor.fm/6a5c9833/8106bfe2.mp3
Processing state: not_requested
JSON: https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/skillsvote-lifecycle-governance-of-agent-skills-from-collection-recommendation-to-evolution
Duration seconds: 1371

## Resource

🤗 Upvotes: 112 | cs.CL, cs.AI Authors: Hongyi Liu, Haoyan Yang, Tao Jiang, Bo Tang, Feiyu Xiong, Zhiyu Li Title: SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution Arxiv: http://arxiv.org/abs/2605.18401v1 Abstract: 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.

## Actions

- request_transcript: `POST https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/skillsvote-lifecycle-governance-of-agent-skills-from-collection-recommendation-to-evolution/transcription-requests` — Idempotently request low-priority transcript generation for this episode.
- read_markdown: `GET https://stenobird.com/podcast/daily-paper-cast-7079649/skillsvote-lifecycle-governance-of-agent-skills-from-collection-recommendation-to-evolution.md` — Read the agent-friendly Markdown representation of this episode resource.

A page view does not enqueue transcription. Agents should invoke `request_transcript` explicitly when they need this episode processed.

## Transcript

Full transcripts are not published on public pages unless there is a clear rights basis.