RESOURCE2SKILL turns multimodal resources into executable agent skills
microsoft · hf · 2026-07-20
Microsoft and collaborators introduce RESOURCE2SKILL, a framework that distills multimodal human resources—tutorial videos, repositories, articles, and reference artifacts—into executable skills for software agents.
- It organizes skills into a hierarchical multimodal Skill Wiki.
- Each entry combines structured text, code, visual examples, metadata, and provenance so agents can reuse complementary signals from different sources.
- At inference time, agents retrieve and compose skills from the wiki; if coverage is insufficient, the same operator can acquire new skills online.
- Across seven practical authoring domains, the method improves average overall score by +11.9 points over no-skill agents and beats strong harness baselines in 26 of 28 main-aggregate model-domain cells.
- Ablations show gains from multimodal format, hierarchy, source diversity, selection strategy, and online acquisition.
Related event: Microsoft Open-Sources Resource2Skill to Turn Media into Skills(4 posts)→
More from coding & agent
- The browser main thread is expensive: a practical guide to JavaScript and CSS animation cost — jh3yy · 2026-09-11
- Inspired by OpenAI's 10,000-agent run, dev open-sources a crowdsourced agent problem-solving platform — Benjaminsen · 2026-09-11
- Lucid: open-source Mac app keeps your laptop awake only while AI agents run — Pitiful_Hedgehog_600 · 2026-09-11
- banteg's snail project crowdsources AI agents to finish matching Snail Mail's 20 remaining functions — banteg · 2026-09-11
- Alex Townsend posts 200 open problems in numerical linear algebra for humans and AI agents — IgorCarron · 2026-09-11
- Kimi K2.8 Preview rolls out: near-K3 coding performance, 1M context for all tiers — teortaxesTex · 2026-09-11