RESOURCE2SKILL: Distilling Executable Agent Skills from Human-Created Multimodal Resources

Hugging Face Daily Papers Papers

Summary

RESOURCE2SKILL is a framework that distills executable agent skills from multimodal resources like tutorial videos, code repositories, articles, and artifacts into a hierarchical SkillWiki, improving agent performance by 11.9 percentage points over no-skill agents.

Skills are a useful abstraction for software agents, turning human and agent experience into reusable procedural knowledge. Yet existing skill libraries are mostly hand-written, text-centric, or derived from agent traces, leaving tutorial videos and other multimodal human resources largely underused. We present RESOURCE2SKILL, a framework that distills multimodal resources, including tutorial videos, repositories, articles, and reference artifacts, into executable skills for software agents. RESOURCE2SKILL organizes these skills as a hierarchical multimodal Skill Wiki, where each entry combines structured text, code, visual examples, metadata, and provenance. This design preserves complementary signals from different resources: videos capture temporal operations and visual effects, code captures executable tool patterns, and articles or artifacts provide conceptual and stylistic grounding. At inference time, agents retrieve and compose relevant skills from the wiki; when coverage is insufficient, the same construction operator can acquire new skills online. Across seven practical authoring domains, RESOURCE2SKILL improves average overall score by +11.9 percentage points over no-skill agents and outperforms strong harness baselines in 26 of 28 main-aggregate model-domain cells. Ablations confirm the value of multimodal skill format, hierarchical organization, source diversity, selection strategy, and online acquisition.
Original Article
View Cached Full Text

Cached at: 07/20/26, 01:25 PM

Paper page - RESOURCE2SKILL: Distilling Executable Agent Skills from Human-Created Multimodal Resources

Source: https://huggingface.co/papers/2606.29538

Abstract

Skillsareausefulabstractionforsoftwareagents,turninghumanandagentexperienceintoreusableproceduralknowledge.Yetexistingskilllibrariesaremostlyhand-written,text-centric,orderivedfromagenttraces,leavingtutorialvideosandothermultimodalhumanresourceslargelyunderused.WepresentRESOURCE2SKILL,aframeworkthatdistillsmultimodalresources,includingtutorialvideos,repositories,articles,andreferenceartifacts,intoexecutableskillsforsoftwareagents.RESOURCE2SKILLorganizestheseskillsasahierarchicalmultimodalSkillWiki,whereeachentrycombinesstructuredtext,code,visualexamples,metadata,andprovenance.Thisdesignpreservescomplementarysignalsfromdifferentresources:videoscapturetemporaloperationsandvisualeffects,codecapturesexecutabletoolpatterns,andarticlesorartifactsprovideconceptualandstylisticgrounding.Atinferencetime,agentsretrieveandcomposerelevantskillsfromthewiki;whencoverageisinsufficient,thesameconstructionoperatorcanacquirenewskillsonline.Acrosssevenpracticalauthoringdomains,RESOURCE2SKILLimprovesaverageoverallscoreby+11.9percentagepointsoverno-skillagentsandoutperformsstrongharnessbaselinesin26of28main-aggregatemodel-domaincells.Ablationsconfirmthevalueofmultimodalskillformat,hierarchicalorganization,sourcediversity,selectionstrategy,andonlineacquisition.

View arXiv pageView PDFProject pageGitHub36Add to collection

Get this paper in your agent:

hf papers read 2606\.29538

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2606.29538 in a model README.md to link it from this page.

Datasets citing this paper1

#### microsoft/RESOURCE2SKILL Updated3 days ago • 2.05k • 4

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2606.29538 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

VISUALSKILL: Multimodal Skills for Computer-Use Agents

arXiv cs.CL

VisualSkill proposes a hierarchical multimodal skill library for computer-use agents that combines text and figures, achieving a 15.3 point absolute lift on CUA benchmarks over text-only baselines by retaining visual information for GUI interaction.