Evo-Harness: Context-to-Harness Skill Compilation for Self-Evolving Agents

[2608.15071] Evo-Harness: Context-to-Harness Skill Compilation for Self-Evolving Agents Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Artificial Intelligence arXiv:2608.15071 (cs) [Submitted on 15 Aug 2026 ( v1 ), last revised 30 Aug 2026 (this version, v2)] Title: Evo-Harness: Context-to-Harness Skill Compilation for Self-Evolving Agents Authors: Tianxin Wei , Zhan Shi , Minhua Lin , Bing He , Zewen Liu , Yisi Sang , Yuanchen Bei , Xuying Ning , Jiaru Zou , Ting-Wei Li , Xiao Lin , Yanjun Zhao , Chi Wang , Benoit Dumoulin , Dakuo Wang , Jingrui He , Hanqing Lu View a PDF of the paper titled Evo-Harness: Context-to-Harness Skill Compilation for Self-Evolving Agents, by Tianxin Wei and 16 other authors View PDF HTML (experimental) Abstract: Learning from experience is critical for developing capable, self-improving large language model (LLM) agents. Existing methods typically extract knowledge from accumulated trajectories via reflection, memory, rules, or skills. However, agents in realistic environments continuously encounter novel tasks, often offering only a one-shot opportunity to improve. These executions yield rich but highly noisy contexts, entangling broadly useful lessons with task-specific artifacts. Critically, prior works rarely validate their effectiveness on complex real-world tasks or isolate the underlying drivers of improvement. To address these gaps, we formulate online harness learning, where a frozen agent improves by continually updating a structured harness across sequential tasks. This formulation enables a systematic study of key self-improvement factors through our proposed Evo-Harness. At its core, context-to-harness skill compilation distills noisy, single-shot executions into reusable skill harnesses for cross-domain and topic-level adaptation. To demonstrate the efficacy of one-shot skill compilation, we evaluate across five realistic benchmarks (TerminalBench2, SWE-bench, CL-Bench, -bench, WebArena-Infinity). Our extensive analysis demonstrates the effectiveness of Evo-Harness and provides a principled understanding of how LLM agents can effectively learn on the fly. Our code is available at this https URL . Comments: EMNLP 2026 Main Subjects: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL) Cite as: arXiv:2608.15071 [cs.AI] (or arXiv:2608.15071v2 [cs.AI] for this version) https://doi.org/10.48550/arXiv.2608.15071 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Tianxin Wei [ view email ] [v1] Sat, 15 Aug 2026 06:43:56 UTC (600 KB) [v2] Sun, 30 Aug 2026 19:47:36 UTC (600 KB) Full-text links: Access Paper: View a PDF of the paper titled Evo-Harness: Context-to-Harness Skill Compilation for Self-Evolving Agents, by Tianxin Wei and 16 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.AI < prev | next > new | recent | 2026-08 Change to browse by: cs cs.CL References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Evo-Harness: Context-to-Harness Skill Compilation for Self-Evolving Agents#611022
• Next-Generation Agentic Reinforcement Learning Systems Enable Self-Evolving Agents#329051
• SkillDRE: Dual-Stage Red-Team Evolution of Agent Skills via Pre-Execution and Runtime Feedback#1116731
• SkillClaw: Let Skills Evolve Collectively with Agentic Evolver#130768
• SkillClaw: Let Skills Evolve Collectively with Agentic Evolver#2654