Zhuoshi Pan, ZhiYuan Feng, Yukuo Cen, Honglin Lin, Junru Lu, Zhongxia Chen, Shuo Yang, H. Vicky Zhao · 2026 · arXiv
DOI: 10.48550/arXiv.2610.26770 · open-access PDF
Pengembangan Harness memainkan peran penting dalam membangun agen AI yang mampu. Pendekatan baru-baru ini meningkatkan harness melalui perbaikan diri recursive (RSI), tetapi peningkatan kinerja mereka sering datang dengan biaya eksekusi yang lebih tinggi. Kami memperkenalkan HarnessPro, metode bebas label untuk mengembangkan harness untuk meningkatkan kinerja tugas sambil mengurangi biaya eksekusi. Dalam pengaturan ini, harness kandidat dievaluasi menggunakan tes yang dihasilkan oleh LLM tanpa akses ke solusi dasar kebenaran atau tes resmi. agen khusus mendiagnosis lintasan eksekusi, merencanakan pembaruan dengan prioritas biaya kinerja yang berbeda, dan imple
Machine translation (Meta M2M100); the English original follows.
Harness development plays a crucial role in building capable AI agents. Recent approaches improve harnesses through recursive self-improvement (RSI), but their performance gains often come with higher execution costs. We introduce HarnessPro, a label-free method for evolving harnesses to improve task performance while reducing execution cost. In this setting, candidate harnesses are evaluated using LLM-generated tests without access to ground-truth solutions or official tests. Specialized agents diagnose execution trajectories, plan updates with different performance-cost priorities, and imple
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.26770, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange