arXiv cs.AI· Jingzhe Liu, Jiliang Tang, Tong Zhao, Neil Shah, Clark Mingxuan Ju·· 13 小时前AI 评分38
通过连续规模竞赛实现智能体框架进化：SSR 将更多任务锻造成更优 Harness
Forging More Tasks into Better Harnesses: Agentic Harness Evolution via Successive Scale Racing
AI 导读
针对智能体框架进化中任务池扩大反而导致性能下降的问题，研究者提出 Successive Scale Racing（SSR）框架，在每轮进化中按任务质量与覆盖度构造多样化证据组合，并以小算力预算对候选 harness 进行竞赛筛选。
正文 · 原文
Abstract:Agentic harness evolution optimizes an agent's instructions, tools, and control flow by using its task execution experiences as evolving evidence. While more evolution tasks should intuitively improve performance, our preliminary study reveals a paradoxical failure mode: the performance of existing methods degrades as the task pool expands. Our further analysis demonstrates that this degradation stems from suboptimal evidence selection during optimization, as different evidence combinations lead to substantially different evolution outcomes. To address this issue, we propose Successive Scale Racing (SSR), a framework that adaptively searches for optimal evidence combinations in each evolution round. SSR constructs diverse evidence combinations based on the corresponding task quality and coverage, and efficiently races the resulting candidate harnesses under a small compute budget. Empirically, across three distinct benchmarks, SSR achieves state-of-the-art results in all six configurations. Notably, as the task pool grows from 40 to 200, SSR steadily improves the pass rate from 64.3% to 68.3%, while the baselines' performances all drop. Furthermore, its racing mechanism identifies near-optimal candidates while reducing validation executions by 60%.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.28815 [cs.AI] |
| (or arXiv:2610.28815v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.28815 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jingzhe Liu [view email]
[v1]
Tue, 20 Oct 2026 18:36:33 UTC (216 KB)
来源：arXiv cs.AI · arxiv.org