跳到正文
arXiv cs.AI· Jiahang Lin, Jiahao Chen, Yiding Wang, Shichun Liu, Chengjun Pan, Shihan Dou, Honglin Guo, Yuyang Hu, Changhao Jiang, Zhenhua Han, Hang Yan, Qi Zhang, Tao Gui, Xuanjing Huang·· 2 小时前AI 评分51

AHE-Beta 提出以需求为中心的 Agent Harness 演化方法,pass@1 从 21.9% 提升至 33.3%

Agentic Harness Engineering Beta: Requirement-Centered Evolution of Agent Harnesses

AI 导读

复旦大学等机构研究团队提出 Agentic Harness Engineering Beta(AHE-Beta),以真实用户需求为中心驱动 agent harness 演化,包含模拟用户提需求、团队化修改和需求驱动选择三步。

正文 · 原文

Authors:Jiahang Lin, Jiahao Chen, Yiding Wang, Shichun Liu, Chengjun Pan, Shihan Dou, Honglin Guo, Yuyang Hu, Changhao Jiang, Zhenhua Han, Hang Yan, Qi Zhang, Tao Gui, Xuanjing Huang

View PDF HTML (experimental)

Abstract:Real-world harness engineering is driven by explicit and implicit user requirements, which guide development and validation. However, existing harness evolution methods often overlook implicit requirements and interaction needs, while using a single evolution agent to modify the harness and benchmark scores to select changes. This process often produces narrow patches and leads to benchmark-specific local optima. We introduce Agentic Harness Engineering Beta (AHE-Beta), a requirement-centered loop that brings real-world engineering practices into harness evolution. The loop consists of three steps: (1) User-driven evaluation lets simulated users raise their requirements as issues while they work with the harness over multiple turns. (2) Team-based modification implements those requirements as generalizable changes rather than task-specific patches. (3) Requirement-driven selection merges a change only when it resolves a verified requirement and passes review. Empirically, on held-out tasks, AHE-Beta raises pass@1 from 21.9% to 33.3% while using 40.8% fewer tokens than Base Harness, and achieves higher pass@1 than Claude Code, Meta-Harness, and AHE. In a blind human A/B test, real users prefer AHE-Beta in 31 of 48 valid pairs and rate it higher on all five dimensions, matching the directional preference of the user simulator. The human A/B results show that AHE-Beta achieves its goal of aligning harness evolution with real-world user requirements. Without further evolution, the gains transfer to GLM-5.3 and DeepSeek-V4.1-Flash with pass@1 improvements of 15.8% and 5.3% over Base Harness. Together, these results show that requirement-centered harness evolution is a more general method for improving agent capabilities.
Subjects: Software Engineering (cs.SE); Artificial Intelligence (cs.AI)
Cite as: arXiv:2611.24924 [cs.SE]
  (or arXiv:2611.24924v1 [cs.SE] for this version)
  https://doi.org/10.48550/arXiv.2611.24924

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Jiahang Lin [view email]
[v1] Wed, 18 Nov 2026 18:52:13 UTC (512 KB)

来源:arXiv cs.AI · arxiv.org