| title | Harness^2: Recursive Agent Harnessing for an Open World |
|---|---|
| authors | Ruiyao Xu, Yanfei Chen, Zhongying CuiZhu, Bhavana Dalvi Mishra, Yifei Ming, Han Yu, Rujun Han, Chen-Yu Lee, Tomas Pfister |
| date | 2026-10-09 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2610.14224 |
| affiliation | |
| upvotes | 84 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | LLM agents' capabilities depend not only on their underlying models but also on their execution harnesses. Recursive self-improvement (RSI) offers a promising approach to automatically evolve these harnesses. However, deploying RSI in open-world settings still faces two critical challenges. First, open-world tasks are typically unseen during the harness design phase and novel at test time, leaving no ground-truth verifiers to reliably guide online harness edits. Second, the RSI process remains highly task-specific and fails to generalize to novel scenarios. We introduce Harness^2, a plug-and-play, recursive agent harnessing framework that addresses these challenges through two connected levels of recursion. Task-level recursion refines the current task's harness using a contrastive Propose-Probe-Compose step that reliably guides edits without ground-truth verifiers, and can be scaled further via parallel or sequential recursion. Harnessing-level recursion then extracts experience from these edits to update a continual improvement harness, enabling the agent to better adapt to future tasks. Across three professional benchmarks and four model-harness configurations, a single step consistently improves GLM-5 and Gemini 3.5 Flash over their base harnesses, yielding gains of up to 11.5 points on WorkBuddy-Bench, 4.5 points on JobBench, and 11.8 percentage points on LAB, with further gains as the task-level recursion budget increases. |
cite
@misc{xu2026harness,
title={Harness^2: Recursive Agent Harnessing for an Open World},
author={Ruiyao Xu and Yanfei Chen and Zhongying CuiZhu and Bhavana Dalvi Mishra and Yifei Ming and Han Yu and Rujun Han and Chen-Yu Lee and Tomas Pfister},
year={2026},
eprint={2610.14224},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2610.14224}
}