The study investigates how multi‑harness reinforcement learning (RL) affects coding agents by comparing two grouping strategies—Within (one group per task‑harness pair) and Cross (harnesses pooled within a task)—using a Qwen3‑8B policy trained on frozen task‑harness records from Aider, OpenHands, Qwen Code, and SWE‑agent. Across 24,000 sealed evaluations, the choice of evaluation harness dramatically increases solve rates (from 2.14 % to 9.27 %), while the grouping rule has a negligible effect. Both grouping rules yield similar gains on the same source harness, and Cross‑harness credit does not improve portability beyond Within‑harness credit, suggesting that multi‑harness RL reports should specify grouping boundaries and test on unseen harnesses.
By Chenqian Le, Jiayi Cheng, Qijia He, Runhao Li, Yinghao Li, Xupeng Chen
arXiv:2610.10426v1 Announce Type: new
Abstract: Terminal-agent capability depends jointly on model weights and the runtime harness that formats prompts, binds tools, and handles error recovery. Exist...
By Jixuan Chen, Jiaxin Zhang, Qinyuan Ye, Yada Pruksachatkun, Haoxiang Zhang, Jingming Zhuo, Yifan Zhang, Yutong Dai, Juntao Tan, Xiangyu Peng, Silvio Savarese, Zeyuan Chen, Lianhui Qin, Chien-Sheng Wu
Terminal-agent capability depends jointly on model weights and the runtime harness that formats prompts, binds tools, and handles error recovery. Existing harness-model co-evolution approaches improve...
The paper reports that applying reinforcement learning (RL) to the Kimi K2.7 Code model on 1,700 agentic coding tasks improves its performance on six external benchmarks. After a single epoch of GSPO training on a rank‑32 LoRA adapter, pass‑@1 scores increased across all benchmarks, with significant gains even on data released after training. The trained model also reduces agent steps and avoids common failure modes such as dropping requirements or breaking existing behavior.
By Sushant Mehta, Logan Ritchie, Edwin Chen
arXiv:2609.13739v1 Announce Type: cross
Abstract: Language-model agents are increasingly deployed through diverse harnesses that differ in system prompts, tool schemas, control loops, and trajectory...
By Hongliang Wei (Harbin Institute of Technology, Alibaba Cloud), Xiaobing Tu (Alibaba Cloud), Yinggui Wang (Alibaba Cloud), Zhengxi Liu (Alibaba Cloud), Rongkun Xue (Alibaba Cloud), Jinkui Ren (Alibaba Cloud), Xiantao Zhang (Alibaba Cloud), Debin Zhao (Harbin Institute of Technology), Xiaopeng Fan (Harbin Institute of Technology)
The paper investigates how optimizing the harness of language model agents—without changing model weights—affects performance. It distinguishes between gains that improve success on tasks already within reach (elicitation) and gains that broaden the range of solvable tasks (expansion). By comparing optimized harnesses to their pre‑optimization versions across static and dynamic tasks, the study finds that benefits can reverse at higher attempt budgets and that aggregate gains may mask shortcomings on harder tasks, highlighting the need for detailed diagnostics.
By Younghyun Kim, Wooseok Seo, Minseo Kim, Seunghyuk Oh, Minjae Lee, Donghoon Kim, Hyung Il Koo, Jaehyung Kim, Wonjun Kang
LEGO-RL is a framework that connects native coding-agent harnesses with scalable policy‑gradient training without altering the harnesses’ internal flow. It achieves faithful optimization through in‑process LLM proxying, reliable execution via sandbox orchestration, and observable training with automated validation and a Live UI. Experiments show LEGO‑RL improves the Qwen3.5‑35B‑A3B model’s performance on three native harnesses while preserving high rollout‑training probability correlation.
By Yiming Du, Yuxin Jiang, Tao Yuan, Jianbo Dai, Shaowei Wang, Jierun Chen, Chaofan Tao, Xianzhi Yu, Lifeng Shang, Kam-Fai Wong, Xiaohui Li, Haoli Bai
arXiv:2609.37105v1 Announce Type: cross
Abstract: Language model agents can be improved by updating their model weights or refining the harness that guides task execution. These components are couple...
By Jiexing Qi, Yu He, Jun Liu, Qichen Huang, Shaohua Hu, Zhan Dang, Guohua Chen, Rui Yang, Wen Jiang, Yang Liu, Tao Lyu, Fangming Li
The paper introduces Self-HPO, a recursive framework that alternates between optimizing the harness and the policy of large language model agents for coding tasks. By letting the current policy propose new harness candidates based on its failures, the method aligns harness evolution with policy improvement, leading to consistent performance gains across three benchmarks. Experiments show that Self-HPO raises the average resolve rate of Qwen3.5-35B-A3B from 57.8% to 64.8% and improves reliability and capability metrics, with benefits that generalize to out‑of‑distribution settings.
By Zhepei Wei, Wenlin Yao, Baolin Peng, Danqing Wang, Qianhui Wu, Hao Cheng, Yu Meng, Jianfeng Gao
arXiv:2610.01133v1 Announce Type: cross
Abstract: Scaling reasoning typically spends more compute on reinforcement learning (RL) or on inference. We show that a completed RL training history can yiel...
By Bangji Yang, Jiajun Fan, Hongba Ma, Ruihan Guo, Ge Liu
arXiv:2610.17666v1 Announce Type: cross
Abstract: Reinforcement learning with verifiable rewards (RLVR) for multi-turn agents relies on sparse terminal rewards that say little about individual steps....
By Xuyan Ye, Xiyan Fu, Shengda Fan, Jiawei Cui, Yankai Lin, Wei Lu
arXiv:2607. 27271v1 Announce Type: new Abstract: Code models are increasingly trained with execution feedback, but most training signals still stop at correctness.
By Huihao Jing, Haozhe Cui, Wenbin Hu, Shaojin Chen, Haochen Shi, Changxuan Fan, Yuxuan Liu, Hanyu Yang, Sirui Zhang, Ziyi Chen, Haoran Li, Yangqiu Song