arXiv AI

HarnessBandit: Joint Learnability-Transferability Scheduling for Multi-Harness Agentic Reinforcement Learning

arXiv Computation and Language
Oct 8

CoTrace: Data Recipes for Training Terminal Agents with Harness-Model Co-Evolution

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
arXiv AI
Oct 12

Multi-Harness Reinforcement Learning for Coding Agents: Training Gains and Harness Dependence

The study evaluates multi-harness reinforcement learning (RL) for coding agents by training two Qwen3-8B RL variants—one with rewards normalized within each harness and one across harnesses—using identical replay data. Results show modest gains over the supervised fine-tuning baseline (+0.48 and +0.77 percentage points for within and cross normalization, respectively), but no consistent advantage of cross normalization on unseen harnesses. Performance differences across harnesses are much larger than the training gains, indicating that harness dependence remains a significant challenge.

By Chenqian Le, Jiayi Cheng, Qijia He, Runhao Li, Yinghao Li, Xupeng Chen
arXiv Machine Learning
Aug 7

EvoHarness-RL: Learning Self-Evolving Runtime Harness for Long-Horizon LLM Agents

arXiv:2608. 05446v1 Announce Type: new Abstract: Long-horizon LLM agents increasingly rely on external execution support to maintain state, track progress, invoke tools, verify outcomes, and reuse experience across interactions.

By Xuying Ning, Dongqi Fu, Tianxin Wei, Hanqing Zeng, Yuanchen Bei, Bingxuan Li, Zihao Li, Qifan Wang, Xiang Shen, Yifan Wu, Jiayi Liu, Hong Li, Yinglong Xia, Xiangjun Fan, Hanghang Tong, Jingrui He
arXiv Machine Learning
Oct 7

EvoHarness-RL: Learning Runtime Harness Coordination for Self-Evolving Agents

arXiv:2608.05446v2 Announce Type: replace Abstract: Long-horizon LLM agents increasingly rely on external execution support to maintain state, track progress, recover from failures, and reuse experie...

By Xuying Ning, Dongqi Fu, Tianxin Wei, Yuanchen Bei, Xiyuan Yang, Wujiang Xu, Yueqi Song, Bingxuan Li, Zihao Li, Hanqing Zeng, Xiang Shen, Yajuan Wang, Yifan Wu, Qifan Wang, Jiayi Liu, Hong Li, Yinglong Xia, Xiangjun Fan, Hanghang Tong, Jingrui He
arXiv AI
Aug 18

ClawGym II: Exploring Black-Box RL on Agent Harness

arXiv:2608. 16798v1 Announce Type: cross Abstract: Agent harnesses have substantially improved performance on long-horizon tasks by coordinating agent interactions with the environment.

By Huatong Song, Fei Bai, Ming Yang, Renyuan Li, Jia Deng, Jujie He, Zhange Zhang, Daixuan Cheng, Yan Xing, Qi Yun, Xuxing Chen, Danyang Li, Feng Chang, Chuan Hao, Ran Tao, Jian Yang, Bryan Dai, Wayne Xin Zhao, Mingjie Tang, Ji-Rong Wen
Hugging Face Trending Papers
Oct 27

EnvSched: Environment-Aware Scheduling for Rollout-Efficient Agent Reinforcement Learning

EnvSched is an online scheduler that learns from rollout history to improve rollout efficiency in agent reinforcement learning. It assigns scheduling value by exploiting tasks likely to yield informative reward differences and by covering underobserved environments and interaction patterns. By modeling environment–task pairs in a dual-relation graph and propagating historical rollout statistics, EnvSched predicts reward variance and allocates batches to tasks with high predicted variance, achieving higher scores than random selection within fewer training steps.

arXiv AI
Oct 15

HarnessMDP: Learning to Control LLM Agent Harnesses with Offline Reinforcement Learning

HarnessMDP is a learning-based framework that treats the execution harness of large language model agents as a learnable control layer. By formulating agent execution as a finite-horizon Markov decision process, the harness learns to select structural execution actions from the evolving agent state, using offline reinforcement learning from collected trajectories. Experiments on coding tasks, tau-bench, AgentBench, and other evaluation settings show that HarnessMDP consistently improves execution behavior and final task performance over baseline harnesses.

By Haiwen Yi, Xinyuan Song
arXiv Machine Learning
Oct 21

Elicitation or Expansion? Demystifying Gains from Agent Harness Optimization

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