arXiv Machine Learning June 25, 2026 By Kyungmin Kim, Youngbin Choi, Seoyeon Lee, Suhyeon Jun, Dongwoo Kim, Sangdon Park

The Interplay of Harness Design and Post-Training in LLM Agents

Read the original on arXiv Machine Learning →

arXiv:2606. 25447v1 Announce Type: new Abstract: Tool-integrated LLM agents are often wrapped within a harness: the scaffolding that determines which tools are exposed, how they are described, and what auxiliary information accompanies each per-step observation.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

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

llms agents reinforcement-learning fine-tuning

arXiv AI

Jul 17

MemoHarness: Agent Harnesses That Learn from Experience

arXiv:2607. 14159v1 Announce Type: new Abstract: An agent harness is the external control layer that turns a base LLM into an executable agent by managing context, tools, orchestration, memory, decoding, and output handling.

By Yue Huang, Wenjie Wang, Han Bao, Yuchen Ma, Xiaonan Luo, Yi Nian, Haomin Zhuang, Zheyuan Liu, Yue Zhao, Xiangliang Zhang

llms agents benchmarks

arXiv AI

Aug 7

HarnessOpt-Bench: Evaluating LLMs at Harness Optimization

arXiv:2608. 06301v1 Announce Type: new Abstract: As LLMs are increasingly deployed within agentic systems, their capabilities depend not only on the model weights but also on the harness: the prompts, tools, control flow, memory, and orchestration code surrounding them.

By Varun Ursekar, Apaar Shanker, Yash Maurya, Shehab Yasser, Vijay S. Kalmath, Veronica Chatrath, Yuan Xue

llms agents benchmarks

arXiv AI

Jun 2

ToolSelf: Unifying Task Execution and Self-Reconfiguration via Tool-Driven Emergent Adaptation

arXiv:2602. 07883v3 Announce Type: replace Abstract: LLM-powered agentic systems excel at complex long-horizon tasks, but remain constrained by static configurations fixed before execution.

By Jingqi Zhou, Sheng Wang, Dezhao Deng, Junwen Lu, Junwei Su, Qintong Li, Jiahui Gao, Hao Wu, Jiyue Jiang, Lingpeng Kong, Dunhong Jin, Chuan Wu

llms agents reinforcement-learning fine-tuning benchmarks

arXiv AI

Jul 8

Learning to Control LLM Agent Harnesses with Offline Reinforcement Learning

arXiv:2607. 05458v1 Announce Type: cross Abstract: Large language model (LLM) agents are usually improved by changing prompts, models, or hand-written workflows, while the execution harness around the model is treated as fixed infrastructure.

By Haiwen Yi, Xinyuan Song

llms agents reinforcement-learning benchmarks

arXiv AI

Aug 11

Hierarchical Self-Improvement: A Framework for Task-Specific Evolvable Agent Harnesses

arXiv:2608. 08466v1 Announce Type: new Abstract: Modern LLM agents are often improved by modifying prompts, tools, or workflows manually, while the executable scaffold surrounding the model---the \emph{harness}---is typically treated as a fixed artifact after deployment.

By Tailin Zhou

llms agents

Related stories

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

MemoHarness: Agent Harnesses That Learn from Experience

HarnessOpt-Bench: Evaluating LLMs at Harness Optimization

ToolSelf: Unifying Task Execution and Self-Reconfiguration via Tool-Driven Emergent Adaptation

Learning to Control LLM Agent Harnesses with Offline Reinforcement Learning

Hierarchical Self-Improvement: A Framework for Task-Specific Evolvable Agent Harnesses