paper-with-me

Papers

Living-Harness Is an Interactive-Agent Evolver

2026-07-29 · Yuetian Du, Yucheng Wang, He Xu, Jiexu Xu, Shanwen Tan, Bing Zhao, Boyu Yang, Zhijie Xu, Ming Kong, Hu Wei, Jie Liu, Qiang Zhu arxiv

Large language model (LLM) agents may recover from a failure within an episode or after a retry, yet the same execution failure can recur in later tasks because post-episode feedback rarely revises the persistent harness that guides future interactions. Static harnesses improve reliability through fixed tools, context, memory, and workflow structures, but remain unchanged after deployment. We propose $\textbf{Living-Harness}$, a self-evolving agent harness that converts each completed trajectory and its evaluator signals into posterior evidence for bounded harness updates. Guided by a domain-level $\textbf{Evolution-SOP}$ ($\textbf{S}$tandard $\textbf{O}$perating $\textbf{P}$rocedure), Living-Harness extracts an episode abstraction and structured update evidence, and writes two complementary forms of procedural knowledge: episodic memory that records trigger conditions, failure patterns, and recovery actions, and a state graph that records state nodes, repair edges, and transition rules. The updated harness state is retrieved to guide future interactions, while tools and base context remain frozen, allowing procedural repairs to accumulate across evolution cycles. On eight interactive environments derived from $τ^2$-Bench and MultiWOZ-2.4, Living-Harness improves average Pass@1 over the strongest interactive baseline by 10.07 and 9.91 percentage points, respectively, and supports retrieval-only reuse of the evolved harness state across model backbones.

📄 PDF Abstract BibTeX arXiv:2607.26598

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

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

2026-08-09 · Tailin Zhou hf

Modern LLM agents are often improved by modifying prompts, tools, or workflows manually, while the executable scaffold surrounding the model---the harness---is typically treated as a fixed artifact after deployment. This…

OPD-Evolver: Cultivating Holistic Agent Evolver via On-Policy Distillation

2026-06-16 · Guibin Zhang, Xun Xu, Yanwei Yue, Zikun Su 외 arxiv

Memory has become a standard substrate for self-evolving agents, yet retaining experience is not the same as learning how to evolve through it. Existing memory agents can store trajectories, retrieve reflections, or accu…

Adaptive Auto-Harness: Sustained Self-Improvement for Agentic System Deployment on Open-Ended Task Streams

2026-06-01 · Zewen Liu, Zhan Shi, Yisi Sang, Bing He 외 arxiv

Auto-harness systems such as A-Evolve, GEPA, and Meta-Harness improve LLM agents by optimizing prompts, skills, tools, memories, and supporting infrastructure from execution feedback, but they are typically evaluated on …

Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents

2026-05-28 · Minhua Lin, Juncheng Wu, Zijun Wang, Zhan Shi 외 arxiv

LLM agents are increasingly deployed as systems built around editable external harnesses, including prompts, skills, memories and tools, that shape task execution without changing model parameters. Harness self-evolution…

Instruction Following

AgentEvolver: Towards Efficient Self-Evolving Agent System

2025-11-13 · Yunpeng Zhai, Shuchang Tao, Cheng Chen, Anni Zou 외 arxiv

Autonomous agents powered by large language models (LLMs) have the potential to significantly enhance human productivity by reasoning, using tools, and executing complex tasks in diverse environments. However, current ap…

Reinforcement Learning