paper-with-me

Papers

DarwinX: Evolving Agent Harnesses Through Natural Selection

2026-07-31 · Yifan Zhang, Yutong Dai, Juntao Tan, Luyu Yang, Rishi Mullur, Thai Hoang, Zhiyuan Hu, James Zhu, Phil Mui, Silvio Savarese, Ran Xu, Zeyuan Chen hf

An LLM agent's capability depends not only on model weights but on its harness: prompts, tools, skills, and control flow. Self-improvement loops already edit harnesses, yet single-lineage search is path-dependent and local wins often regress other tasks. We introduce DarwinX, which treats self-evolution as selection over a population of harnesses with the model frozen: a preserve-and-extend contract admits only variants that extend coverage without regressing, an archive keeps alternative lineages for recombination, and failure-, teacher-, and self-derived evidence share one edit interface. Fitness comes from each benchmark's own verifier: no gold solutions, no hand-picked winners. Across four benchmarks that progressively separate the evolution signal from the test, one loop adds about 17 points on average: Terminal-Bench 2.1 rises +7.7 to 83.2% on a matched base and to the verified frontier at 84.7% on a stronger one; TerminalWorld's held-out split reaches 68.3%, ahead of every off-the-shelf agent; WebArena-Infinity real-task pass@1 rises from 43.5% to 93.0% audit-clean; and a Terminal-Bench 2.1 harness transfers unchanged to SWE-bench Verified. What evolves is general agent competence, not benchmark-specific patches, so it survives changes of task, verifier, and base model. A frozen model need not be a fixed agent: harness selection turns evaluation compute into durable capability.

📄 PDF Abstract BibTeX arXiv:2608.07545

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

$A^2E$ : An End-to-End Agent Auditing Engine

2026-08-10 · Haoning Wang, Mingxun Zhang, Chenyue Yu, Yingjun Shang 외 hf

With the rapid advancement of large language models (LLMs), harnesses have become essential infrastructure for deploying agents across a wide range of domains. The fast-evolving harness ecosystem has also made rigorous c…

EvoTrainer: Co-Evolving LLM Policies and Training Harnesses for Autonomous Agentic Reinforcement Learning

2026-06-02 · Guhong Chen, Yingcheng Shi, Yongbin Li, Binhua Li 외 arxiv

Autonomous LLM training is often framed as recipe search, which leaves the training harness largely static. This limitation sharpens in agentic RL, where shifting bottlenecks and scalar rewards mask diverse failure modes…

Reinforcement LearningMathematical ReasoningCode Generation

Natural-Language Agent Harnesses

2026-03-26 · Linyue Pan, Lexiao Zou, Shuo Guo, Jingchen Ni 외 arxiv

Agent performance is strongly shaped by the surrounding harness: the external execution system around a model that organizes a task run. Yet this logic is usually buried in tightly coupled controller code, which makes ha…

EvoSafeHarness: Evolving Model- and Domain-Specific Harnesses for Securing Agents

2026-09-05 · Nanxi Li, Yingzi Ma, Yulong Cao, Edward Suh 외 hf

Large Language Model (LLM) agents are turning language into real-world effects, making safety necessary against both indirect prompt injections and direct harmful requests. System-level safety harnesses add an enforcemen…

HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry

2026-06-12 · Tingyang Chen, Shuo Lu, Kang Zhao, Weicheng Meng 외 arxiv

AI agent performance depends critically on the runtime harness, comprising the prompts, tools, memory, and control flow that mediate how a model observes, reasons, and acts. Yet today's harnesses remain largely hand-craf…

Reinforcement Learning