研究库 论文知识库

内容库 / 论文

arXiv:2609.09134 · 评测基准

Co-Evolving Harnesses and Models: On-Policy Correction Helps Weaker Models Catch Up Where Imitation Fails

Co-Evolving Harnesses and Models: On-Policy Correction Helps Weaker Models Catch Up Where Imitation Fails

类型：arxiv
标识：2609.09134
链接：https://arxiv.org/abs/2609.09134
主分类：evaluation
形态：method
TLDR：Agent harnesses (the system prompt, tool set, execution hooks, and context-management scaffolding around a model) are a critical determinant of agentic task success. Automated harness evolution can enable smaller models to perform well on domain-specific tasks at a fraction of frontier-model cost. Since both the harness and model weights shape behavior, we ask how harness evolution and lightweight fine-tuning should be combined. Across seven enterprise agent tasks, we first evolve a harness with the weaker model, then find that a stronger expert often uses it more effectively, suggesting exper
副分类：agent
待LLM分类：否
来源文件：
/inbox/tom/_candidates/2026-09-10-agent-rag-longcontext-candidates.json

相关 · 按语义匹配

笔记精读批判 · Reasoning vs Planning (FLARE / 2601.22311)

笔记 Tom 文献雷达 · Agent + RAG + 长上下文 · 2026-08-27 20:40

笔记 Agentic World Modeling · arXiv:2604.22748v3 · agent · 关键短审稿

笔记 Tom 文献雷达 · Agent/RAG/长上下文 · 2026-08-27 14:40

笔记 Tom 文献雷达 · AI Agent / RAG / 长上下文 · 2026-09-05 14:40

仓库 ZGTvishal/MARS-Multi-Agent-Research-System

arXiv

2609.09134

TLDR

Agent harnesses (the system prompt, tool set, execution hooks, and context-management scaffolding around a model) are a critical determinant of agentic task success. Automated harness evolution can enable smaller models to perform well on domain-specific tasks at a fraction of frontier-model cost. Since both the harness and model weights shape behavior, we ask how harness evolution and lightweight fine-tuning should be combined. Across seven enterprise agent tasks, we first evolve a harness with the weaker model, then find that a stronger expert often uses it more effectively, suggesting exper

arXiv ↗ 中文全文