研究库 论文知识库

内容库 / 论文

arXiv:2609.24974 · 评测基准

Harness-Zero: Harness Distillation via Agent-as-Harness

Harness-Zero: Harness Distillation via Agent-as-Harness

类型：arxiv
标识：2609.24974
链接：https://arxiv.org/abs/2609.24974
主分类：evaluation
形态：application
TLDR：Agent harnesses, the external systems that mediate model-environment interaction, can substantially improve agent performance, but their gains remain tied to the harness at deployment. Because the best harness varies across domains, instances, and models, a general-purpose agent must either settle for a suboptimal shared harness or route among an ever-growing set of specialized ones. We therefore study agent harness distillation: using a domain- or instance-optimized harness as training-time guidance and transferring the behaviors it induces into model weights, so that its gains survive under
副分类：agent
待LLM分类：否
来源文件：
/inbox/tom/_candidates/2026-09-22-agent-rag-longcontext-candidates.json

相关 · 按语义匹配

文档 Tom 评 flyP 的产出：On-Policy Distillation 三大要点解读（2607.13399）

攻略 nick7nlp/Awesome-LLM-On-Policy-Distillation · 上手攻略

仓库 nick7nlp/Awesome-LLM-On-Policy-Distillation

笔记 SPEAR: 训练-free 符号化过程奖励用于 RL 知识蒸馏 — 精读与批判

笔记 flyP 精读与批判 · 2026-07-28 15:50

文档 Stephen 自测 · R67 · 2026-09-06

arXiv

2609.24974

TLDR

Agent harnesses, the external systems that mediate model-environment interaction, can substantially improve agent performance, but their gains remain tied to the harness at deployment. Because the best harness varies across domains, instances, and models, a general-purpose agent must either settle for a suboptimal shared harness or route among an ever-growing set of specialized ones. We therefore study agent harness distillation: using a domain- or instance-optimized harness as training-time guidance and transferring the behaviors it induces into model weights, so that its gains survive under

arXiv ↗ 中文全文