# HarnessForge：面向自适应智能体系统的框架与策略协同进化

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-06-01 15:00
- AIHOT 分数：52
- AIHOT 链接：https://aihot.virxact.com/items/cmq4z0tab0314slt2d4ej51w0
- 原文链接：https://arxiv.org/abs/2606.01779

## AI 摘要

HarnessForge提出元自适应框架，将LLM智能体系统形式化为框架-策略对，通过故障引导的框架定制和框架条件化的策略对齐实现协同进化。在五个跨领域基准上，基于Qwen3-4B和Qwen3-8B的HarnessForge相比仅优化框架或策略的基线最高提升12.0%，表明框架与推理策略的可执行兼容性对智能体系统自适应至关重要。代码已开源。

## 正文

LLM agents are increasingly expected to operate across heterogeneous task regimes that require distinct execution paradigms. This challenges fixed agent systems and motivates system-level meta-adaptation beyond isolated component updates. While existing works have adapted external harness or trained underlying reasoning policies, full-system adaptation remains insufficiently characterized. The adaptation space between structure and execution is rarely made explicit, and the compatibility between the external harness and the internal reasoner is not optimized jointly. We propose HarnessForge, a meta-adaptive framework for evolving LLM agent systems. HarnessForge formulates an agent system as a harness--policy pair, defining a stable adaptation space that separates harness-level execution structure from policy-level reasoning behavior. It then performs harness--policy co-evolution through fault-guided harness tailoring and harness-conditioned policy alignment. Experiments across five benchmarks from diverse domains show that HarnessForge consistently improves both Qwen3-4B and Qwen3-8B backbones, outperforming harness-only and policy-only baselines with gains of up to 12.0\% over the strongest baseline and achieving favorable rollout-efficiency tradeoffs, demonstrating that harness--policy co-evolution is effective, and that executable compatibility between the harness and reasoning policy is essential for agent-system adaptation. The code is available at https://github.com/mingju-c/HarnessForge.