# HarnessBridge：面向LLM智能体调控的可学习双向控制器

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-06-11 08:00
- AIHOT 分数：62
- AIHOT 链接：https://aihot.virxact.com/items/cmqaa49oc0jjyslldwsyt0wqj
- 原文链接：https://arxiv.org/abs/2606.12882

## AI 摘要

HarnessBridge是一个轻量级可学习调控控制器，将智能体-环境接口参数化为双向投影：观测投影将原始轨迹蒸馏为紧凑、决策相关状态，动作投影将提议动作转换为可执行转换或轨迹接地拒绝。在harness监督数据集上通过统一指令微调训练，HarnessBridge在Terminal-Bench 2.0和SWE-bench Verified上匹配或超越强专用调控方案，同时大幅减少token使用和轨迹长度，并从小型生成器泛化到更大商业模型。

## 正文

Large language models are increasingly deployed as agents for long-horizon tasks, yet their performance is shaped not only by model capability and environment design, but also by the harness that mediates agent--environment interaction. Existing harnesses are largely manually engineered, making them difficult to scale as trajectories grow longer and interactions become more complex. In this work, we ask whether harness can be generated by a learnable plug-in module that can be trained in an end-to-end fashion. We introduce HarnessBridge, a lightweight learnable harness controller that parameterizes the agent--environment interface as a bidirectional projection. HarnessBridge learns two bidirectional projections: observation projection, which distills raw trajectories into compact, decision-relevant states, and action projection, which converts proposed actions into executable transitions or trajectory-grounded rejections. We train HarnessBridge on a harness supervision dataset via unified instruction tuning. On Terminal-Bench~2.0 and SWE-bench Verified, HarnessBridge matches or surpasses strong specialized harnesses while substantially reducing token usage and trajectory length, and generalizes from smaller generators to larger commercial models.