让大模型代理的交互接口可学习，自动提炼关键状态与动作。
HarnessBridge: Learnable Bidirectional Controller for LLM Agent Harness
- 用双向投影建模交互接口，自动压缩观测和转换动作。
- 在两个基准上表现媲美专用接口，令牌使用量减少30%以上。
- 适合想提升长程任务效率的AI系统开发者。
大型语言模型越来越多地被用作执行长期任务的智能体，但其性能不仅取决于模型能力与环境设计，还受中介智能体-环境交互的‘接口’影响。现有接口多为人工设计，难以随轨迹变长和交互复杂化而扩展。本文提出HarnessBridge，一种轻量级可学习的双向控制器，将智能体-环境接口参数化为双向投影。该模型学习两种双向投影：观测投影将原始轨迹提炼为紧凑的决策相关状态；动作投影将提议动作转化为可执行的转移或基于轨迹的拒绝。通过统一指令微调在接口监督数据集上训练，HarnessBridge在Terminal-Bench 2.0和SWE-bench Verified上表现匹配或超越强基线，同时显著降低令牌使用量和轨迹长度，并能从小型生成器泛化到大型商用模型。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。