2606.12882v1 Jun 11, 2026 cs.AI

HarnessBridge: Learnable Bidirectional Controller for LLM Agent Harness

Xiaoxuan Wang
Xiaoxuan Wang
Citations: 305
h-index: 7
Jason Cong
Jason Cong
Citations: 209
h-index: 8
Yizhou Sun
Yizhou Sun
Citations: 259
h-index: 8
Alexander Taylor
Alexander Taylor
Citations: 8
h-index: 1
Haixin Wang
Haixin Wang
Citations: 32
h-index: 2
Wei Wang
Wei Wang
Citations: 15
h-index: 3

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.

0 Citations
0 Influential
4 Altmetric
20.0 Score
Original PDF

No Analysis Report Yet

This paper hasn't been analyzed by Gemini yet.

Log in to request an AI analysis.

댓글

댓글을 작성하려면 로그인하세요.

아직 댓글이 없습니다. 첫 번째 댓글을 남겨보세요!