cs.LGMay 15, 2026

Harnesses for Inference-Time Alignment over Execution Trajectories

Authors: Boyuan WangBochao LiMinghan WangYuxin TaoFang Kong

Abstract

Harness engineering has emerged as an important inference-time technique for large language model (LLM) agents, aiming to improve long-term performance through task decomposition and guided execution. However, more elaborate harnesses are not uniformly better: increasing decomposition or guidance can sometimes improve execution, but can also reduce final task success. We study harness design through the lens of inference-time trajectory alignment. This perspective separates harness into two mechanisms: task decomposition, which structures a task into sub-goals, and guided execution, which reshapes local action distributions during execution. This decomposition allows us to quantify how workflow granularity, retry budgets, and guidance-induced action reweighting shape the performance limits of harness design. It further reveals concrete failure modes, including over-decomposition, over-pruning, and hallucinated execution. We validate these predictions through controlled synthetic experiments and real terminal agent benchmarks. Inspired by the theory, we further show that effective harnesses can be partial: specifying only the initial steps and leaving the remaining execution to agent can achieve higher pass rate than fully structured workflows.

Explore similar work

CardsList
  1. HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?

    Sep 1, 2026Yuhao Wu, Jingyuan Zhang, Jiajun Shi +16Agent Harness

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

    Sep 21, 2026Haoran Ye, Yuxing Lu, Haonan Dong +2Agent Harness