Measuring Harness-Induced Belief Divergence in Multi-Step LLM Agents
arXiv:2607.04528v3 Announce Type: replace Abstract: Software agents are becoming increasingly important in modern coding workflows, where they solve complex tasks through multi-step interaction with code repositories. A central component of these systems is the execution harness, which governs how the underlying LLM observes, acts on, and verifies its environment. We show that the harness can in turn shape the agent's evolving beliefs about the environment, even when the task, environment, and…