Abstract
Software-agent benchmarks usually report whether an agent solves a task, but the agent reaches that outcome through a harness that controls what it sees, which actions it can take, which failures are repaired, which states are verified, and which evidence is logged. We show that this harness can change the agent's multi-step beliefs even when the task, environment, and base LLM are fixed.
We introduce a belief-rollout diagnostic that elicits structured K-step trajectories over progress, risk, recoverability, constraints, failure mode, uncertainty, future success, repair cost, and next action under alternative harnesses.
We define a cross-harness belief divergence and decompose it into an arrival term for immediate interface shifts and a growth term for horizon-dependent belief changes. On controlled coding tasks and public-benchmark stress tests, blocked actions, compressed repairs, selective verification, and cost-aware evidence pruning often preserve terminal success while changing the beliefs that drive later decisions.
We further introduce BIWM, a no-training protocol that canonicalizes observations, logs censored branches, expands repair traces, records verification masks, executes risky branches in shadow, and aligns belief trajectories across harness views. The results suggest that harness design is an experimental variable in agent evaluation, not an implementation detail.
Blogger's Review: This study emphasizes the importance of harness design in evaluating LLM agents, revealing how belief divergence can influence decision-making processes. It provides a fresh perspective for future agent designs, encouraging researchers to focus on optimizing harnesses to enhance agent performance.