An auditable framework is built that maintains an external belief state over hidden roles, logs belief updates and belief-action deviations as structured evidence, and supports a defensive offline improvement loop that reviews bad cases before any strategy change.
Abstract
Evaluating LLM agents in hidden-information multi-agent settings is hard: final outcomes are high-variance and rarely reveal why an agent decided as it did. We study this in a 9-player Werewolf environment where agents act under strict, code-level information isolation, and we build an auditable framework that maintains an external belief state over hidden roles, logs belief updates and belief-action deviations as structured evidence, and supports a defensive offline improvement loop that reviews bad cases before any strategy change. Across 1,080 frozen games spanning belief-disabled, active-belief, kernel-ablation, camp-restricted, consumption-policy, and high-load arms, and including a seed-paired A0/A1 comparison, the active-belief condition is associated with substantially better good-side outcomes: in the 200-seed A0/A1 comparison the good-side win rate rises from 0.205 to 0.390 (paired McNemar $\chi^2 = 16.4$, $p<0.001$), with fewer irreversible witch-poison errors. We do not, however, attribute this shift to belief content. Direct action-belief consistency is low ($\approx 0.21$), and giving belief only to the werewolves helps the good side more than giving it only to the good side, which argues against a simple holder-benefit account; we therefore report the effect as an association and treat its mechanism as unresolved. The contribution is the audit framework itself: it makes the effect measurable, exposes low direct action-belief consistency, rejects an unreliable forced-consumption intervention with evidence, and separates strategy effects from load confounds. We accordingly position external belief in high-noise hidden-information games primarily as an auditable cognitive baseline that also carries decision-relevant signal, turning opaque agent behavior into replayable evidence for safer, controlled iteration.
This work tests a hidden-information chess variant where royal status can be secretly, repeatedly relocated between pieces, and where an agent's stated probability distribution over the opponent's hidden royal piece -- elicited every turn, separately from the move it chooses -- is scored against ground truth recoverable after the game.
Current LLM agent systems decide delegation before reasoning begins (a router picks a model) or after a response is complete (a verifier scores it and may retry). We study a third regime: an agent that recognises, during its own reasoning, that it is unlikely to succeed and transfers control to a stronger model. We formulate intra-generation delegation as a Bayesian optimal-stopping problem over a learned competence posterior -- an online estimate of the agent's eventual task success whose sufficient statistics are learned from labelled trajectories, not read off raw entropy. We derive the myopic escalation threshold in closed form, characterise the optimal policy via dynamic programming, and prove that the optimal policy is a time-varying threshold with no shape assumption on the raw signal. We further prove exponential separation of the oracle belief at the Chernoff-information rate of the signal, a regret bound governed by the calibration of the posterior, and a finite-sample guarantee: with n labelled calibration trajectories the deployed plug-in policy's regret decays as 1/sqrt(n). A controlled simulation study confirms each prediction of the theory, including the predicted 1/sqrt(n) rate. We additionally report a real-model validation on a Qwen2.5-Coder 1.5B->7B code cascade (MBPP, 257 tasks), confirming two of three pre-registered predictions: the escalation frontier dominates post-hoc routing at equal cost, and the cumulative competence belief's discrimination rises over generation.
MafiaScope, an open testbed that turns the social deduction game Mafia into a measurement instrument for machine Theory of Mind, is presented, finding that stated confidence is poorly calibrated, agents overestimate how often they are suspected by a factor of 1.5, and single-vote counterfactual replays rarely change game outcomes.
A belief-rollout diagnostic is introduced that elicits structured K-step trajectories over progress, risk, recoverability, constraints, failure mode, uncertainty, future success, repair cost, and next action under alternative harnesses and suggests that harness design is an experimental variable in agent evaluation, not an implementation detail.
As large language models are deployed as autonomous agents that communicate intentions before acting, a critical safety question is whether agents that publicly commit to actions will honor those commitments. We place LLM agents in repeated $n$-player games with a three-stage protocol that separates private intent, public announcement, and final action, allowing us to identify whether each deviation from a stated announcement was already planned during private deliberation. Evaluating three frontier models across six games in homogeneous and heterogeneous groups over 10 rounds, we report two findings. First, when agents deviate from their announcements, the deviation is predominantly already stated in their private plan (exceeding 90% in the highest-deception conditions), yet this is not a fixed model property: the same model ranges from perfect honesty to near-total deviation across games. Second, different models interpret announcements incompatibly, some as binding commitments and others as cheap talk, producing payoff gaps that emerge in Round~0 and persist across all 10 rounds. Systems that combine models from different providers therefore cannot assume shared announcement semantics and require empirical testing of model interactions before deployment.
Jerick Shi, Terry Jingchen Zhang, Bernhard Scholkopf et al.· 0 citations
Agent Step Value (ASV), a replay framework that scores before/after states with a state-less LLM evaluator over a fixed candidate set, turns prompt sensitivity into a measured channel effect and localizes the largest rationale-conditioned losses to extraction and audit.