Stable Answers, Unfinished Reasoning: Why Self-Consensus Is Not a Safe Early-Exit Signal

2026-09-09

AI Summary

研究探讨了自共识作为推理模型提前退出信号的不安全性，通过实验验证了其会导致非终止答案被采纳，并提出了一种边界置信度控制方法(DEER)作为更优解决方案。

Abstract

A natural way to cut reasoning-model inference cost is to repeatedly probe a single partial trajectory for its current answer and stop once probes agree -- self-consensus. We ask whether any such rule is both safe and token-saving, and whether one can be selected once and reused. A preregistered sweep of 3,520 consensus rules, replayed on frozen trajectories from two models and three benchmarks, clears none of three acceptance gates fixed in advance; the frontier reproduces on a held-out split and on two unseen models -- while a boundary-confidence control (DEER) swept through the same pipeline clears all three. The reason lies in the signal: agreement establishes that the current answer persists under a fixed probing procedure, not that the reasoning has terminated -- a consensus-termination gap. Stopping on it commits non-terminal answers. At a rule still saving 32% of the tokens, one stop in nine fires on an answer the trajectory itself later abandons, and most of those stops cut off a correction it would otherwise have made. Widening the agreement window does not remove them: the share levels off near 7%, and by then the saving has fallen to 8%. Probe re-wording and a hand-labelled error taxonomy show the agreed answer is often a placeholder the model had not settled on. Used on its own as the stop signal, agreement fails not because it is insufficiently strict, but because it repeatedly measures the wrong object.

Problem

• self-consensus
• reasoning-model inference cost
• consensus-termination gap
• early-exit signal

Innovation

• self-consensus
• early-exit signal
• boundary-confidence control (DEER)
• reasoning termination
• token-saving