SABER: Stability-Aware Early Exit for LLM Reasoning via Adversarial Branch Probing

2026-08-28

AI Summary

为解决大型推理模型中冗余推理问题，SABER通过构建对抗分支并轻量级探测以实现稳定性感知的提前退出，有效减少了推理消耗同时保持了准确性。

Abstract

Large Reasoning Models (LRMs) achieve strong reasoning capabilities, yet long-chain reasoning becomes inefficient once the intermediate answer stabilizes across reasoning steps: additional reasoning yields little marginal benefit while incurring substantial inference cost. Existing early-exit methods based on confidence or entropy poorly capture reasoning stability, while consistency-based approaches rely on multi-step trajectory agreement, requiring sequential evaluations that delay exit. To better balance efficiency and reliability, we propose SABER, a training-free framework for stability-aware early exit via adversarial branch probing. SABER constructs simple yet effective semantic perturbations around intermediate reasoning states to form adversarial branches, and applies lightweight probing to estimate their likely final outcomes without full trajectory rollouts. When the probed outcomes remain consistent across branches, SABER exits early; otherwise, it continues reasoning. Experiments across multiple reasoning benchmarks and model architectures show that SABER reduces reasoning token consumption by 30.2\%--39.8\% on average while maintaining competitive accuracy with full-length reasoning.

Problem

• Large Reasoning Models
• Reasoning Stability
• Early Exit
• Inference Cost
• Adversarial Branch Probing

Innovation

• Stability-Aware Early Exit
• Adversarial Branch Probing
• Semantic Perturbations