ThinkBrake: Efficient Reasoning via Log-Probability Margin Guided Decoding

arXiv:2510.00546v5 Announce Type: replace Abstract: Large Reasoning Models (LRMs) allocate substantial inference-time compute to Chain-of-Thought (CoT) reasoning, improving performance on mathematics, scientific QA, and tool usage. However, this introduces overthinking: LRMs often reach a correct intermediate solution, continue reasoning, and overwrite it with an incorrect answer. We first demonstrate that oracle stopping--where we inject at every sentence boundary and select the best stopping point in hindsight--improves average accuracy by 8% while reducing thinking tokens by 72%, exposing substantial overthinking. Motivated by this finding, we propose ThinkBrake, which monitors the log-probability margin between the top continuation token and at sentence boundaries, stopping reasoning when this margin narrows. ThinkBrake requires no training and achieves favorable accuracy-efficiency trade-offs across math, scientific QA, and tool usage benchmarks, reducing thinking token usage by up to 30%. Furthermore, we provide theoretical analysis showing that ThinkBrake is equivalent to test-time realignment with a reward bonus for the token.

Related

• STU-PID: Steering Token Usage via PID Controller for Efficient Large Language Model Reasoning
• ATTNPO: Attention-Guided Process Supervision for Efficient Reasoning
• Large Reasoning Models Are (Not Yet) Multilingual Latent Reasoners
• Neural Chain-of-Thought Search: Searching the Optimal Reasoning Path to Enhance Large Language Models
• SeLaR: Selective Latent Reasoning in Large Language Models

Source: arXiv cs.CL | 2026-04-21