Logit–Entropy Adaptive Stopping Heuristic for Efficient Chain-of-Thought Reasoning

Chain-of-thought (CoT) decoding improves reasoning in LLMs, yet fixed-length rationales and vote-heavy schemes waste tokens and inflate latency. We introduce LEASH — Logit–Entropy Adaptive Stopping Heuristic, a training-free, decoding-time algorithm that adaptively halts CoT generation by monitoring two intrinsic signals: (i) the local slope of token-level entropy and (ii) the improvement in top-logit margin. LEASH accepts a rationale when both signals plateau within a short sliding window after a small minimum length, then elicits a concise final answer. Across GSM8K (n=300) and four instruction-tuned models, LEASH retains $\approx 85\%$ of vanilla CoT accuracy ($\approx 15\%$ relative drop) while using $\sim 50\%$ fewer tokens and reducing the end-to-end inference time by $\sim 50\%$. A brief check on AQuA-RAT dataset exhibits the same trend. LEASH is model-agnostic and requires no additional training or supervision, offering a simple and efficient alternative to CoT decoding.