# Think Just Enough: Sequence-Level Entropy as a Confidence Signal for LLM Reasoning

arXiv: https://arxiv.org/abs/2510.08146 · HTML: https://mlsanity.com/paper/2510.08146/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning.
- Builds on 9 of its 11 references that are in the map.
- First posted on arXiv 9 Oct 2025.

## Placed in

- LLM reasoning / [Test-time compute and efficient thinking](https://mlsanity.com/lr/test-time-compute-and-efficient-thinking/)

## Builds on (most cited first, 9 of 9)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation](https://mlsanity.com/paper/2302.09664/) (2023)
- [DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference](https://mlsanity.com/paper/2004.12993/) (2020)
- [Confident Adaptive Language Modeling](https://mlsanity.com/paper/2207.07061/) (2022)
- [Branch-Solve-Merge Improves Large Language Model Evaluation and Generation](https://mlsanity.com/paper/2310.15123/) (2023)
- [Answer Convergence as a Signal for Early Stopping in Reasoning](https://mlsanity.com/paper/2506.02536/) (2025)
- [Uncertainty-Guided Chain-of-Thought for Code Generation with LLMs](https://mlsanity.com/paper/2503.15341/) (2025)

## Built on by (most cited first, 24 of 24)

- [Parallel-Probe: Towards Efficient Parallel Thinking via 2D Probing](https://mlsanity.com/paper/2602.03845/) (2026)
- [From Efficiency to Adaptivity: A Deeper Look at Adaptive Reasoning in Large Language Models](https://mlsanity.com/paper/2511.10788/) (2025)
- [LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling](https://mlsanity.com/paper/2605.08083/) (2026)
- [Same Signal, Opposite Meaning: Direction-Informed Adaptive Learning for LLM Agents](https://mlsanity.com/paper/2605.06908/) (2026)
- [From Conflict to Consensus: Boosting Medical Reasoning via Multi-Round Agentic RAG](https://mlsanity.com/paper/2603.03292/) (2026)
- [Rethinking the Role of Entropy in Optimizing Tool-Use Behaviors for Large Language Model Agents](https://mlsanity.com/paper/2602.02050/) (2026)
- [The Stepwise Informativeness Assumption: Why are Entropy Dynamics and Reasoning Correlated in LLMs?](https://mlsanity.com/paper/2604.06192/) (2026)
- [When Should an AI Workflow Release? Always-Valid Inference for Black-Box Generate-Verify Systems](https://mlsanity.com/paper/2605.12947/) (2026)
- [interwhen: A Generalizable Framework for Steering Reasoning Models with Test-time Verification](https://mlsanity.com/paper/2602.11202/) (2026)
- [Don't Blink: Evidence Collapse during Multimodal Reasoning](https://mlsanity.com/paper/2604.04207/) (2026)
- [Towards Generation-Efficient Uncertainty Estimation in Large Language Models](https://mlsanity.com/paper/2605.06053/) (2026)
- [When Do LLMs Reason? A Dynamical Systems View via Entropy Phase Transitions](https://mlsanity.com/paper/2605.22873/) (2026)
- [The Shape of Overthinking: Backtracking Bursts in Long Reasoning Traces](https://mlsanity.com/paper/2605.27965/) (2026)
- [AutoCRAT: Within-trajectory Joint Control of Stochasticity and Compute for LLM Reasoning](https://mlsanity.com/paper/2608.29988/) (2026)
- [How Confident Is the First Token? An Uncertainty-Calibrated Prompt Optimization Framework for Large Language Model Classification and Understanding](https://mlsanity.com/paper/2603.18009/) (2026)
- [Dual-Dimensional Consistency: Balancing Budget and Quality in Adaptive Inference-Time Scaling](https://mlsanity.com/paper/2605.15100/) (2026)
- [Answer-Distribution Trajectories: A Stochastic-Dynamics View of LLM Reasoning](https://mlsanity.com/paper/2609.09030/) (2026)
- [A Single Revision Step Improves Token-Efficient LLM Reasoning](https://mlsanity.com/paper/2602.02828/) (2026)
- [Cut Your Losses! Learning to Prune Paths Early for Efficient Parallel Reasoning](https://mlsanity.com/paper/2604.16029/) (2026)
- [Entropy Centroids as Intrinsic Rewards for Test-Time Scaling](https://mlsanity.com/paper/2604.26173/) (2026)
- [Latent Performance Profiling of Large Language Models](https://mlsanity.com/paper/2605.30018/) (2026)
- [Confidently Deceptive: On the Relationship Between Confidence and Deception in LLMs](https://mlsanity.com/paper/2607.20444/) (2026)
- [Do small language models know what they don't know?](https://mlsanity.com/paper/2609.20824/) (2026)
- [Certainty Is Not Just Correctness: Rethinking Token-Level Certainty in LLM Reasoning](https://mlsanity.com/paper/2610.00296/) (2026)

## Abstract (arXiv)

We introduce a simple, yet novel entropy-based framework to drive token efficiency in large language models during reasoning tasks. Our approach uses Shannon entropy from token-level logprobs as a confidence signal to enable early stopping, achieving 25-50% computational savings while maintaining task accuracy. Crucially, we demonstrate that entropy-based confidence calibration represents an emergent property of advanced post-training optimization present in modern reasoning models but notably absent in standard instruction-tuned and pre-trained models (Llama 3.3 70B). We show that the entropy threshold to stop reasoning varies from model to model but can be calculated easily in one shot using only a few examples from existing reasoning datasets. Our results indicate that advanced reasoning models often know that they've gotten a correct answer early on, and that this emergent confidence awareness can be exploited to save tokens and reduce latency. The framework demonstrates consistent performance across reasoning-optimized model families with 25-50% computational cost reduction while preserving accuracy, revealing that confidence mechanisms represent a distinguishing characteristic of modern post-trained reasoning systems versus their predecessors.