# Early Stopping for Large Reasoning Models via Confidence Dynamics

arXiv: https://arxiv.org/abs/2604.04930 · HTML: https://mlsanity.com/paper/2604.04930/

## Key facts

- Cited by 6 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 25 of its 30 references that are in the map.
- First posted on arXiv 6 Apr 2026.

## 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, 25 of 25)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [s1: Simple test-time scaling](https://mlsanity.com/paper/2501.19393/) (2025)
- [Chain of Draft: Thinking Faster by Writing Less](https://mlsanity.com/paper/2502.18600/) (2025)
- [Training Language Models to Reason Efficiently](https://mlsanity.com/paper/2502.04463/) (2025)
- [Dynamic Early Exit in Reasoning Models](https://mlsanity.com/paper/2504.15895/) (2025)
- [Deep Think with Confidence](https://mlsanity.com/paper/2508.15260/) (2025)
- [Reasoning Models Can Be Effective Without Thinking](https://mlsanity.com/paper/2504.09858/) (2025)
- [Reasoning Models Know When They're Right: Probing Hidden States for Self-Verification](https://mlsanity.com/paper/2504.05419/) (2025)
- [Llama-Nemotron: Efficient Reasoning Models](https://mlsanity.com/paper/2505.00949/) (2025)
- [Sketch-of-Thought: Efficient LLM Reasoning with Adaptive Cognitive-Inspired Sketching](https://mlsanity.com/paper/2503.05179/) (2025)
- [Self-Training Elicits Concise Reasoning in Large Language Models](https://mlsanity.com/paper/2502.20122/) (2025)
- [Think Silently, Think Fast: Dynamic Latent Compression of LLM Reasoning Chains](https://mlsanity.com/paper/2505.16552/) (2025)
- [ShorterBetter: Guiding Reasoning Models to Find Optimal Inference Length for Efficient Reasoning](https://mlsanity.com/paper/2504.21370/) (2025)
- [Efficiently Scaling LLM Reasoning with Certaindex](https://mlsanity.com/paper/2412.20993/) (2024)
- [Answer Convergence as a Signal for Early Stopping in Reasoning](https://mlsanity.com/paper/2506.02536/) (2025)
- [Making Slow Thinking Faster: Compressing LLM Chain-of-Thought via Step Entropy](https://mlsanity.com/paper/2508.03346/) (2025)
- [No Answer Needed: Predicting LLM Answer Accuracy from Question-Only Linear Probes](https://mlsanity.com/paper/2509.10625/) (2025)
- [Think or Not? Exploring Thinking Efficiency in Large Reasoning Models via an Information-Theoretic Lens](https://mlsanity.com/paper/2505.18237/) (2025)
- [Entropy After </Think> for reasoning model early exiting](https://mlsanity.com/paper/2509.26522/) (2025)
- [Knowing Before Saying: LLM Representations Encode Information About Chain-of-Thought Success Before Completion](https://mlsanity.com/paper/2505.24362/) (2025)
- [Probing for Arithmetic Errors in Language Models](https://mlsanity.com/paper/2507.12379/) (2025)
- [The Evolution of Thought: Tracking LLM Overthinking via Reasoning Dynamics Analysis](https://mlsanity.com/paper/2508.17627/) (2025)
- [Conformal Thinking: Risk Control for Reasoning on a Compute Budget](https://mlsanity.com/paper/2602.03814/) (2026)

## Built on by (most cited first, 6 of 6)

- [Answer-Distribution Trajectories: A Stochastic-Dynamics View of LLM Reasoning](https://mlsanity.com/paper/2609.09030/) (2026)
- [Stable Answers, Unfinished Reasoning: Why Self-Consensus Is Not a Safe Early-Exit Signal](https://mlsanity.com/paper/2609.09989/) (2026)
- [State of Thought Enables Endogenous Reasoning](https://mlsanity.com/paper/2609.16055/) (2026)
- [Learning to Stop without Learning to Stop: Self-Supervised Confidence Training Improves Reasoning Efficiency](https://mlsanity.com/paper/2609.31619/) (2026)
- [When Reasoning Goes Astray: Attention Dynamics of Uncontrolled Reasoning](https://mlsanity.com/paper/2609.38817/) (2026)
- [The belief-action gap in language model agents](https://mlsanity.com/paper/2610.17444/) (2026)

## Abstract (arXiv)

Large reasoning models rely on long chain-of-thought generation to solve complex problems, but extended reasoning often incurs substantial computational cost and can even degrade performance due to overthinking. A key challenge is determining when the model should stop reasoning and produce the final answer. In this work, we study the confidence of intermediate answers during reasoning and observe two characteristic behaviors: correct reasoning trajectories often reach high-confidence answers early, while incorrect rollouts tend to produce long, unproductive reasoning traces and exhibit less reliable confidence dynamics. Motivated by these observations, we propose CoDE-Stop (Confidence Dynamics Early Stop), an early stopping method that leverages the dynamics of intermediate answer confidence to decide when to terminate reasoning, requiring no additional training and easily integrating into existing models. We evaluate CoDE-Stop on diverse reasoning and science benchmarks across multiple models. Compared to prior early stopping methods, it achieves a more favorable accuracy-compute tradeoff and reduces total token usage by 25-50% compared to standard full-length reasoning. In addition, we provide analyses of confidence dynamics during reasoning, offering insights into how confidence changes in both correct and incorrect trajectories.