# Answer Convergence as a Signal for Early Stopping in Reasoning

arXiv: https://arxiv.org/abs/2506.02536 · HTML: https://mlsanity.com/paper/2506.02536/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning.
- Builds on 20 of its 29 references that are in the map.
- First posted on arXiv 3 Jun 2025.

## Placed in

- LLM reasoning / [Prompting and chain-of-thought reasoning](https://mlsanity.com/lr/prompting-and-chain-of-thought-reasoning/)

## Builds on (most cited first, 20 of 20)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [Training Large Language Models to Reason in a Continuous Latent Space](https://mlsanity.com/paper/2412.06769/) (2024)
- [Measuring Faithfulness in Chain-of-Thought Reasoning](https://mlsanity.com/paper/2307.13702/) (2023)
- [RouteLLM: Learning to Route LLMs with Preference Data](https://mlsanity.com/paper/2406.18665/) (2024)
- [Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models](https://mlsanity.com/paper/2503.16419/) (2025)
- [Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach](https://mlsanity.com/paper/2502.05171/) (2025)
- [Reasoning Models Don't Always Say What They Think](https://mlsanity.com/paper/2505.05410/) (2025)
- [Chain of Draft: Thinking Faster by Writing Less](https://mlsanity.com/paper/2502.18600/) (2025)
- [O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning](https://mlsanity.com/paper/2501.12570/) (2025)
- [TokenSkip: Controllable Chain-of-Thought Compression in LLMs](https://mlsanity.com/paper/2502.12067/) (2025)
- [Token-Budget-Aware LLM Reasoning](https://mlsanity.com/paper/2412.18547/) (2024)
- [Dynamic Early Exit in Reasoning Models](https://mlsanity.com/paper/2504.15895/) (2025)
- [ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning](https://mlsanity.com/paper/2504.01296/) (2025)
- [DAST: Difficulty-Adaptive Slow-Thinking for Large Reasoning Models](https://mlsanity.com/paper/2503.04472/) (2025)
- [Sketch-of-Thought: Efficient LLM Reasoning with Adaptive Cognitive-Inspired Sketching](https://mlsanity.com/paper/2503.05179/) (2025)
- [Concise Thoughts: Impact of Output Length on LLM Reasoning and Cost](https://mlsanity.com/paper/2407.19825/) (2024)
- [Self-Training Elicits Concise Reasoning in Large Language Models](https://mlsanity.com/paper/2502.20122/) (2025)
- [Think More, Hallucinate Less: Mitigating Hallucinations via Dual Process of Fast and Slow Thinking](https://mlsanity.com/paper/2501.01306/) (2025)

## Built on by (most cited first, 30 of 40)

- [Sample More to Think Less: Group Filtered Policy Optimization for Concise Reasoning](https://mlsanity.com/paper/2508.09726/) (2025)
- [Don't Overthink It: A Survey of Efficient R1-style Large Reasoning Models](https://mlsanity.com/paper/2508.02120/) (2025)
- [Entropy After </Think> for reasoning model early exiting](https://mlsanity.com/paper/2509.26522/) (2025)
- [Think Just Enough: Sequence-Level Entropy as a Confidence Signal for LLM Reasoning](https://mlsanity.com/paper/2510.08146/) (2025)
- [Towards Concise and Adaptive Thinking in Large Reasoning Models: A Survey](https://mlsanity.com/paper/2507.09662/) (2025)
- [Parallel-Probe: Towards Efficient Parallel Thinking via 2D Probing](https://mlsanity.com/paper/2602.03845/) (2026)
- [Self-Compression of Chain-of-Thought via Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2601.21919/) (2026)
- [From Efficiency to Adaptivity: A Deeper Look at Adaptive Reasoning in Large Language Models](https://mlsanity.com/paper/2511.10788/) (2025)
- [Conformal Thinking: Risk Control for Reasoning on a Compute Budget](https://mlsanity.com/paper/2602.03814/) (2026)
- [LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling](https://mlsanity.com/paper/2605.08083/) (2026)
- [Neural Chain-of-Thought Search: Searching the Optimal Reasoning Path to Enhance Large Language Models](https://mlsanity.com/paper/2601.11340/) (2026)
- [Probing the Trajectories of Reasoning Traces in Large Language Models](https://mlsanity.com/paper/2601.23163/) (2026)
- [TERMINATOR: Learning Optimal Exit Points for Early Stopping in Chain-of-Thought Reasoning](https://mlsanity.com/paper/2603.12529/) (2026)
- [Early Stopping for Large Reasoning Models via Confidence Dynamics](https://mlsanity.com/paper/2604.04930/) (2026)
- [When Is Thinking Enough? Early Exit via Sufficiency Assessment for Efficient Reasoning](https://mlsanity.com/paper/2604.06787/) (2026)
- [PEAR: Phase Entropy Aware Reward for Efficient Reasoning](https://mlsanity.com/paper/2510.08026/) (2025)
- [Re-FORC: Adaptive Reward Prediction for Efficient Chain-of-Thought Reasoning](https://mlsanity.com/paper/2511.02130/) (2025)
- [When Reasoning Meets Its Laws](https://mlsanity.com/paper/2512.17901/) (2025)
- [Lil: Less is Less When Applying Post-Training Sparse-Attention Algorithms in Long-Decode Stage](https://mlsanity.com/paper/2601.03043/) (2026)
- [SyncThink: A Training-Free Strategy to Align Inference Termination with Reasoning Saturation](https://mlsanity.com/paper/2601.03649/) (2026)
- [NEAT: Neuron-Based Early Exit for Large Reasoning Models](https://mlsanity.com/paper/2602.02010/) (2026)
- [Efficient Test-Time Scaling via Temporal Reasoning Aggregation](https://mlsanity.com/paper/2604.17304/) (2026)
- [SAT: Balancing Reasoning Accuracy and Efficiency with Stepwise Adaptive Thinking](https://mlsanity.com/paper/2604.07922/) (2026)
- [Towards Generation-Efficient Uncertainty Estimation in Large Language Models](https://mlsanity.com/paper/2605.06053/) (2026)
- [The Shape of Overthinking: Backtracking Bursts in Long Reasoning Traces](https://mlsanity.com/paper/2605.27965/) (2026)
- [Small RL Controller, Large Language Model: RL-Guided Adaptive Sampling for Test-Time Scaling](https://mlsanity.com/paper/2606.03102/) (2026)
- [AutoCRAT: Within-trajectory Joint Control of Stochasticity and Compute for LLM Reasoning](https://mlsanity.com/paper/2608.29988/) (2026)
- [Intra-request branch orchestration for efficient LLM reasoning](https://mlsanity.com/paper/2509.24957/) (2025)
- [Think Less, Know More: State-Aware Reasoning Compression with Knowledge Guidance for Efficient Reasoning](https://mlsanity.com/paper/2604.09150/) (2026)
- [ParaTempo: Efficient Parallel Reasoning via Temporal Confidence](https://mlsanity.com/paper/2608.16425/) (2026)

## Abstract (arXiv)

Chain-of-thought (CoT) prompting enhances reasoning in large language models (LLMs) but often leads to verbose and redundant outputs, thus increasing inference cost. We hypothesize that many reasoning steps are unnecessary for producing correct answers. To investigate this, we start with a systematic study to examine what is the minimum reasoning required for a model to reach a stable decision. We find that on math reasoning tasks like math, models typically converge to their final answers after 60% of the reasoning steps, suggesting substantial redundancy in the remaining content. Based on these insights, we propose three inference-time strategies to improve efficiency: (1) early stopping via answer consistency, (2) boosting the probability of generating end-of-reasoning signals, and (3) a supervised method that learns when to stop based on internal activations. Experiments across five benchmarks and five open-weights LLMs show that our methods significantly reduce token usage with little or no accuracy drop. In particular, on NaturalQuestions, Answer Consistency reduces tokens by over 40% while further improving accuracy. Our work underscores the importance of cost-effective reasoning methods that operate at inference time, offering practical benefits for real-world applications.