# Efficient Reasoning for Large Reasoning Language Models via Certainty-Guided Reflection Suppression

arXiv: https://arxiv.org/abs/2508.05337 · HTML: https://mlsanity.com/paper/2508.05337/

## 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 2 of its 43 references that are in the map.
- First posted on arXiv 7 Aug 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, 2 of 2)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [A Survey of Slow Thinking-based Reasoning LLMs using Reinforced Learning and Inference-time Scaling Law](https://mlsanity.com/paper/2505.02665/) (2025)

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

- [BrokenMath: A Benchmark for Sycophancy in Theorem Proving with LLMs](https://mlsanity.com/paper/2510.04721/) (2025)
- [The Evolution of Thought: Tracking LLM Overthinking via Reasoning Dynamics Analysis](https://mlsanity.com/paper/2508.17627/) (2025)
- [Stop When Enough: Adaptive Early-Stopping for Chain-of-Thought Reasoning](https://mlsanity.com/paper/2510.10103/) (2025)
- [Neural Chain-of-Thought Search: Searching the Optimal Reasoning Path to Enhance Large Language Models](https://mlsanity.com/paper/2601.11340/) (2026)
- [Accordion-Thinking: Self-Regulated Step Summaries for Efficient and Readable LLM Reasoning](https://mlsanity.com/paper/2602.03249/) (2026)
- [When Is Thinking Enough? Early Exit via Sufficiency Assessment for Efficient Reasoning](https://mlsanity.com/paper/2604.06787/) (2026)
- [Less is More: Improving LLM Reasoning with Minimal Test-Time Intervention](https://mlsanity.com/paper/2510.13940/) (2025)
- [Overthinking Loops in Agents: A Structural Risk via MCP Tools](https://mlsanity.com/paper/2602.14798/) (2026)
- [Explore Briefly, Then Decide: Mitigating LLM Overthinking via Cumulative Entropy Regulation](https://mlsanity.com/paper/2510.02249/) (2025)
- [Unveiling the Entropy Dynamics of Chain-of-Thought Reasoning](https://mlsanity.com/paper/2606.02020/) (2026)
- [Membership Inference Attacks on Tokenizers of Large Language Models](https://mlsanity.com/paper/2510.05699/) (2025)
- [NEAT: Neuron-Based Early Exit for Large Reasoning Models](https://mlsanity.com/paper/2602.02010/) (2026)
- [From GPT-3 to GPT-5: Mapping their capabilities, scope, limitations, and consequences](https://mlsanity.com/paper/2604.10332/) (2026)
- [Efficient Test-Time Scaling via Temporal Reasoning Aggregation](https://mlsanity.com/paper/2604.17304/) (2026)
- [interwhen: A Generalizable Framework for Steering Reasoning Models with Test-time Verification](https://mlsanity.com/paper/2602.11202/) (2026)
- [Resource Consumption Threats in Large Language Models](https://mlsanity.com/paper/2603.16068/) (2026)
- [TRiMS: Real-Time Tracking of Minimal Sufficient Length for Efficient Reasoning via RL](https://mlsanity.com/paper/2603.17449/) (2026)
- [ETR: Entropy Trend Reward for Efficient Chain-of-Thought Reasoning](https://mlsanity.com/paper/2604.05355/) (2026)
- [SAT: Balancing Reasoning Accuracy and Efficiency with Stepwise Adaptive Thinking](https://mlsanity.com/paper/2604.07922/) (2026)
- [Dissecting Failure Dynamics in Large Language Model Reasoning](https://mlsanity.com/paper/2604.14528/) (2026)
- [ChainV: Atomic Visual Hints Make Multimodal Reasoning Shorter and Better](https://mlsanity.com/paper/2511.17106/) (2025)
- [Directional Reasoning Trajectory Change (DRTC): Identifying Critical Trace Segments in Reasoning Models](https://mlsanity.com/paper/2602.15332/) (2026)
- [Risky Business: Measuring The Faithfulness-Safety Tension](https://mlsanity.com/paper/2608.03745/) (2026)
- [MetaCtrl: Your Large Language Models Can Reason Better and More Concisely with a Metacognitive Controller](https://mlsanity.com/paper/2609.37304/) (2026)

## Abstract (arXiv)

Recent Large Reasoning Language Models (LRLMs) employ long chain-of-thought reasoning with complex reflection behaviors, typically signaled by specific trigger words (e.g., "Wait" and "Alternatively") to enhance performance. However, these reflection behaviors can lead to the overthinking problem where the generation of redundant reasoning steps that unnecessarily increase token usage, raise inference costs, and reduce practical utility. In this paper, we propose Certainty-Guided Reflection Suppression (CGRS), a novel method that mitigates overthinking in LRLMs while maintaining reasoning accuracy. CGRS operates by dynamically suppressing the model's generation of reflection triggers when it exhibits high confidence in its current response, thereby preventing redundant reflection cycles without compromising output quality. Our approach is model-agnostic, requires no retraining or architectural modifications, and can be integrated seamlessly with existing autoregressive generation pipelines. Extensive experiments across four reasoning benchmarks (i.e., AIME24, AMC23, MATH500, and GPQA-D) demonstrate CGRS's effectiveness: it reduces token usage by an average of 18.5% to 41.9% while preserving accuracy. It also achieves the optimal balance between length reduction and performance compared to state-of-the-art baselines. These results hold consistently across model architectures (e.g., DeepSeek-R1-Distill series, QwQ-32B, and Qwen3 family) and scales (4B to 32B parameters), highlighting CGRS's practical value for efficient reasoning.