# Prolonged Reasoning Is Not All You Need: Certainty-Based Adaptive Routing for Efficient LLM/MLLM Reasoning

arXiv: https://arxiv.org/abs/2505.15154 · HTML: https://mlsanity.com/paper/2505.15154/

## Key facts

- Cited by 35 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 30 of its 69 references that are in the map.
- First posted on arXiv 21 May 2025.

## Placed in

- LLM reasoning / [Test-time compute and efficient thinking](https://mlsanity.com/lr/test-time-compute-and-efficient-thinking/)
- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 30 of 30)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [Training Large Language Models to Reason in a Continuous Latent Space](https://mlsanity.com/paper/2412.06769/) (2024)
- [DeepSeek-VL: Towards Real-World Vision-Language Understanding](https://mlsanity.com/paper/2403.05525/) (2024)
- [VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model](https://mlsanity.com/paper/2504.07615/) (2025)
- [Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models](https://mlsanity.com/paper/2503.16419/) (2025)
- [Chain of Draft: Thinking Faster by Writing Less](https://mlsanity.com/paper/2502.18600/) (2025)
- [Token-Budget-Aware LLM Reasoning](https://mlsanity.com/paper/2412.18547/) (2024)
- [CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation](https://mlsanity.com/paper/2502.21074/) (2025)
- [Reasoning Models Can Be Effective Without Thinking](https://mlsanity.com/paper/2504.09858/) (2025)
- [Seed1.5-Thinking: Advancing Superb Reasoning Models with Reinforcement Learning](https://mlsanity.com/paper/2504.13914/) (2025)
- [Concise Thoughts: Impact of Output Length on LLM Reasoning and Cost](https://mlsanity.com/paper/2407.19825/) (2024)
- [DocPedia: Unleashing the Power of Large Multimodal Model in the Frequency Domain for Versatile Document Understanding](https://mlsanity.com/paper/2311.11810/) (2023)
- [How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach](https://mlsanity.com/paper/2503.01141/) (2025)
- [Efficient Reasoning Models: A Survey](https://mlsanity.com/paper/2504.10903/) (2025)
- [UniDoc: A Universal Large Multimodal Model for Simultaneous Text Detection, Recognition, Spotting and Understanding](https://mlsanity.com/paper/2308.11592/) (2023)
- [A Bounding Box is Worth One Token: Interleaving Layout and Text in a Large Language Model for Document Understanding](https://mlsanity.com/paper/2407.01976/) (2024)
- [Reasoning to Learn from Latent Thoughts](https://mlsanity.com/paper/2503.18866/) (2025)
- [Vision as LoRA](https://mlsanity.com/paper/2503.20680/) (2025)
- [Advancing Sequential Numerical Prediction in Autoregressive Models](https://mlsanity.com/paper/2505.13077/) (2025)
- [Boosting of Thoughts: Trial-and-Error Problem Solving with Large Language Models](https://mlsanity.com/paper/2402.11140/) (2024)
- [EVE: Towards End-to-End Video Subtitle Extraction with Vision-Language Models](https://mlsanity.com/paper/2503.04058/) (2025)

## Built on by (most cited first, 30 of 35)

- [Don't Overthink It: A Survey of Efficient R1-style Large Reasoning Models](https://mlsanity.com/paper/2508.02120/) (2025)
- [Towards Concise and Adaptive Thinking in Large Reasoning Models: A Survey](https://mlsanity.com/paper/2507.09662/) (2025)
- [MEML-GRPO: Heterogeneous Multi-Expert Mutual Learning for RLVR Advancement](https://mlsanity.com/paper/2508.09670/) (2025)
- [Aware First, Think Less: Dynamic Boundary Self-Awareness Drives Extreme Reasoning Efficiency in Large Language Models](https://mlsanity.com/paper/2508.11582/) (2025)
- [SABER: Switchable and Balanced Training for Efficient LLM Reasoning](https://mlsanity.com/paper/2508.10026/) (2025)
- [Efficient Inference for Large Vision-Language Models: Bottlenecks, Techniques, and Prospects](https://mlsanity.com/paper/2604.05546/) (2026)
- [Neural Chain-of-Thought Search: Searching the Optimal Reasoning Path to Enhance Large Language Models](https://mlsanity.com/paper/2601.11340/) (2026)
- [iReasoner: Trajectory-Aware Intrinsic Reasoning Supervision for Self-Evolving Large Multimodal Models](https://mlsanity.com/paper/2601.05877/) (2026)
- [Think-as-You-See: Streaming Chain-of-Thought Reasoning for Large Vision-Language Models](https://mlsanity.com/paper/2603.02872/) (2026)
- [Verifying Meta-Awareness via Predictive Rewards in Reasoning Models](https://mlsanity.com/paper/2510.03259/) (2025)
- [Learning to Reason Efficiently with Discounted Reinforcement Learning](https://mlsanity.com/paper/2510.23486/) (2025)
- [Can Confidence Estimates Decide When Chain-of-Thought Is Necessary for LLMs?](https://mlsanity.com/paper/2510.21007/) (2025)
- [Don't Blink: Evidence Collapse during Multimodal Reasoning](https://mlsanity.com/paper/2604.04207/) (2026)
- [From Perception to Reasoning: Deep Thinking Empowers Multimodal Large Language Models](https://mlsanity.com/paper/2511.12861/) (2025)
- [LPCAN: Lightweight Pyramid Cross-Attention Network for Rail Surface Defect Detection Using RGB-D Data](https://mlsanity.com/paper/2601.09118/) (2026)
- [Knowledge-Embedded and Hypernetwork-Guided Few-Shot Substation Meter Defect Image Generation Method](https://mlsanity.com/paper/2601.09238/) (2026)
- [MA-LipNet: Multi-Dimensional Attention Networks for Robust Lipreading](https://mlsanity.com/paper/2601.20881/) (2026)
- [HyPER: Bridging Exploration and Exploitation for Scalable LLM Reasoning with Hypothesis Path Expansion and Reduction](https://mlsanity.com/paper/2602.06527/) (2026)
- [Bridging Efficiency and Transparency: Explainable CoT Compression in Multimodal Large Reasoning Models](https://mlsanity.com/paper/2602.09485/) (2026)
- [The Diffusion Duet: Harmonizing Dual Channels with Wavelet Suppression for Image Separation](https://mlsanity.com/paper/2602.13361/) (2026)
- [Detecting Deepfakes with Multivariate Soft Blending and CLIP-based Image-Text Alignment](https://mlsanity.com/paper/2602.15903/) (2026)
- [Efficient Image Super-Resolution with Multi-Scale Spatial Adaptive Attention Networks](https://mlsanity.com/paper/2603.00118/) (2026)
- [A Deformable Attention-Based Detection Transformer with Cross-Scale Feature Fusion for Industrial Coil Spring Inspection](https://mlsanity.com/paper/2603.13429/) (2026)
- [Transmittance-Guided Structure-Texture Decomposition for Nighttime Image Dehazing](https://mlsanity.com/paper/2603.29507/) (2026)
- [Hierarchical Awareness Adapters with Hybrid Pyramid Feature Fusion for Dense Depth Prediction](https://mlsanity.com/paper/2604.03339/) (2026)
- [Breaking the Reward Barrier: Accelerating Tree-of-Thought Reasoning via Speculative Exploration](https://mlsanity.com/paper/2605.10195/) (2026)
- [Local Spatiotemporal Convolutional Network for Robust Gait Recognition](https://mlsanity.com/paper/2605.14548/) (2026)
- [Do You Need Text Rectification? Soft Attention Mask Embedding for Rectification-Free Scene Text Spotting](https://mlsanity.com/paper/2605.18173/) (2026)
- [DAIN: Dynamic Agent-Based Interaction Network for Efficient and Collaborative Multimodal Reasoning](https://mlsanity.com/paper/2606.30189/) (2026)
- [ProWAFT: A ROMA-LPD Instance for Workload-Aware and Dynamic Fault Tolerance in FPGA-Based CNN Accelerators](https://mlsanity.com/paper/2607.01602/) (2026)

## Abstract (arXiv)

Recent advancements in reasoning have significantly enhanced the capabilities of Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) across diverse tasks. However, excessive reliance on chain-of-thought (CoT) reasoning can impair model performance and brings unnecessarily lengthened outputs, reducing efficiency. Our work reveals that prolonged reasoning does not universally improve accuracy and even degrade performance on simpler tasks. To address this, we propose Certainty-based Adaptive Reasoning (CAR), a novel framework that dynamically switches between short answers and long-form reasoning based on the model perplexity. CAR first generates a short answer and evaluates its perplexity, triggering reasoning only when the model exhibits low confidence (i.e., high perplexity). Experiments across diverse multimodal VQA/KIE benchmarks and text reasoning datasets show that CAR outperforms both short-answer and long-form reasoning approaches, striking an optimal balance between accuracy and efficiency.