# CoT-Kinetics: A Theoretical Modeling Assessing LRM Reasoning Process

arXiv: https://arxiv.org/abs/2505.13408 · HTML: https://mlsanity.com/paper/2505.13408/

## Key facts

- Cited by 51 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 10 of its 91 references that are in the map.
- First posted on arXiv 19 May 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, 10 of 10)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advances](https://mlsanity.com/paper/2410.18775/) (2024)
- [ChartCoder: Advancing Multimodal Large Language Model for Chart-to-Code Generation](https://mlsanity.com/paper/2501.06598/) (2025)
- [A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluations](https://mlsanity.com/paper/2502.14881/) (2025)
- [LLaVA Steering: Visual Instruction Tuning with 500x Fewer Parameters through Modality Linear Representation-Steering](https://mlsanity.com/paper/2412.12359/) (2024)
- [Keeping Yourself is Important in Downstream Tuning Multimodal Large Language Model](https://mlsanity.com/paper/2503.04543/) (2025)
- [PERFT: Parameter-Efficient Routed Fine-Tuning for Mixture-of-Expert Model](https://mlsanity.com/paper/2411.08212/) (2024)
- [Chain-of-Probe: Examining the Necessity and Accuracy of CoT Step-by-Step](https://mlsanity.com/paper/2406.16144/) (2024)
- [ThoughtProbe: Classifier-Guided Thought Space Exploration Leveraging LLM Intrinsic Reasoning](https://mlsanity.com/paper/2504.06650/) (2025)

## Built on by (most cited first, 30 of 51)

- [ReTrack: Evidence-Driven Dual-Stream Directional Anchor Calibration Network for Composed Video Retrieval](https://mlsanity.com/paper/2604.17898/) (2026)
- [OFFSET: Segmentation-based Focus Shift Revision for Composed Image Retrieval](https://mlsanity.com/paper/2507.05631/) (2025)
- [ASCD: Attention-Steerable Contrastive Decoding for Reducing Hallucination in MLLM](https://mlsanity.com/paper/2506.14766/) (2025)
- [HUD: Hierarchical Uncertainty-Aware Disambiguation Network for Composed Video Retrieval](https://mlsanity.com/paper/2512.02792/) (2025)
- [INTENT: Invariance and Discrimination-aware Noise Mitigation for Robust Composed Image Retrieval](https://mlsanity.com/paper/2604.18051/) (2026)
- [HABIT: Chrono-Synergia Robust Progressive Learning Framework for Composed Image Retrieval](https://mlsanity.com/paper/2604.18037/) (2026)
- [MetaSkill-Evolve: Recursive Self-Improvement of LLM Agents via Two-Timescale Meta-Skill Evolution](https://mlsanity.com/paper/2607.05297/) (2026)
- [Verifying Chain-of-Thought Reasoning via Its Computational Graph](https://mlsanity.com/paper/2510.09312/) (2025)
- [Air-Know: Arbiter-Calibrated Knowledge-Internalizing Robust Network for Composed Image Retrieval](https://mlsanity.com/paper/2604.19386/) (2026)
- [ConeSep: Cone-based Robust Noise-Unlearning Compositional Network for Composed Image Retrieval](https://mlsanity.com/paper/2604.20358/) (2026)
- [TEMA: Anchor the Image, Follow the Text for Multi-Modification Composed Image Retrieval](https://mlsanity.com/paper/2604.21806/) (2026)
- [Graph is a Substrate Across Data Modalities](https://mlsanity.com/paper/2601.22384/) (2026)
- [Can Visual Input Be Compressed? A Visual Token Compression Benchmark for Large Multimodal Models](https://mlsanity.com/paper/2511.02650/) (2025)
- [UORA: Uniform Orthogonal Reinitialization Adaptation in Parameter-Efficient Fine-Tuning of Large Models](https://mlsanity.com/paper/2505.20154/) (2025)
- [ARIA: Training Language Agents with Intention-Driven Reward Aggregation](https://mlsanity.com/paper/2506.00539/) (2025)
- [What if Agents Could Imagine? Reinforcing Open-Vocabulary HOI Comprehension through Generation](https://mlsanity.com/paper/2602.11499/) (2026)
- [OPD-V: Visual On-Policy Self-Distillation with Modality Balance](https://mlsanity.com/paper/2608.05131/) (2026)
- [Pretraining on the Test Set Is No Longer All You Need: A Debate-Driven Approach to QA Benchmarks](https://mlsanity.com/paper/2507.17747/) (2025)
- [MINED: Probing and Updating with Multimodal Time-Sensitive Knowledge for Large Multimodal Models](https://mlsanity.com/paper/2510.19457/) (2025)
- [TraPO: A Semi-Supervised Reinforcement Learning Framework for Boosting LLM Reasoning](https://mlsanity.com/paper/2512.13106/) (2025)
- [ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning](https://mlsanity.com/paper/2608.03972/) (2026)
- [PreP-OCR: A Complete Pipeline for Document Image Restoration and Enhanced OCR Accuracy](https://mlsanity.com/paper/2505.20429/) (2025)
- [Beyond Scalars: Evaluating and Understanding LLM Reasoning via Geometric Progress and Stability](https://mlsanity.com/paper/2603.10384/) (2026)
- [MV-Debate: Multi-view Agent Debate with Dynamic Reflection Gating for Multimodal Harmful Content Detection in Social Media](https://mlsanity.com/paper/2508.05557/) (2025)
- [Set-Valued Prediction for Large Language Models with Feasibility-Aware Coverage Guarantees](https://mlsanity.com/paper/2603.22966/) (2026)
- [CoT2-Meta: Budgeted Metacognitive Control for Test-Time Reasoning](https://mlsanity.com/paper/2603.28135/) (2026)
- [EchoRL: Reinforcement Learning via Rollout Echoing](https://mlsanity.com/paper/2605.31228/) (2026)
- [AStF: Motion Style Transfer via Adaptive Statistics Fusor](https://mlsanity.com/paper/2511.04192/) (2025)
- [Diffusion-Based Image Editing: An Unforeseen Adversary to Robust Invisible Watermarks](https://mlsanity.com/paper/2511.05598/) (2025)
- [SatireDecoder: Visual Cascaded Decoupling for Enhancing Satirical Image Comprehension](https://mlsanity.com/paper/2512.00582/) (2025)

## Abstract (arXiv)

Recent Large Reasoning Models significantly improve the reasoning ability of Large Language Models by learning to reason, exhibiting the promising performance in solving complex tasks. LRMs solve tasks that require complex reasoning by explicitly generating reasoning trajectories together with answers. Nevertheless, judging the quality of such an output answer is not easy because only considering the correctness of the answer is not enough and the soundness of the reasoning trajectory part matters as well. Logically, if the soundness of the reasoning part is poor, even if the answer is correct, the confidence of the derived answer should be low. Existing methods did consider jointly assessing the overall output answer by taking into account the reasoning part, however, their capability is still not satisfactory as the causal relationship of the reasoning to the concluded answer cannot properly reflected. In this paper, inspired by classical mechanics, we present a novel approach towards establishing a CoT-Kinetics energy equation. Specifically, our CoT-Kinetics energy equation formulates the token state transformation process, which is regulated by LRM internal transformer layers, as like a particle kinetics dynamics governed in a mechanical field. Our CoT-Kinetics energy assigns a scalar score to evaluate specifically the soundness of the reasoning phase, telling how confident the derived answer could be given the evaluated reasoning. As such, the LRM's overall output quality can be accurately measured, rather than a coarse judgment (e.g., correct or incorrect) anymore.