# Explainable Chain-of-Thought Reasoning: An Empirical Analysis on State-Aware Reasoning Dynamics

arXiv: https://arxiv.org/abs/2509.00190 · HTML: https://mlsanity.com/paper/2509.00190/

## Key facts

- Cited by 16 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 21 of its 25 references that are in the map.
- First posted on arXiv 29 Aug 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, 21 of 21)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge](https://mlsanity.com/paper/1811.00937/) (2018)
- [Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.04388/) (2023)
- [Training Large Language Models to Reason in a Continuous Latent Space](https://mlsanity.com/paper/2412.06769/) (2024)
- [SpinQuant: LLM quantization with learned rotations](https://mlsanity.com/paper/2405.16406/) (2024)
- [Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps](https://mlsanity.com/paper/2407.07071/) (2024)
- [Faithfulness Tests for Natural Language Explanations](https://mlsanity.com/paper/2305.18029/) (2023)
- [Towards a Mechanistic Interpretation of Multi-Step Reasoning Capabilities of Language Models](https://mlsanity.com/paper/2310.14491/) (2023)
- [Does Physical Adversarial Example Really Matter to Autonomous Driving? Towards System-Level Effect of Adversarial Object Evasion Attack](https://mlsanity.com/paper/2308.11894/) (2023)
- [Rethinking External Slow-Thinking: From Snowball Errors to Probability of Correct Reasoning](https://mlsanity.com/paper/2501.15602/) (2025)
- [Unlocking General Long Chain-of-Thought Reasoning Capabilities of Large Language Models via Representation Engineering](https://mlsanity.com/paper/2503.11314/) (2025)
- [Towards Understanding In-Context Learning with Contrastive Demonstrations and Saliency Maps](https://mlsanity.com/paper/2307.05052/) (2023)
- [Analyzing Chain-of-Thought Prompting in Large Language Models via Gradient-based Feature Attributions](https://mlsanity.com/paper/2307.13339/) (2023)
- [Towards Uncovering How Large Language Model Works: An Explainability Perspective](https://mlsanity.com/paper/2402.10688/) (2024)
- [CTRLS: Chain-of-Thought Reasoning via Latent State-Transition](https://mlsanity.com/paper/2507.08182/) (2025)
- [Beyond Words: A Latent Memory Approach to Internal Reasoning in LLMs](https://mlsanity.com/paper/2502.21030/) (2025)
- [CogErgLLM: Exploring Large Language Model Systems Design Perspective Using Cognitive Ergonomics](https://mlsanity.com/paper/2407.02885/) (2024)

## Built on by (most cited first, 16 of 16)

- [WS-GRPO: Weakly-Supervised Group-Relative Policy Optimization for Rollout-Efficient Reasoning](https://mlsanity.com/paper/2602.17025/) (2026)
- [Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning](https://mlsanity.com/paper/2605.02913/) (2026)
- [Streaming Hallucination Detection in Long Chain-of-Thought Reasoning](https://mlsanity.com/paper/2601.02170/) (2026)
- [Unveiling the Entropy Dynamics of Chain-of-Thought Reasoning](https://mlsanity.com/paper/2606.02020/) (2026)
- [Stepwise Penalization for Length-Efficient Chain-of-Thought Reasoning](https://mlsanity.com/paper/2603.00296/) (2026)
- [Saliency-R1: Enforcing Interpretable and Faithful Vision-language Reasoning via Saliency-map Alignment Reward](https://mlsanity.com/paper/2604.04500/) (2026)
- [OLIVIA: Online Learning via Inference-time Action Adaptation for Decision Making in LLM ReAct Agents](https://mlsanity.com/paper/2605.11169/) (2026)
- [ProSR: Process-Shaped Spatial Reasoning for Reliable Chain-of-Thought in VLMs](https://mlsanity.com/paper/2605.25524/) (2026)
- [AutoCRAT: Within-trajectory Joint Control of Stochasticity and Compute for LLM Reasoning](https://mlsanity.com/paper/2608.29988/) (2026)
- [PRISM: A Dual View of LLM Reasoning through Semantic Flow and Latent Computation](https://mlsanity.com/paper/2603.22754/) (2026)
- [Skill-CMIB: Multimodal Agent Skill for Consistent Action via Conditional Multimodal Information Bottleneck](https://mlsanity.com/paper/2605.08526/) (2026)
- [F-GRPO: Factorized Group-Relative Policy Optimization for Unified Candidate Generation and Ranking](https://mlsanity.com/paper/2605.12995/) (2026)
- [Step-Tagging: Toward controlling the generation of Language Reasoning Models through step monitoring](https://mlsanity.com/paper/2512.14332/) (2025)
- [TRACES: Tagging Reasoning Steps for Adaptive Cost-Efficient Early-Stopping](https://mlsanity.com/paper/2604.21057/) (2026)
- [Interpreting Latent CoT Reasoning as Dynamical Systems](https://mlsanity.com/paper/2607.09698/) (2026)
- [CoT-Core: Accelerating LLM Evaluation via CoT-Aware Coreset Selection](https://mlsanity.com/paper/2608.00014/) (2026)

## Abstract (arXiv)

Recent advances in chain-of-thought (CoT) prompting have enabled large language models (LLMs) to perform multi-step reasoning. However, the explainability of such reasoning remains limited, with prior work primarily focusing on local token-level attribution, such that the high-level semantic roles of reasoning steps and their transitions remain underexplored. In this paper, we introduce a state-aware transition framework that abstracts CoT trajectories into structured latent dynamics. Specifically, to capture the evolving semantics of CoT reasoning, each reasoning step is represented via spectral analysis of token-level embeddings and clustered into semantically coherent latent states. To characterize the global structure of reasoning, we model their progression as a Markov chain, yielding a structured and interpretable view of the reasoning process. This abstraction supports a range of analyses, including semantic role identification, temporal pattern visualization, and consistency evaluation.