Chain-of-Thought Reasoning

Follow this topic Ask about this topic

Recent momentum

-35%

13 papers in the last 28 days · 0.2% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this topic, kept on the site without email delivery.

Period ending 2026-09-21

3 new papers

A weekly snapshot of new work published in Chain-of-Thought Reasoning.

Period ending 2026-09-14

7 new papers

A weekly snapshot of new work published in Chain-of-Thought Reasoning.

Period ending 2026-09-07

6 new papers

A weekly snapshot of new work published in Chain-of-Thought Reasoning.

231 papers

Latest in Chain-of-Thought Reasoning

Browse all topics →

Do Models Know Why They Changed Their Mind? Interpretability and Faithfulness of Chain-of-Thought Under Knowledge Conflict
May 26, 2026Pruthvinath Jeripity VenkataChain-of-Thought Reasoning Model Interpretability
Can Segmentation Models Understand the World? Towards Proactive Affordance Reasoning via Visual Chain-of-Thought
May 26, 2026Yuchen Guo, Junli Gong, Hongmin Cai +2Affordances Segmentation Model
GeoFaith: A Spatio-Temporal Dual View of Faithful Chain-of-Thought
May 26, 2026Weijiang Lv, Wentong Zhao, Jiayu Wang +3Explanation Faithfulness Chain-of-Thought Reasoning
What Makes Chain-of-Thought Work at Probe Time? Local Co-occurrence Rather Than Global Derivation
May 26, 2026Xiang Wang, Wei WeiChain-of-Thought Reasoning Co-Occurrence
Beyond a Single Direction: Chain-of-Thought Disrupts Simple Steering of Refusal
May 26, 2026Kia-Jüng Yang, Dominik Meier, Jiachen Zhao +2Refusals Large Reasoning Models
Rethinking the Multilingual Reasoning Gap with Layer Swap
May 26, 2026Maxence Lasbordes, Amélie Chatelain, Djamé SeddahMultilingual Reasoning Large Language Model Reasoning
Reasoning, Code, or Both? How Large Language Models Handle Variations in Math Questions
May 26, 2026Matthew KutakhLarge Language Model Reasoning Math Problems
When Do LLM Agents Treat Surface Noise Differently from Semantic Noise? A 68-Cell Measurement Study with a Held-Out Trace-Level Validation
May 25, 2026Liyun Zhang, Jiayi GuoLarge Language Model Agents Perturbations
Step-TP: A Grounded, Step-Level Dataset with Chain-of-Thought Reasoning for LLM-Guided Tensor Program Optimization
May 25, 2026Mengfan Liu, Da Zheng, Junwei Su +1Tensor Programs Code Optimization
MuCRASP: Multimodal Chain-of-thought Reasoning aware Structured Pruning
May 25, 2026Aritra Dutta, Somak AdityaMulti-Modal Large Language Models Visual Token Pruning
Investigating the Interplay between Contextual and Parametric Chain-of-Thought Faithfulness under Optimization
May 24, 2026Jingyi Sun, Qianli Wang, Pepa Atanasova +2Explanation Faithfulness Faithfulness
Clustering as Reasoning: A $k$ -Means Interpretation of Chain-of-Thought Graph Learning
May 24, 2026Xuanting Xie, Zhaochen Guo, Bingheng Li +4Graph Representation Learning Chain-of-Thought Reasoning
Reasoning as an Attack Surface: Adaptive Evolutionary CoT Jailbreaks for LLMs
May 23, 2026Jianan Li, Simeng Qin, Xiaojun Jia +5Large Language Model Jailbreaks Jailbreak Evaluations
PointLLM-R: Enhancing 3D Point Cloud Reasoning via Chain-of-Thought
May 21, 2026Chaoqi Chen, Qile Xu, Wenjun Zhou +13D Scene Understanding Certified Point-Cloud
Mechanics of Bias and Reasoning: Interpreting the Impact of Chain-of-Thought Prompting on Gender Bias in LLMs
May 19, 2026Edie Pearman, Sophia Osborne, Mira Kandlikar-Bloch +3Large Language Model Bias Gender Bias
Do as I Say, Not as I Do: Instruction-Induction Conflict in LLMs
May 19, 2026Carolina Camassa, Derek ShillerInstruction-Tuned Models Instruction
The Expressive Power of Low Precision Softmax Transformers with (Summarized) Chain-of-Thought
May 18, 2026Moritz Brösamle, Stephan EcksteinTransformer Layers Gumbel-Softmax Relaxation
TTE-Flash: Accelerating Reasoning-based Multimodal Representations via Think-Then-Embed Tokens
May 15, 2026Jianpeng Cheng, Xian Wu, Jiangfan Zhang +10Multimodal Embeddings Latent Reasoning Tokens
Reasoning Models Don't Just Think Longer, They Move Differently
May 14, 2026Anders Gjølbye, Lars Kai Hansen, Sanmi KoyejoLarge Reasoning Models Chain-of-Thought Reasoning
Training on Documents About Monitoring Leads to CoT Obfuscation
May 14, 2026Reilly Haskins, Bilal Chughtai, Joshua EngelsObfuscation Chain-of-Thought Reasoning
Stateful Reasoning via Insight Replay
May 14, 2026Bin Lei, Caiwen Ding, Jiachen Yang +2Chain-of-Thought Reasoning Reasoning Trajectory
Pause and Reflect: Conformal Aggregation for Chain-of-Thought Reasoning
May 13, 2026Yu Gu, Zijun Yu, Vahid Partovi Nia +1Chain-of-Thought Reasoning Self-Consistency
Multilingual OCR-Aware Fine-Tuning and Prompt-Guided Chain-of-Thought Reasoning for Multimodal Large Language Models
May 13, 2026Qinwu Xu, Yifan Jiang, Haoyu RenMulti-Modal Large Language Models Deepseek-Ocr
Respecting Self-Uncertainty in On-Policy Self-Distillation for Efficient LLM Reasoning
May 13, 2026Junlong Ke, Zichen Wen, Weijia Li +2Unsupervised On-Policy Self-Distillation On-Policy Distillation
An Agentic AI Framework with Large Language Models and Chain-of-Thought for UAV-Assisted Logistics Scheduling with Mobile Edge Computing
May 13, 2026Hanwen Zhang, Dusit Niyato, Wei Zhang +2Edge Computing Last Mile
CoT-Guard: Small Models for Strong Monitoring
May 12, 2026Nirav Diwan, Han Wang, Berkcan Kapusuzoglu +6Guard Small Models
Intermediate Artifacts as First-Class Citizens: A Data Model for Durable Intermediate Artifacts in Agentic Systems
May 12, 2026Josh Rosen, Seth RosenAgentic Systems Content Provenance
When Reasoning Traces Become Performative: Step-Level Evidence that Chain-of-Thought Is an Imperfect Oversight Channel
May 12, 2026Wenkai Li, Fan Yang, Ananya Hazarika +2Reasoning Traces Chain-of-Thought Reasoning
Drop the Act: Probe-Filtered RL for Faithful Chain-of-Thought Reasoning
May 12, 2026Swapnil Parekh, Naman GoyalChain-of-Thought Reasoning Explanation Faithfulness
Latent Chain-of-Thought Improves Structured-Data Transformers
May 11, 2026Carson Dudley, Samet OymakTransformer Architectures Chain-of-Thought Reasoning
The Last Word Often Wins: A Format Confound in Chain-of-Thought Corruption Studies
May 11, 2026Gabriel GarciaChain-of-Thought Reasoning Correctness
Can You Keep a Secret? Involuntary Information Leakage in Language Model Writing
May 11, 2026Ari Holtzman, Peter WestData Leakage Leakage
Breaking the Reward Barrier: Accelerating Tree-of-Thought Reasoning via Speculative Exploration
May 11, 2026Shuzhang Zhong, Haochen Huang, Shengxuan Qiu +3Large Language Model Reasoning Tree-Of-Thoughts
Distilling 3D Spatial Reasoning into a Lightweight Vision-Language Model with CoT
May 10, 2026Alaa Asfour, Christopher Indris, Leihan Chen +23D Spatial Reasoning Spatial Reasoning
Efficient LLM Reasoning via Variational Posterior Guidance with Efficiency Awareness
May 10, 2026Zizhao Chen, Yuying Li, Siting Lin +1Efficient Inference Large Language Model Reasoning
Hidden Error Awareness in Chain-of-Thought Reasoning: The Signal Is Diagnostic, Not Causal
May 10, 2026Aojie Yuan, Zhiyuan Julian Su, Haiyue Zhang +2Chain-of-Thought Reasoning Reasoning Errors
Beyond Thinking: Imagining in 360 $^\circ$ for Humanoid Visual Search
May 9, 2026Jingdong Zhang, Yizhou Wang, Zhengzhong Tu +3Multimodal Search Agents Imagination
Relative Kinetic Utility for Reasoning-Aware Structural Pruning in Large Language Models
May 9, 2026Tianhao QianHeterogeneous Pruning Scores Large Models
The Coupling Tax: How Shared Token Budgets Undermine Visible Chain-of-Thought Under Fixed Output Limits
May 8, 2026Wenhua Nie, Junlin Liu, Jianan Wu +5Chain-of-Thought Reasoning Efficient Chain-Of-Thought Reasoning
ExpThink: Experience-Guided Reinforcement Learning for Adaptive Chain-of-Thought Compression
May 8, 2026Tingcheng Bian, Yuzhe Zhang, Jing Jin +5Large Reasoning Models Thinking
RCoT-Seg: Reinforced Chain-of-Thought for Video Reasoning and Segmentation
May 8, 2026Junwei Wen, Deshui Miao, Guangming Lu +2Video Object Segmentation Video Temporal Grounding
LaTER: Efficient Test-Time Reasoning via Latent Exploration and Explicit Verification
May 8, 2026Xuan Li, Yining Wang, Yuchen Liu +7Efficient Latent Reasoning Chain-of-Thought Reasoning
Convergence and Emergence of In-Context Reinforcement Learning with Chain of Thought
May 8, 2026Zixuan Xie, Xinyu Liu, Rohan Chandra +1In-Context Learning Iterative Co-Training
Extracting Search Trees from LLM Reasoning Traces Reveals Myopic Planning
May 7, 2026Sixing Chen, Ji-An Li, Saner Cakir +3Large Language Model Planning Large Language Model Reasoning
A Theory of Online Learning with Autoregressive Chain-of-Thought Reasoning
May 7, 2026Ilan Doron-Arad, Idan Mehalel, Elchanan MosselAutoregressive Generation Online Learning
Measuring Black-Box Confidence via Reasoning Trajectories: Geometry, Coverage, and Verbalization
May 7, 2026Marc Boubnovski Martell, Josefa Lia Stoisser, Kaspar Märtens +4Reasoning Trajectory Reasoning Benchmark
Policy-Guided Stepwise Model Routing for Cost-Effective Reasoning
May 7, 2026Wenwen Si, Insup Lee, Osbert BastaniInference Cost Chain-of-Thought Reasoning
Novelty-based Tree-of-Thought Search for LLM Reasoning and Planning
May 7, 2026Leon Hamm, Zlatan AjanovicTree-Of-Thoughts Large Language Model Planning
Think, then Score: Decoupled Reasoning and Scoring for Video Reward Modeling
May 7, 2026Yuan Wang, Ouxiang Li, Yulong Xu +8Large-Scale Video Generation Models Scoring
Evaluating Prompting and Execution-Based Methods for Deterministic Computation in LLMs
May 4, 2026Hongkun YuDeterministic Chain-of-Thought Reasoning
Act2See: Emergent Active Visual Perception for Video Reasoning
May 3, 2026Martin Q. Ma, Yuxiao Qu, Aditya Agrawal +4Visual Reasoning Visual Perception
Grounding Multi-Hop Reasoning in Structural Causal Models via Group Relative Policy Optimization
May 2, 2026Yunhan Bu, Quan Zhang, Huaping Zhang +9Multi-Hop Reasoning Structural Causal Model
Compliance versus Sensibility: On the Reasoning Controllability in Large Language Models
Apr 29, 2026Xingwei Tan, Marco Valentino, Mahmud Elahi Akhter +3Large Language Model Reasoning Chain-of-Thought Reasoning
Barriers to Universal Reasoning With Transformers (And How to Overcome Them)
Apr 28, 2026Oliver Kraus, Yash Sarrof, Yuekun Yao +2Transformer Architectures Chain-of-Thought Reasoning
Dual-Track CoT: Budget-Aware Stepwise Guidance for Small LMs
Apr 27, 2026Sagnik Chatterjee, Atharva Patil, Sricharan RameshLarge Language Model Reasoning Small Language Models
Learning to Think from Multiple Thinkers
Apr 27, 2026Nirmit Joshi, Roey Magen, Nathan Srebro +2Chain-of-Thought Reasoning Active Learning
When Chain-of-Thought Fails, the Solution Hides in the Hidden States
Apr 25, 2026Houman Mehrafarin, Amit Parekh, Ioannis KonstasChain-of-Thought Reasoning Reasoning Traces
CAP-CoT: Cycle Adversarial Prompt for Improving Chain of Thoughts in LLM Reasoning
Apr 25, 2026Shuxu Chen, Yitian Zhou, Jiaquan Zhang +6Adversarial Prompting Prior Prompt Optimization Techniques
Beyond Chain-of-Thought: Rewrite as a Universal Interface for Generative Multimodal Embeddings
Apr 24, 2026Peixi Wu, Ke Mei, Feipeng Ma +15Multimodal Embeddings Rewrite
Large Language Models Decide Early and Explain Later
Apr 24, 2026Ayan Datta, Zhixue Zhao, Bhuvanesh Verma +3Large Language Model Reasoning Chain-of-Thought Reasoning

May 26, 2026 · cs.CLJ/K move · Enter open · S save

Do Models Know Why They Changed Their Mind? Interpretability and Faithfulness of Chain-of-Thought Under Knowledge Conflict

Pruthvinath Jeripity Venkata

Independent Researcher

When a language model sees a document contradicting its training knowledge, it must choose: follow the document or trust itself. Prior work proved this choice depends on how well-known the fact is. We ask: does the model's chain-of-thought (CoT) reasoning faithfully report this mechanism? We introduce introspective faithfulness and test it across 200 questions, 8 models, and 4 prompt conditions. We find CoT reasoning is highly stable across opposite decisions: flip pairs retain 96% of same-answer similarity (d=0.34; confirmed by ROUGE-L, d=0.45). Yet self-rated confidence carries a faint genuine signal: for obscure facts where entity fame is uninformative, confidence still predicts decisions (p<0.001) and tracks item-level knowledge (r=0.134). GPT-4o is the only model with statistically reliable reasoning-decision coupling. Claude Sonnet 4.6 shows the widest confidence range (SD=1.39) but near-zero pooled correlation because the confidence-decision relationship reverses between conditions; a temperature ablation confirms this is model-specific. Internal thinking tokens show greater decision-sensitivity than user-facing CoT (p=0.033). CoT decomposes into a decision-invariant knowledge display (~96%) and a thin confidence layer with weak but real signal. For monitoring: read confidence, not the argument.

Chain-of-Thought Reasoning Model Interpretability Knowledge Conflicts

Open paper Ask about it PDF

Recent momentum

Neighbouring directions

Recent digests

3 new papers

7 new papers

6 new papers

Latest in Chain-of-Thought Reasoning