Latest Chain-of-Thought Reasoning Research Papers

The newest Chain-of-Thought Reasoning papers from across the field — arXiv, NeurIPS, CVPR, Nature, and more — refreshed daily and ranked by relevance. Distill AI tracks Chain-of-Thought Reasoning so you don’t have to: get the standout work delivered to your inbox every morning, with 2-sentence summaries and the option to chat with any paper.

Recent papers

• The Sociolinguistics of Machine Identity: LLM Personality and Ideology Propagation
  Guangni Li · OpenAlex · Dec 31, 2026

  Do large language models (LLMs) possess a measurable "personality," and how do the linguistic properties of training corpora shape their cognitive style and downstream reasoning? This paper approaches these questions from a sociolinguistic …

• Multi-dimensional hierarchical temporal alignment for improved temporal commonsense reasoning in large language models
  Ge Yan, Hai-Tao Yu, Lei Chao, 30751052 et al. · Institutional Repositories ... · Nov 1, 2026

  Benefiting from recent advances in generative AI and large language models (LLMs), current LLM-driven AI systems are rapidly reshaping how we reason, plan, and make decisions. Yet endowing these systems with human-like temporal intelligence…

• PIVOT: Progressive Intervention via Online Teacher Correction
  Zhihao Yang, Boyuan Zheng, Puhui Tan, Yukun Chen et al. · arXiv · Oct 29, 2026

  Reinforcement learning from verifiable rewards (RLVR) is limited by sparse outcome-level feedback on hard reasoning tasks: when all rollouts in a group fail, rewards provide no learning signal. Stronger teachers can provide additional guida…

• Homebrewed SLMs: Autoregressive and Masked Diffusion Language Models Built at Home for Portuguese
  Pedro Carvalho Brom · arXiv · Oct 29, 2026

  Building a language model of one's own no longer requires a data centre. This tutorial trains one from scratch, tokenizer included, on one consumer GPU, and shows how to tell whether it is good for the tasks of a specialist domain. It propo…

• Agentic LLM reasoning in pediatric diabetes outcome prediction from multimodal medical records
  Daniel Palacios, Guantong Qi, Anna Kadi, Natali Borrego et al. · arXiv · Oct 29, 2026

  Large language model (LLM) agents are proposed for clinical prediction but are untested in pediatrics, where cohorts are small and outcomes are uncommon. Using records from 2,489 youth with type 2 diabetes (T2D) and 4,018 with type 1 diabet…

• Don't Lose the Thread: Empowering Long-Horizon LLM Agents with Cognitive Resource Self-Allocation
  Zheng Zhu, Xiaozhuan Liang, Xi Chen, Bei Yu et al. · arXiv · Oct 29, 2026

  Agents powered by large language models (LLMs) have demonstrated remarkable progress in solving complex reasoning tasks. However, LLM agents often falter on long-horizon tasks due to cognitive overload, as their working memory becomes clutt…

• Latent Path Exploration via Potential-Guided Subtrajectory Balance
  Xiaoling Zeng, Qi Zhang · arXiv · Oct 29, 2026

  Continuous latent reasoning enables language models to perform intermediate computation without generating explicit reasoning traces. Advances in stochastic latent reasoning allow multiple paths to be sampled in continuous space, but stocha…

• Incentivizing Self-Learning in Large Language Models via Reinforcement Learning
  Lingkai Kong, Yuzhe Gu, Haiteng Zhao, Zijian Wu et al. · arXiv · Oct 29, 2026

  Large language models (LLMs) draw on parametric knowledge and retrieval-augmented generation (RAG) to solve knowledge-intensive tasks. Yet problem solving in unfamiliar domains calls for tightly coupled knowledge acquisition and reasoning, …

• Diagnosing the Reference Gap: What Visual Scaffolds Can and Cannot Fix in Multimodal Reasoning
  Guizhen Chen, Weiwen Xu, Wotao Yin, Anh Tuan Luu et al. · arXiv · Oct 29, 2026

  Multimodal large language models can recognize visual content yet struggle to reason reliably over it across multiple steps. In counting, a model may see all objects but lose track of which ones it has counted. We argue that such failures, …

• How Specific Do I Need to Be? Effects of User Query Underspecification on Deep Research Agents
  Yi Wen, Xiangjue Dong, Bingxuan Li, Hangxiao Zhu et al. · arXiv · Oct 29, 2026

  Deep research agents (DRAs) conduct long-horizon reasoning, search, and literature synthesis to provide long-form answers to complex, domain-specific questions. These agents are typically trained and evaluated on fully specified user querie…

• Grounding Multimodal Reasoning with Evidence-Ablated Negatives
  Chenxi Liu, Tianyi Xiong, Yanshuo Chen, Heng Huang · arXiv · Oct 29, 2026

  Reinforcement learning with verifiable rewards (RLVR) has become a powerful tool for improving multimodal reasoning. However, standard outcome supervision suffers from credit assignment ambiguity, as a model may receive positive rewards by …

• Reasoning or Pattern Exploitation? Mechanistic Insights from RL-Trained Language Models
  Aishik Nagar, Cheston Tan · arXiv · Oct 29, 2026

  Large language models (LLMs) are increasingly described as acquiring "reasoning" skills after reinforcement learning with verifiable rewards. However, whether these gains reflect genuine reasoning or more superficial adaptations remains und…

• Implicit Reasoning in Transformers: Bridging the Compositionality Gap in GPT-2-like Models
  Davide Venuto, Leonardo Venuto · arXiv · Oct 28, 2026

  Compositional generalization remains a persistent limitation of transformer language models: even when a model learns to combine known facts correctly in-distribution (ID), the same compositional mechanism may fail when applied to out-of-di…

• AtomTree: A Hierarchical Framework for State-Aware Embodied Instruction Following with LLMs
  Haotian Zhai, Tianming Sha, Junnan Li · arXiv · Oct 28, 2026

  Embodied instruction following in interactive environments requires agents to interpret natural language commands and complete long-horizon tasks. Existing planners either rely on large labeled trajectories, or use few-shot and zero-shot LL…

• Weaken to Strengthen: Weakening-Induced On-Policy Self-Distillation for Large Reasoning Models
  Yecheng Wu, Song Han, Han Cai · arXiv · Oct 28, 2026

  Self-distillation offers a way to improve reasoning models when a suitable external teacher is unavailable. However, common approaches rely on privileged information to construct a stronger self-teacher, limiting their use when only unlabel…

• Do Audio LLMs HEAR Pain? Tracing Acoustic Evidence from Speech to Language Reasoning
  Wenqi Li, Xiangjue Dong, Sulaiman Vesal · arXiv · Oct 28, 2026

  Large audio language models (LALMs) can process speech directly, but it remains unclear how well they use the non-lexical acoustic information that speech carries. We study this question through pain, using TAME-Pain, which contains pain-ne…

• CoSTA: Co-Evolving Self-Play Timeline Agents for Complex Temporal Knowledge Graph Question Answering
  Haikun Liu, Zhichao Yan, Shaoru Guo, Jiawei Gu et al. · arXiv · Oct 28, 2026

  Complex Temporal Knowledge Graph Question Answering (TKGQA) involves more than retrieving facts: the timestamp or validity interval of one fact can constrain the search for another, while multiple intervals may jointly determine the answer.…

• Teach reality, not ethics: a drop-in continued-pretraining corpus installs coupled human-biosphere-AI welfare dispositions across model families
  Trent R. Northen, Mingxun Wang · arXiv · Oct 27, 2026

  Large language models (LLMs) are increasingly used to make and execute decisions that affect living systems. Yet, to our knowledge, ecological reasoning is not a focus of pre- or post-training. This increases the risk that under operational…

• Representing the Unseen: Rethinking Visual Imagination for Spatial Reasoning
  Zengqi Zhao, Zun Wang, Shoubin Yu, Mohit Bansal et al. · arXiv · Oct 27, 2026

  Visual world models increasingly support spatial reasoning by generating RGB views of unobserved states. However, RGB has become the default interface largely because it is well suited for visual generation, rather than necessarily being th…

• Watermark Basins: Black-Box Detection of Distilled LLMs
  Hongyan Chang, Hady Elsahar, Tom Sander, Pierre Fernandez et al. · arXiv · Oct 27, 2026

  Proprietary language models and their reasoning traces are vulnerable to API-based distillation, where an adversary trains a student model on the teacher model's outputs. To obtain evidence of distillation, model providers can watermark the…

• Uncovering Shortcut Amplification in Video RLVR through the Lens of Perceptual Uncertainty Collapse
  Jiafeng Liang, Xianhao Ou, Tao Ren, Rongchuan Mu et al. · arXiv · Oct 27, 2026

  Reinforcement learning with verifiable rewards (RLVR) has emerged as an effective post-training paradigm for enhancing the video reasoning capability of Large Multimodal Models (LMMs). Despite its empirical effectiveness, we show that outco…

• Prospector: learning a compact graph traversal policy for scientific reasoning
  Haiqian Yang, Markus J. Buehler · arXiv · Oct 27, 2026

  Scientific reasoning in specialized engineering fields depends on knowledge scattered across the literature, often proprietary and absent from frontier LLM training data. In such domains, frontier models tend to give generic answers. Knowle…

• Guided-RLVR: Guided Exploration in Reinforcement Learning with Verifiable Rewards
  Bo Yang, Zishuai Zhang, Weihua Li, Qinnan Zhang et al. · arXiv · Oct 27, 2026

  Reinforcement learning with verifiable rewards (RLVR) has shown strong empirical gains in improving the reasoning ability of large language models (LLMs) on tasks such as mathematics and programming. However, recent studies have shown that …

• SpectRAG: Weighted Chunk Graphs for Token-Budgeted Context Selection in Multi-Hop Retrieval-Augmented Generation
  Zafer Sahinoglu, Abdulazeez Mohammed, Buse Yaren Kazangirler, Cahit Berkay Kazangirler · arXiv · Oct 27, 2026

  Retrieval-augmented generation (RAG) systems ground large language models (LLMs) by retrieving external evidence and conditioning generation on the retrieved context. Although dense retrieval is effective for local semantic matching, indepe…

• HiLo-RD: Cross-Budget Self-Distillation for Masked Diffusion Language Models
  Xiang Li, Chengting Yu, Jungang Li, Yilun Zheng et al. · arXiv · Oct 27, 2026

  We propose HiLo-RD (High-to-Low Budget Representation Distillation) to improve masked diffusion language models (MDLMs) under a limited generation budget. Unlike autoregressive models, MDLMs choose both what to generate and where to commit …

• Latent Visual Contrastive Reasoning with Multi-Branch Exploration
  Kegeng Tang, Jingbo Wang, Yangming Zhang, Huanshu Zhang et al. · arXiv · Oct 27, 2026

  Multimodal large language models have made substantial progress in visual question answering, but complex visual reasoning often requires locating and comparing multiple pieces of question-relevant visual evidence. Existing methods that mov…

• DocSkill: Skill-Integrated Agentic Reasoning for Multilingual Multi-Hop Document Question Answering
  Jing Huang, Zhiya Tan, Changtao Miao, Shutao Gong et al. · arXiv · Oct 27, 2026

  Multilingual multi-hop document question answering (MMHop-DocQA) requires locating and integrating evidence across complex layouts, document pages, and diverse languages. Existing approaches include single-pass processing and adaptive tool …

• Is Token Confidence Just Chain Length? A Signal-Processing Audit of Reasoning Traces
  Pragna Mallappa · arXiv · Oct 27, 2026

  Reasoning language models answer math problems by writing long chains of thought, and sampling many chains per problem and taking a majority vote raises accuracy at a large cost in generated text. A popular way to cut that cost scores each …

• PRISM-BENCH: Diagnosing Grounded and Faithful Multimodal Reasoning Beyond Final-Answer Accuracy
  Vansh Bhatia, Mehdi Rezagholizadeh, Parsa Ashrafi Fashi, Igor Gilitschenski et al. · arXiv · Oct 27, 2026

  Final-answer accuracy reports whether a vision-language model was right, but not whether its answer was grounded in the image, whether its stated reasoning reflects that evidence, or what the answer cost to produce. Those are the properties…

• How Much Does the Hint Matter? Scope Conditions for Hindsight Self-Distillation in Financial Reasoning
  Johnny Yu, Cyril Gorlla · arXiv · Oct 26, 2026

  Financial institutions operating under data-residency constraints are restricted to open-weight models small enough to locally host, which trail frontier systems on multi-step quantitative reasoning. On-policy distillation narrows such gaps…