CoT Reasoning

CoT: Chain-of-Thought

Follow this topic Ask about this topic

Momentum

12 papers in the last four weeks, up 71% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 150

Jul 23, 2026cs.CL

REFACT: Adaptive Fact Restatement for Compact and Faithful Chain-of-Thought Reasoning

Large Language Models (LLMs) increasingly leverage long-form reasoning to solve complex tasks, yet their reasoning processes can deviate from the provided context when evidence is incomplete, noisy, or conflicts with parametric knowledge. Existing grounding approaches either append citations after generation or encourage LLMs to retrieve evidence during reasoning, but they often fail to ensure that cited information is sufficient to support intermediate inferences and final answers. To address this limitation, we propose REFACT, an adaptive fact-restatement citation framework that enables LLMs to determine when contextual grounding is needed and selectively restate source facts at appropriate levels of detail for reliable reasoning. To facilitate adaptive citation during reasoning, REFACT first leverages a teacher LLM to construct high-quality citation-aware reasoning trajectories under diverse context conditions with varying evidence lengths, and then optimizes the student LLM through a two-stage SFT-to-RL framework. Experiments on LongBench, LV-Eval, and ConFiQA demonstrate that REFACT improves long-context question answering and counterfactual faithfulness while substantially reducing the number of reasoning tokens. Further analysis reveals that REFACT achieves higher evidence density by preserving more answer-relevant facts with fewer restatements, producing reasoning traces that are more concise yet better grounded. All code and data will be released via https://github.com/NEUIR/REFACT.

Zhensheng Jin, Xin Dai, Zhenghao Liu +5

Northeastern University · Shenyang, China · Tsinghua University +1

LLM Grounding Long-Context QA CoT Reasoning

Jul 21, 2026cs.RO

Cognitive Dual-Process Planning for Autonomous Driving with Structured Scene Knowledge and Verifiable Reasoning-Action Consistency

High-level planning for autonomous driving is a knowledge-intensive engineering decision task that requires accurate scene understanding, timely inference, and internally consistent action selection. Vision-language models (VLMs) can make intermediate reasoning explicit, but their use in deployed planners is constrained by costly structured supervision, unnecessary reasoning in routine scenes, and possible inconsistencies between generated rationales and driving actions. We present a cognitive dual-process planning framework that represents planning-relevant scene knowledge in a machine-parsable structured chain-of-thought (S-CoT) schema. An automated data engine integrates perception foundation models, critical-path filtering, and an expert VLM to generate S-CoT supervision without manual annotation of individual rationales. A lightweight visual Arbiter estimates scene complexity from multilevel vision-encoder features before language decoding and routes each input to either fast meta-action prediction or slow structured reasoning. For slow-path outputs, a deterministic rule-based validator checks whether the parsed S-CoT fields are consistent with the final meta-action and provides verifiable rewards for Group Relative Policy Optimization (GRPO). In a 195-scene manual audit, the generated annotations achieve 91.8% CoT accuracy and a 98.5% Logical Consistency Score (LCS). On 574 manually verified NAVSIM test samples, the planner achieves 80.14% planning accuracy and 97.20% LCS while reducing average latency by 17.39% relative to applying slow reasoning to every scene. Evaluation on external long-tail subsets further identifies conditions under which routing and planning performance degrade. Together, these results show how explicit scene knowledge can be operationalized through adaptive reasoning and rule-based verification to support high-level VLM planning decisions.

Zhongyao Yang, Haoyu Li, Yu Yan +3

School of Mechanical Engineering, Beijing Institute of Technology, Beijing, 100081, Beijing, China · National Engineering Research Center of Electric Vehicles, Beijing Institute of Technology, Beijing, 100081, Beijing, China · School of Mechanical Engineering, Southeast University, Nanjing, 211189, Jiangsu, China +1

VLMs for Autonomous Driving CoT Reasoning VLM Reasoning Autonomous Driving Planning

Jul 20, 2026cs.LG

A Geometric Perspective on Stabilizing Value Conflict Resolution

Large Language Models (LLMs) often struggle to navigate value conflicts when trained with the compressed scalar rewards of Reinforcement Learning from Human Feedback (RLHF). To address this challenge, we investigate how chain-of-thought (CoT) reasoning can help improve performance in this domain. Geometrically, we show that CoT correlates with further smoothing the model's loss landscape in its sharpest direction, helping resolve the optimization instability of traditional scalar rewards. We also demonstrate via relevant downstream benchmarks that value conflict-focused CoT may generalize to different kinds of moral reasoning, demonstrating that this CoT has the potential to be an effective mechanism for better moral reasoning. To capitalize on this potential, we create a new value conflict-focused CoT design that further smooths the sharpest direction of the loss landscape and increases moral reasoning performance. This finding shows that explicitly modifying and improving the design of reasoning dynamics offers a promising avenue for improving model performance on user requests with complex value conflicts, advancing pluralistic alignment in LLMs.

Saket Reddy, Andy Liu

Supervised Program for Alignment Research (SPAR) · University of Illinois - Urbana-Champaign · Carnegie Mellon University

LLM Alignment Moral Reasoning in Language Models CoT Reasoning

Jul 18, 2026cs.AI

Training Continuous Chain of Thought Models: A Tale of Two Regimes

Continuous Chain-of-Thought methods replace verbose reasoning traces with a short sequence of dense latent representations. Earlier continuous CoT methods indirectly supervise the latent representations such that its final state match that of verbose reasoning traces, requiring autoregressive, slow generation during training. We introduce C-MTP, a simpler, faster direct supervision approach that models each latent as an average of the embeddings in the CoT traces to be compressed. Our approach outperforms a prior direct supervision method that approximates the distribution of compressed tokens, and performs competitively to slower indirect supervision approaches in existing evaluation setup with simplified CoT traces (less than 100 tokens). Lastly, we extend the evaluation of Continuous CoT methods to complex tasks with longer reasoning traces (

\ge

few hundreds reasoning tokens). We find both direct and indirect supervision training methods perform poorly (roughly 65% performance drop) in this setting, revealing the limitations of current continuous CoT methods. The code and checkpoints are released at https://github.com/Varun221/cmtp_research

Varun Yerram, He He, Eunsol Choi

Center for Data Science, New York University

CoT Reasoning Continuous Latent Reasoning LLM Training CoT Compression Latent Reasoning

Jul 11, 2026cs.CL

When Reasoning Hurts Legal Drafting: The Verbalization Bottleneck in Patent Claim Generation

Patent claim drafting is a challenging legal drafting task that requires technical expertise, precise linguistic control, strict adherence to formal conventions, and the preservation of complex logical relationships among claim elements. While Chain-of-Thought (CoT) prompting has been widely used to improve the reasoning capabilities of large language models (LLMs), recent evidence suggests that its benefits may be limited, or even negative, in highly structured or pattern-sensitive tasks. Therefore, this paper investigates whether CoT prompting benefits patent claim generation. We propose a task-specific CoT method for patent claim generation and evaluate its effectiveness through both automatic metrics and human expert assessment. Our results show that reasoning-enhanced prompting can improve claim quality. Moreover, we demonstrate a counter-intuitive but important empirical finding: implicit CoT, where reasoning is kept internal rather than explicitly verbalized, consistently outperforms explicit CoT. Through systematic analysis, we show that explicit CoT can introduce an unnecessary information bottleneck for claim generation. Verbalized reasoning may compromise the quality of final outputs through three specific mechanisms: abstraction of critical details, disruption of internalized generation patterns, and cascading error propagation. Our findings provide new insights into legal tasks and CoT applications.

Lekang Jiang, Wenjun Sun, Stephan Goetz

University of Cambridge · National Science Library, Chinese Academy of Sciences; Department of Information Resources Management, School of Economics and Management, University of Chinese Academy of Sciences.

LLM Prompting CoT Reasoning Text Generation LLM Reasoning

Jul 11, 2026cs.CL

Structured Thoughts For Improved Reasoning And Context Pruning

Large language models (LLMs) excel at generating long chains of thought, but long reasoning traces are often verbose and memory-inefficient. In this work, we introduce Structured Thoughts, a framework that organizes reasoning into alternating <try> and <outcome> blocks: <try> captures exploratory scratch work, while <outcome> contains the distilled conclusion of that step. We construct a dataset of structured thoughts by segmenting reasoning traces into <try> blocks and prompting an LLM to summarize each step into its corresponding <outcome>. Fine-tuning pretrained foundation models on this reformatted data produces models that adopt the structured reasoning style, leading to performance gains of up to 8.08% on reasoning benchmarks compared to standard SFT. The explicit structure also enables context pruning: after each <try>/<outcome> pair, the <try> can be pruned, allowing the model to retain conclusions without keeping the full scratch work in the context. A proof-of-concept pruning implementation achieves an average of 85% memory / context savings with an 8.67% performance drop across mathematical tasks.

Zain Sarwar, Supriyo Chakraborty, Berkcan Kapusuzoglu +5

University of Chicago · Capital One

CoT Reasoning Efficient Language Model Reasoning Structured Reasoning LLM Context Management LLM Reasoning

Jul 8, 2026cs.LG

The Optimal Sample Complexity of Learning Autoregressive Chain-of-Thought

We prove that, in the realizable PAC setting, the sample complexity of exact-trace learning for full autoregressive Chain-of-Thought traces is upper bounded by the standard multiclass rate of the local next-token class, where this rate is governed by the Daniely--Shalev-Shwartz dimension. Under exact-trace loss, one wrong action makes the whole trace incorrect; nevertheless, for every stopping rule

\mathtt{halt}

and every pointwise

\mathtt{halt}

-halting local class

\mathrm{H}

,

n_{\mathrm{PAC}}^{\varepsilon,δ}(\operatorname{Roll}_{\mathtt{halt}}(\mathrm{H}))=O((\operatorname{DSdim}(\mathrm{H})+\log(1/δ))/\varepsilon)

, with no dependence on rollout length. The dependence on

\operatorname{DSdim}(\mathrm{H})

is worst-case optimal, since one-step stopping recovers ordinary multiclass learning of

\mathrm{H}

. The proof introduces parity dimension, a rollout-stable refinement of DS dimension based on even pseudo-cubes. It controls one-inclusion density via a low-coordinate spanning theorem on finite restrictions and, unlike DS dimension itself, does not increase under autoregressive rollout. We also show why this detour is necessary: DS dimension can increase under rollout.

Zhiyuan Li

Toyota Technological Institute at Chicago

CoT Reasoning PAC Learning Statistical Learning Theory

Jul 2, 2026cs.AI

Purified OPSD: On-Policy Self-Distillation Without Losing How to Think

On-policy self-distillation (OPSD) has emerged as a promising paradigm for improving LLM reasoning, where a privileged teacher with access to reference solutions provides token-level supervision on the student's own generated trajectories. However, we find that OPSD consistently fails on long chain-of-thought (long-CoT) reasoning models, yielding at best marginal gains while destabilizing the reflective reasoning capability these models depend on. Through a novel decomposition of the teacher's supervision signal, we identify the root cause: the teacher's supervision is dominated by a reference-induced component that drives rote memorization of reference-specific shortcuts, while the question-conditioned, inference-transferable component is ignored or actively opposed. Based on this diagnosis, we propose a two-step solution. First, we construct a reference-only teacher (the same model conditioned on the reference without the question) to isolate the non-transferable component of the supervision signal; the residual after subtracting this component captures the question-conditioned, inference-transferable correction. Second, we use pointwise mutual information (PMI) as the mechanism to transform this residual into a well-formed PMI target distribution that the student can directly distill from, filtering out the reference-induced shortcut. Experiments on four long-CoT models across two datasets demonstrate consistent improvements over both the base model and standard OPSD, while preserving the models' natural epistemic behavior throughout training.

Zhanming Shen, Jintao Tong, Shaotian Yan +9

1Zhejiang University · 2Tongyi Lab, Alibaba Group · 3Huazhong University of Science and Technology +1

CoT Distillation On-Policy Self-Distillation CoT Reasoning On-Policy Distillation LLM Reasoning

Jul 1, 2026cs.AI

Revisiting Chain-of-Thought Reasoning under Limited Supervision: Semi-supervised Chain-of-Thought Learning

Chain-of-thought (CoT) reasoning has emerged as an effective approach for activating latent reasoning capabilities in large language models. However, most existing CoT methods use reasoning chains mainly as inference-time prompts, while the generated reasoning traces are rarely reused as semi-supervised learning signals. In this report, we define \textbf{Semi-supervised Chain-of-Thought Learning} and propose \textbf{Semi-CoT}, a simple framework that uses unlabeled questions to construct pseudo reasoning supervision. Semi-CoT samples multiple pseudo-CoTs for each unlabeled question, estimates answer-level semantic entropy, and selects low-entropy reasoning chains as reliable pseudo-CoT demonstrations. This extends the self-training view of CoT from inference-time refinement to semi-supervised pseudo-supervision. Pilot experiments on AQuA, SVAMP, GSM8K, and MultiArith show that the entropy gate selects high-precision pseudo-CoTs, with pseudo-answer precision ranging from

91.36\%

to

100\%

. Semi-CoT also gives small gains on SVAMP and GSM8K, while AQuA shows negative transfer and MultiArith reaches a ceiling. These results suggest that unlabeled questions can provide reliable pseudo reasoning signals, but their effective use still requires stronger demonstration selection or student training.

Hongyang He, Jiuming Liu, Victor Sanchez

University of Warwick · University of Cambridge

Self-Training for Language Models CoT Reasoning Semantic Entropy Semi-Supervised Learning Language Model Self-Improvement

Jun 30, 2026cs.LG

Bridging the Gap Between Latent and Explicit Reasoning with Looped Transformers

Language models typically reason via explicit chain-of-thought (CoT), generating intermediate steps token-by-token. Latent CoT offers an alternative: it performs multi-step reasoning in the model's hidden states, replacing decoded tokens with continuous representations for greater efficiency. However, existing latent CoT methods underperform explicit CoT beyond 1B parameters, and the gap widens with scale. Looped, or recurrent-depth, Transformers, which reuse their weights to increase computation depth without adding parameters, are a natural fit for latent reasoning. We therefore ask whether looped Transformers can bridge this gap. We answer affirmatively with a simple recipe: a looped padded Transformer that processes K latent blocks in parallel for R iterations, with a cross-entropy loss on each latent position's gold CoT-step token, similar to explicit CoT supervision. We instantiate it as LOTUS (Looped Transformers with parallel supervision on latents). LOTUS is, to our knowledge, the first latent-CoT method to bridge the gap to explicit CoT at the 3B scale, while cutting thought-phase latency by 2.5x-6.9x from compact math expressions to natural language. Projecting LOTUS's post-loop latents through the base LM head recovers the gold reasoning steps and even surfaces alternative valid intermediate steps, evidence that its latent space is interpretable and CoT-aligned. Ablations confirm that both the looped backbone and the parallel supervision on gold CoT tokens are essential. Code is available at https://github.com/yingfan-bot/lotus.

Ying Fan, Anej Svete, Kangwook Lee

Microsoft Research · 2ETH Zürich · 3KRAFTON +1

CoT Reasoning Recurrent Transformers Continuous Latent Reasoning Efficient Language Model Inference Latent CoT Reasoning

Jun 29, 2026cs.AI

Does Verbose Chain-of-Thought Really Help? In-Distribution Evidence that Content, Not Length, Matters

Chain-of-thought (CoT) prompting improves LLM reasoning, but the source is contested: do the intermediate steps help because they carry useful semantic content, or because conditioning on more tokens buys extra computation before the model commits to an answer? We bring two lines of evidence to bear. First, in distribution: we repeatedly sample each model on the same question and pair a shorter with a longer of its own natural generations that follow the same reasoning plan, so nothing is rewritten and both traces are genuinely in-distribution. Across 25 models the extra tokens leave accuracy essentially unchanged for every independently-trained reasoner, and a blind analysis of the surplus tokens shows that what gain exists elsewhere tracks validation- and checking-content, not verbosity per se. Second, as a controlled intervention, we ask whether two traces expressing the same semantic content (the same facts, operations, and intermediate values, verified through directed acyclic graph equivalence) produce different outcomes when one is more verbose, using a dual-validator design across four targets and eight benchmarks with number-redacted completion and stratified bootstrap confidence intervals. Verbose traces do improve accuracy (25 of 32 benchmark-target cells are positive under at least one validator), but the effects are modest (typically 1-4 points) and depend on the quality of the verbose prose, not merely its length. Under maximum numerical redaction the effect is amplified (median 3.24x across four arithmetic benchmarks), and length-matched non-reasoning filler recovers none of it. Both lines converge: what matters is what the extra tokens do (the reasoning and validation content they carry), not how many there are, a picture neither a pure forward-pass-compute nor a pure semantic-content account fully explains.

Wenlong Wang, Fergal Reid

Fin AI Research

LLM Prompting CoT Reasoning LLM Reasoning Reasoning Trace Analysis

Jun 29, 2026cs.CV

Latent-CURE for Breast Cancer Diagnosis

Multimodal Large Models have significantly advanced automated breast ultrasound diagnosis. However, most existing frameworks utilize opaque, end-to-end paradigms prioritizing global statistical correlations over structured clinical reasoning. Consequently, these models remain susceptible to shortcut learning amid extreme real-world epidemiological imbalances, often bypassing rare but decisive malignant indicators for dominant benign patterns. To address this disconnect, we propose Latent-CURE, a novel diagnostic framework driven by asymmetric weighted chain-of-thought methodology grounded in latent space reasoning. Unlike traditional approaches, our framework constructs an implicit reasoning trajectory forcing the model to sequentially infer standardized BI-RADS morphological descriptors before converging on a final diagnosis. Furthermore, to combat the extreme scarcity of critical malignant features, we couple this architecture with a dual-asymmetric optimization strategy. By dynamically adjusting margins and weights, this strategy safeguards high-specificity malignant descriptors from being overshadowed by common benign priors. Comprehensive evaluations demonstrate that our knowledge-injected approach provides transparent clinical evidence while achieving robust, accurate diagnostic performance in imbalanced medical cohorts.

Weiyi Zhao, Xiaoyu Tan, Lu Gan +2

School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai 201620, China · Tencent YouTu Lab, Shanghai 200232, China · Integrative Clinical Research Ward, Clinical Medicine Research Institute, Zhongshan Hospital, Fudan University, Shanghai 200032, China

Breast Cancer Long-Tail Learning CoT Reasoning Ultrasound Imaging Medical VLMs Explainable Medical Image Analysis

Jun 28, 2026cs.LG

Do Models Read What They Write? Causal Registers in Scratchpad Reasoning

A central hope behind process supervision is that models can expose intermediate variables that matter for their later behavior. For this to help with alignment, a scratchpad must be tied to the computation: when the model writes a state, later steps should compute from that state. To test this requirement, we use a controlled state-tracking task with a known update rule, comparing models trained to report only the final state with models trained to write intermediate states before giving the final answer. At evaluation, we edit the internal representation of one written state while leaving the visible scratchpad text fixed. Because the transition rule is known, the edit has a single correct downstream consequence. In Qwen2.5-Coder-7B, the state-writing model predicts the next phase bit implied by the edited state on 80% and 91% of held-out examples across the two task variants, while pretrained and final-answer-only controls remain near baseline. Additional controls rule out generic next-token steering and copying another continuation: the prediction depends on both the edited state and the current move. The same causal-use pattern replicates across model families. Together, these results suggest a sharper goal for scratchpad oversight: not just to make intermediate reasoning legible, but to train written states that the model uses as part of its computation.

Benjamin Shih, John Winnicki, Eric Darve

Institute for Computational and Mathematical Engineering Stanford University

CoT Faithfulness CoT Reasoning State Tracking Process Supervision Causal Interventions in Language Models

Jun 25, 2026cs.CL

Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization

Building general-purpose role-playing agents that faithfully portray any character from a natural-language profile remains challenging. The dominant paradigm -- supervised fine-tuning -- encourages behavioral mimicry without deep, human-like internal thought processes, resulting in poor out-of-distribution generalization. Therefore, we propose \textbf{Psy-CoT}, a psychology-grounded chain-of-thought framework that decomposes pre-response reasoning into three role-specific steps -- \emph{Interaction Perception}, \emph{Psychological Empathy}, and \emph{Logical Construction} -- so that the model \emph{thinks dynamically} from the profile rather than merely mimicking surface patterns. While structured reasoning provides a foundation, it alone is insufficient; reinforcement learning is essential to further align the model with character fidelity. However, we observe that under LLM-based reward models, both generic phrases that hack the reward model and genuinely role-specific phrases receive identical gradient signals -- this hacking accumulates over training, misleading the model into treating both as equally optimal choices. To address this, we propose \textbf{Role-Aware Policy Optimization (RAPO)}, which uses profile--token mutual information to weight gradients asymmetrically -- amplifying role-specific tokens under positive advantage while attenuating them under negative advantage. Experiments on CoSER, CharacterBench, and CharacterEval demonstrate that Psy-CoT outperforms existing role-playing CoT methods, and RAPO consistently surpasses GRPO across multiple model scales.

Zhenhua Xu, Dongsheng Chen, Jian Li +7

1Zhejiang University · 2Tencent Youtu Lab

Large Language Model-Based Role-Play Simulation Personality Modeling in Language Models CoT Reasoning RL for Language Model Reasoning

Jun 25, 2026cs.AI

Where Do CoT Training Gains Land in LLM based Agents?

Chain-of-thought (CoT) reasoning is widely used in language-model agents, but prior work has shown that verbalized CoT is not always faithful and may instead reflect post-hoc reasoning, which means the model already knows the answer before reasoning. We therefore ask what CoT training is actually improving: is the model getting better at changing its action through generated reasoning, or is it getting better at predicting the action directly from the prompt? We study this question by comparing \emph{prompt actions} (predicting action without CoT) with CoT actions (predicting action with CoT). Across checkpoints, prompt-action quality improves substantially. While interacting with the environment, the relative advantage of CoT actions over prompt actions remains similar, showing that CoT training does not widen the advantage of CoT reasoning, and it helps to improve the quality of prompt actions. We further find that later checkpoints are less likely to revise the action in response to CoT, suggesting greater reliance on the prompt. Motivated by these patterns, we selectively mask action-token supervision on a fraction of training examples. This intervention improves out-of-domain generalization.

Jingyu Liu, Zhiwen Wang, Yuxin Jing +2

Gaoling School of Artificial Intelligence Renmin University of China, Beijing, China · ByteDance · Beijing Key Laboratory of Research on Large Models and Intelligent Governance +1

CoT Reasoning LLM Agents LLM Agent Training

Jun 25, 2026cs.AI

Do Safety Guardrails Need to Reason? LeanGuard: A Fast and Light Approach for Robust Moderation

In order to screen a prompt or a response, the recent guardrail methods generate a chain-of-thought (CoT) before they issue a verdict. This design follows a common belief that step-by-step reasoning improves a decision. However, CoT also makes the guard heavy and slow, because the model must generate many tokens before it decides. This may not match how guardrails are actually deployed. A guardrail sometimes should not be heavy and slow, and it often runs on-device, for example on an embodied robot. In this paper, we pose a question whether a safety guardrail really needs to reason. To answer this question, we train a lightweight bidirectional encoder and a reasoning guard on the same corpus, and we then remove only the reasoning while we keep everything else fixed. With this controlled same-base comparison, we show that the chain does not improve moderation accuracy. We name the resulting guard LeanGuard. A 395M label-only encoder reaches an average F1 of 82.90

\pm

0.26 over public benchmarks. It matches a reasoning guard that is built on a much larger decoder, while it uses only a single forward pass over an input of at most 512 tokens. This is about a ~100x reduction in inference compute. We further show that this label-only encoder stays robust under training-label noise and retains far more recall at a strict false-positive rate than the reasoning guard, so a heavier reasoning guard is not the more robust choice either. Our finding suggests that the current guardrail benchmarks may not be hard enough to reward reasoning, and that the necessity of CoT for moderation is still not proven. We release all source codes and models including LeanGuard at https://github.com/ndb796/LeanGuard.

Dongbin Na

POSTECH

LLM Guardrails CoT Reasoning Safety Filtering Language Model Robustness

Jun 20, 2026cs.SD

ISCSLP 2026 CoT-TTS Challenge: Chain-of-Thought Reasoning for Context-Aware Text-to-Speech

Recent advances in text-to-speech (TTS) have greatly improved speech naturalness, speaker similarity, and controllability. However, most existing controllable TTS systems still rely on explicit user-provided style prompts, making it difficult to automatically determine how a sentence should be spoken in long and complex conversational scenarios. This proposal introduces the ISCSLP 2026 CoT-TTS Challenge, which aims to evaluate whether a system can infer the intended speaking manner from contextual information and generate speech consistent with both the reasoning output and the surrounding scene. The challenge contains two tracks: text-context-aware CoT-TTS and audio-context-aware CoT-TTS. We construct a large-scale bilingual training set from speech-rich media and provide carefully filtered evaluation data for leaderboard comparison. Each system is required to output both a chain-of-thought reasoning analysis and the generated speech waveform. The official evaluation combines objective metrics, multimodal LLM-based evaluation, and human subjective assessment. To facilitate reproducibility, we provide inference code together with a fine-tuning recipe for a 0.6B Qwen3-based model trained via a three-stage strategy. This challenge is expected to support research on context understanding, chain-of-thought reasoning, and expressive speech generation for applications such as film dubbing, audiobook production, virtual characters, and spoken dialogue agents. Further information about the associated challenge is available at:https://iscslp2026-cot-tts.github.io/challenge-website/

Wei Xue, Junlan Feng, Shilei Zhang +9

The Hong Kong University of Science and Technology · China Mobile · Jiutian Artificial Intelligence Technology (Beijing) Co., Ltd., China Mobile +3

TTS Synthesis TTS Evaluation CoT Reasoning Controllable Speech Generation Text-to-Speech

Jun 19, 2026cs.CV

MammoExpert: Benchmarking Chain-of-Thought Reasoning in Mammography Diagnosis

Mammography is an essential tool for breast cancer detection, with millions of examinations conducted annually. However, publicly available high-quality mammography datasets for AI development remain limited in both scale and annotation richness, particularly regarding pathological subtype coverage and structured diagnostic reasoning annotations. In this paper, we present MammoExpert, the first mammography dataset with Chain-of-Thought reasoning annotations across three diagnostic phases: (i) primal observation, (ii) factual assessment, and (iii) diagnostic synthesis. Comprising 2,379 mammography images covering 67 WHO-classified histopathology subtypes, each exam provides 42 radiographic features annotated by nine senior radiologists. We evaluate its performance on the breast lesion classification task, demonstrating superior accuracy and reasonability compared to existing classification models. Combining public dataset CBIS-DDSM with MammoExpert yields 7.1% classification accuracy improvement, while the training model to learn CoT reasoning achieves another 4% gain on the MammoExpert test set. Similar improvements are observed on INBreast and Vindr datasets, where the full approach yields accuracy gains of 6.9% and 6.7%, respectively. MammoExpert can serve as a benchmark for interpretable breast lesion diagnosis through explicit CoT reasoning.

Di Dai, Bo Liu, Youcheng Li +9

State Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University Beijing, China · School of Computer Science and Engineer, Beijing University of Aeronautics and Astronautics Beijing, China · Center for Data Science, Peking University Beijing, China +5

Medical Imaging CoT Reasoning Medical Image Classification Mammography Explainable Medical Image Analysis Medical Image Benchmarks

Jun 18, 2026cs.LG

Efficiently Representing Algorithms With Chain-of-Thought Transformers

The increasing popularity of \emph{reasoning} models -- language models that output a series of reasoning or thought tokens before producing an answer -- is justified, in part, by theoretical results showing that chain-of-thought (CoT) transformers can simulate Turing machines, and thus perform arbitrary computation. However, the Turing machine, while suitable for complexity-theoretic analysis, is not convenient, intuitive, or efficient for discussing algorithms. Algorithms are typically designed and analyzed at a higher level of abstraction, captured by the \emph{Word RAM} model with random-access memory and unit-cost operations on

\bigO(\log n)

-bit words. As a result, Word RAM algorithms can be substantially more efficient than their Turing machine counterparts, raising the question: \emph{Can CoT transformers efficiently simulate Word RAM algorithms?} For instance, can they sort

n

items in

\bigO(n \log n)

steps or run Dijkstra's algorithm in

\bigO(E + V \log V)

steps? We answer affirmatively, up to poly-logarithmic overhead. We first establish this for finite-precision transformers with poly-logarithmic width and rightmost unique hard attention, then strengthen the result to two more practical settings with finite width and log-precision: \emph{continuous} CoT, where reasoning takes the form of vectors rather than tokens, and a \emph{hybrid} architecture in which transformer layers sit atop a recurrent (linear RNN) layer. In all three cases, we find that CoT \emph{can} efficiently simulate any Word RAM algorithm with only a poly-logarithmic overhead in

n

. This overhead reduces to log-square when the Word RAM has a ``flat'' instruction set, and only logarithmic for multiplication-free flat instructions -- in stark contrast to known CoT simulations of Turing machines, which require quadratic overhead over Word RAM.

Yanhong Li, Anej Svete, Ashish Sabharwal +1

Allen Institute for AI · ETH Zürich

Transformer CoT Reasoning Neural Algorithmic Reasoning Efficient Language Model Reasoning Algorithmic Reasoning

Jun 16, 2026cs.CV

Beyond Visual Cues: CoT-Enhanced Reasoning for Semi-supervised Medical Image Segmentation

Semi-supervised medical image segmentation has emerged as a dominant research problem in medical image analysis, mitigating annotation scarcity by leveraging consistency regularization on unlabeled data. However, existing approaches operate predominantly via visual pattern matching, relying heavily on pixel-level similarities. This visual-centric dependency often falters in clinical scenarios characterized by the visual-semantic mismatch, where visually similar lesions warrant distinct diagnostic conclusions, thus failing to capture the underlying diagnostic logic used by experts. To address this, we move beyond visual cues and propose CERS (CoT-Enhanced Reasoning Segmentation), a framework that integrates Chain-of-Thought (CoT) reasoning to distinguish pathologically distinct cases. Specifically, we construct a knowledge pool enriched with linguistic reasoning descriptions generated by large language models (LLMs). A semantic-aware reference selection strategy is introduced to identify historical evidence, filtering candidates first by morphology, and then refining them via CoT consistency to eliminate hard negatives. Furthermore, a multi-scale coordinate attention module (MCAM) is designed to effectively fuse this reasoning-derived context into the decoding process. Extensive experiments demonstrate the superiority of CERS against state-of-the-art approaches, particularly in resolving boundary ambiguities and semantic inconsistencies. The code is available at https://github.com/cymasuna/CERS.

Yuming Chen, Yuxin Xie, Tao Zhou +1

School of Computer Science and Engineering, Southeast University, Nanjing, China · Key Laboratory of New Generation Artiﬁcial Intelligence Technology and Its Interdisciplinary Applications, Ministry of Education, Nanjing, China · Nanjing University of Science and Technology, Nanjing, China

CoT Reasoning Semi-Supervised Medical Image Segmentation Medical Image Segmentation

Jun 15, 2026cs.CL

Robust Dual-Signal Fusion: Hybrid Neuro-Symbolic Gating with Compressed Chain-of-Thought Refinement for Irony Detection in Social Media Texts

Small-scale Large Language Models (LLMs) natively default to literal semantic interpretations, making few-shot irony detection a persistent challenge in noisy, user-generated text. In this study, we show that, despite this limitation, inference from compact LLMs can still be effectively harnessed for this task. We introduce the Robust Dual-Signal (RDS) Fusion framework, a hybrid neuro-symbolic architecture that utilizes a compressed Chain-of-Thought (CoT) of an LLM, alongside a static, pretrained RoBERTa and a symbolic prior module in two downstream fusions. RDS Fusion demonstrates better performance than an unrestricted reasoning ablation, while requiring substantially lower inference time. We also find that in our experiments, unrestricted reasoning does not yield better results than restricted reasoning. Evaluated on a strictly held-out TweetEval test set (

N=734

), RDS Fusion achieves

78.1\%

accuracy and a Macro F1 of

0.777

, which is comparable to a finetuned BERTweet-base. On the heavily imbalanced iSarcasm dataset, the frozen CoT pipeline suppresses

22.5\%

of baseline false positives, yielding a Macro F1 of

0.6726

and Ironic F1 of

0.4821

, outperforming multiple heavily supervised SemEval transformer ensembles. Paired McNemar's tests show that, while adding the symbolic prior to the neural baseline yields an insignificant gain, and the RDS Fusion is statistically insignificant compared to the combined RoBERTa and symbolic prior ablation; the concurrent fusion achieves a statistically significant improvement over the standalone baseline (

p=0.005

).

Ankit Bhattacharjee, Krityapriya Bhaumik

Indian Institute of Technology Kharagpur, India

CoT Reasoning Neuro-Symbolic Reasoning

Jun 14, 2026cs.CL

Free Energy Heuristics: Fast-And-Frugal Cognition as Active Inference Under Uncertain Precision

Chain-of-thought (CoT) improves large language models' performance in math and symbolic reasoning. But on planning, contested ethics, and tasks where the model cannot check itself, more reasoning makes things worse. Both effects are documented; what has been missing is a principled account of which property decides the outcome. We argue it is meta-uncertainty: how unsure the model is about the reliability of its own evidence. When that uncertainty is high, extra reasoning stops adding signal and starts manufacturing false confidence. We prove that the policy minimizing expected free energy under uncertain precision stops integrating cues after a finite number of high-validity ones when the precision prior is heavy-tailed (Theorem 2.6.1), and under a Descending Dominance condition, is sample-wise identical to take-the-best (Theorem 2.7.4). Fast-and-frugal heuristics and active inference are, then, two descriptions of the same computation. The prediction is that on high-meta-uncertainty items, longer CoT should degrade accuracy. We score the regime per item (simulate-and-recover rho > 0.96), build FEH-79, a benchmark of Knightian frames with matched controls, and run a pre-registered study across seven models (five open-weight 3B-32B, two frontier), five CoT lengths, and 7,875 responses. The gate, fixed before any data, required a negative interaction with posterior probability above 0.95 and an accuracy drop of more than 6 points. It held. The high-regime drop is 17.3 points (95% CI [7.7, 25.5]); matched items with definite answers show no cost. The effect is regime-dependent: decisive in capable mid-to-large models, directional in the two frontier systems, absent-to-reversed in the weakest. The framework answers when CoT helps and unifies the Bayesian and fast-and-frugal traditions: less-is-more effects are evidence about the meta-uncertainty regime, not against Bayesian cognition.

Alex Bogdan

Evolutionairy AI Toronto, Canada

Cognitive Modeling Active Inference CoT Reasoning Free Energy Principle Efficient Language Model Reasoning Metacognition in Language Models

Jun 14, 2026cs.CL

ttda704 at SemEval-2026 Task 6: Structured Chain-of-Thought Prompting for Political Evasion Detection

This paper describes our system for SemEval-2026 Task 6, which addresses the classification of political evasion strategies in English question-answer pairs extracted from U.S. presidential interviews. We systematically compare two distinct paradigms: (1) Parameter-Efficient Fine-Tuning of Qwen3 models (4B-32B) using QLoRA, enhanced with tiered upsampling and weighted cross-entropy loss to address severe class imbalance, and (2) structured Chain-of-Thought (CoT) prompting of reasoning-capable API models, namely DeepSeek-V3.2 and Grok-4-Fast. Our evaluation demonstrates that structured CoT prompting of reasoning-enabled models substantially outperforms our baseline parameter-efficient fine-tuning implementation in absolute Macro F1. Our best system, Grok-4-Fast with extended reasoning and few-shot hierarchical CoT prompting, achieves a Macro F1 of 0.5147 on Subtask 2 (9-class evasion) and 0.7979 on Subtask 1 (3-class clarity), ranking 8th out of 33 teams on Subtask 2 and 13th out of 41 teams on Subtask 1 on the official leaderboard. Furthermore, our ablation studies reveal key insights into effective prompt design for evasion detection: presenting labels within a hierarchical taxonomy helps structure model reasoning, while few-shot exemplars provide task calibration. However, the strongest prompt variants are not statistically distinguishable in Macro F1, and explicitly enabling extended reasoning modes yields substantial performance gains by facilitating the multi-step pragmatic analysis required to detect evasive intent.

Tai Tran Tan, An Dinh Thien

University of Information Technology, Ho Chi Minh City, Vietnam · Vietnam National University, Ho Chi Minh City, Vietnam

CoT Reasoning Pragmatic Reasoning in Language Models Few-Shot Prompting Parameter-Efficient Fine-Tuning

Jun 14, 2026cs.AI

RoboPIN: Grounded Embodied Reasoning via Pinned Chain-of-Thought

Embodied reasoning requires models to perceive task-relevant objects and spaces in physical environments and maintain consistent visual grounding throughout multi-step reasoning. However, current vision-language models rely on text-only or coordinate-augmented chain-of-thought, where entity references remain implicit and ambiguous. This may cause the reasoning process to decouple from visual evidence, entity references to drift across steps, and a causal disconnection between the reasoning trajectory and the final answer, with these problems further amplified in multi-view scenarios due to cross-view appearance changes. To address these issues, we propose Pinned Chain-of-Thought (PinCoT), a structured reasoning paradigm that pins every reasoning step to visual evidence. PinCoT introduces the concept of reasoning anchor, which binds each task-relevant entity to a structured visual anchor with entity name, unique identity, view index, and spatial grounding, enabling consistent entity tracking across reasoning steps and views. We build a fully automated data generation pipeline to construct PIN-170K, a high-quality PinCoT-formatted reasoning dataset. We then train RoboPIN through three-stage post-training that progressively injects embodied knowledge, structured reasoning ability, and process-supervised alignment, with rewards that directly constrain both anchor localization and identity consistency during reasoning. On 14 benchmarks covering embodied spatial reasoning, multi-view reasoning, and pointing, RoboPIN with only 4B parameters consistently outperforms 7B level open-source embodied models, achieving a 12% average improvement over the strongest 7B baseline, Mimo-Embodied. Further analysis shows that PinCoT improves grounding accuracy and cross-step identity consistency, validating the effectiveness of process supervision.

Yaoting Huang, Yifu Yuan, Linqi Han +6

1Tianjin University

Visual Spatial Reasoning CoT Reasoning Vision-Language Grounding VLM Reasoning Visually Grounded Reasoning Embodied AI+1

Jun 14, 2026cs.AI

Integrating Reasoning and Generalization in Text-to-SQL via Self-Enhanced Fine-Tuning

Text-to-SQL aims to translate natural language questions into executable SQL queries over structured databases, enabling non-expert users to access data intuitively. While recent advances in large language models (LLMs) have shown promise in this task, existing LLM-based approaches often struggle to strike a balance between strong reasoning capabilities and robust generalization. To address these limitations, we propose CoTE-SQL to enhance the LLM-based text-to-SQL generation with three key innovations: (i) self-enhanced reasoning traces distilled from LLMs without human annotation, (ii) structured chain-of-thought (CoT) prompting with modular decomposition and examples retrieval, and (iii) error-aware revision based on SQL execution feedback. Extensive experiments on the Spider and Bird benchmarks demonstrate that CoTE-SQL achieves new state-of-the-art performance among methods built on open-source LLMs with comparable model sizes on Bird (53.39% EX / 59.02 VES) and strong results on Spider (79.60% EX / 77.19 VES), with especially significant gains on complex queries. Results highlight the effectiveness of combining self-enhancement, structured reasoning, and execution-time feedback within an LLM-based framework for text-to-SQL design.

Feng Lyu, Jinfeng Cen, Sijing Duan +4

Central South University · Tsinghua University · Nanjing University +1

Self-Training for Language Models LLM Fine-Tuning CoT Reasoning Text-to-SQL Language Model Self-Improvement

Jun 12, 2026cs.CL

CoRA: Confidence-Rationale Alignment for Reliable Chain-of-Thought Reasoning

Chain-of-thought (CoT) reasoning can improve LLM performance, but high answer confidence may be misleading when the accompanying CoT rationale is plausible yet incomplete or poorly supported. We study confidence--rationale alignment: whether a model's confidence in its committed answer is justified by its generated rationale. We introduce a GRPO-based reinforcement learning framework that jointly rewards answer correctness, committed-answer probability, and rubric-based rationale support, where the rubric assesses grounding, coherence, task match, and connection to the selected answer without revealing the gold answer to the judge. Across MedQA, MathQA, and OpenBookQA using three open-weight LLMs, our method reduces the confidence--rationale alignment error by up to 26.51% compared with untuned checkpoints, SFT, and correctness-only GRPO, while maintaining competitive accuracy and often improving calibration. These results show that reliable CoT reasoning requires not only confident answers, but rationales that substantively support them.

Juming Xiong, Weixin Liu, Kevin Guo +9

Vanderbilt University · Vanderbilt University Medical Center · Intuit AI Research

CoT Reasoning RL for Language Model Reasoning LLM Reliability LLM Uncertainty Estimation

Jun 9, 2026cs.CL

The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes

Large Language Models (LLMs) have achieved strong performance across natural language processing tasks, yet reliable reasoning remains an open challenge. Although modern LLMs show progress in structured inference, multi-step problem solving, and contextual understanding, their reasoning behavior is often inconsistent and sensitive to prompting strategies, task design, and model scale. This survey provides a systematic analysis of more than 300 recent papers from arXiv, Semantic Scholar, Google Scholar, Papers with Code, and the ACL Anthology to examine how reasoning capabilities emerge in LLMs and where they fail. We make three main contributions. First, we introduce a structured taxonomy of LLM reasoning research, covering Chain-of-Thought reasoning, multi-hop reasoning, mathematical reasoning, common sense reasoning, visual and temporal reasoning, code and algorithmic reasoning, retrieval-augmented reasoning, tool-augmented and agentic reasoning, and reinforcement learning-based reasoning. Second, we analyze methodological trends across these paradigms, including prompting methods, model architectures, training objectives, reward modeling, and evaluation benchmarks. Third, we synthesize recurring limitations and failure modes, such as reasoning hallucinations, brittle multi-step inference, weak causal abstraction, and poor cross-domain generalization. By organizing a rapidly expanding literature, this survey offers a unified view of the current capabilities and limitations of reasoning in LLMs. We also identify emerging research directions, including meta-reasoning, self-evolving reasoning frameworks, multimodal reasoning, and socially grounded reasoning. Overall, this work aims to serve as a reference for developing more robust, interpretable, and generalizable reasoning systems in future language models.

Avinash Anand, Mahisha Ramesh, Avni Mittal +7

SIT × Nvidia AI Center (SNAIC) · MIDAS Lab, IIIT Delhi · MIDAS Lab, IIT Mandi +4

CoT Reasoning RL for Language Model Reasoning Mathematical Reasoning LLM Reasoning

Jun 8, 2026cs.LG

Tight Sample Complexity of Transformers

We tightly characterize the VC dimension of depth-

L

Transformers with a total of

W

parameters, mapping an input sequence of length

T

to a single output, establishing an upper bound of

O(L W \log (T W))

and a nearly matching lower bound of

Ω(L W \log (T W / L))

. We further tightly characterize the sample complexity of chain-of-thought learning using such a Transformer, showing teacher forcing (i.e. selecting a predictor consistent with the entire chain-of-thought on training data) learns with sample complexity

O\left(L W \log \left(\left(T+T^{\prime}\right) W\right)\right)

and that any learning rule that uses chain-of-thought data requires at least

Ω\left(L W \log \left(\left(T+T^{\prime}\right) W / L\right)\right)

examples, where

T

is the input length and

T^{\prime}

is the number of autoregressive steps.

Chenxiao Yang, Nathan Srebro, Zhiyuan Li

Toyota Technological Institute at Chicago (TTIC)

Transformer Expressivity Transformer Sample Complexity CoT Reasoning

Jun 8, 2026cs.CL

IS-CoT: Breaking the Long-form Generation Collapse via Interleaved Structural Thinking

Generating coherent and controllable long-form content remains a persistent challenge for Large Language Models (LLMs). While reasoning-enhanced models have demonstrated success in logic-intensive domains, our evaluation reveals that they suffer from a severe length collapse in open-ended writing, where performance degrades sharply as target lengths exceed 2,000 words. We attribute this failure to the limitation of static hierarchical planning, which struggles to provide dynamic guidance over extended contexts. To bridge this gap, we introduce the Interleaved Structural Chain-of-Thought (IS-CoT) framework. Unlike external agentic workflows, IS-CoT embeds a dynamic Plan-Write-Reflect cycle into the generation process, enabling continuous strategy adaptation and global alignment without additional assistance. Based on this framework, we construct a high-quality dataset of interleaved reasoning traces via a multi-teacher pipeline and train IS-Writer-8B. Experiments demonstrate that IS-Writer-8B achieves state-of-the-art performance on challenging long-form benchmarks (e.g., +3.08 vs. DeepSeek-V3.2 on LongBench-Write), exhibiting robust length compliance and coherence competitive with significantly larger proprietary models.

Zechen Sun, Yuyang Sun, Zecheng Tang +6

Institute of Computer Science and Technology, Soochow University · 2Information Research Center of Military Science, PLA Academy of Military Science

Open-Ended Generation Long-Form Document Generation CoT Reasoning LLM Training Text Generation

Jun 7, 2026cs.CR

Sample-Efficient LLM-Based Detection of Malicious Web Server Logs with Forensically Explainable Reasoning

Forensic analysis of web server logs demands both accurate detection and human-readable explanations that can satisfy legal requirements. We present CEF-Log, a context-enhanced few-shot chain-of-thought prompting strategy for Large Language Models that addresses this dual requirement. CEF-Log embeds expert investigative methodology through a structured five-step reasoning template, enabling the model to learn \textit{how} to analyze logs rather than \textit{what} patterns to memorize. Experimental evaluation demonstrates that CEF-Log achieves an F1-score of 0.99 on the CSIC 2010 dataset using only four examples while providing a

10\times

improvement in sample efficiency compared to other prompting-based methods. We also introduce ForenWebLog, a new dataset that incorporates real-world attacks and multi-step attack sequences for comprehensive evaluation. Qualitative analysis confirms that CEF-Log generates traceable, accurate explanations suitable for forensic documentation, addressing the critical "black-box" limitation of traditional machine learning approaches.

Bernhard Kneip, Nhien-An Le-Khac, Hong-Hanh Nguyen-Le

Explainable Artificial Intelligence CoT Reasoning Digital Forensics Few-Shot Prompting Anomaly Detection