The effectiveness of Large Language Models (LLMs) is heavily influenced by the reasoning strategies, or styles of thought, employed in their prompts. However, the interplay between these reasoning styles, model architecture, and task type remains poorly understood. To address this, we introduce StyleBench, a comprehensive benchmark for systematically evaluating reasoning styles across diverse tasks and models. We assess five representative reasoning styles--Chain-of-Thought (CoT), Tree-of-Thought (ToT), Algorithm-of-Thought (AoT), Sketch-of-Thought (SoT), and Chain-of-Draft (CoD)--on five reasoning tasks, using 15 open-source models from major families (LLaMA, Qwen, Mistral, Gemma, GPT -OSS, Phi, and DeepSeek) ranging from 270M to 120B parameters. Our large-scale analysis reveals that no single style is universally optimal. We demonstrate that strategy efficacy is highly contingent on both model scale and task type: search-based methods (AoT, ToT) excel in open-ended problems but require large-scale models, while concise styles (SoT, CoD) achieve radical efficiency gains on well-defined tasks. Furthermore, we identify key behavioral patterns: smaller models frequently fail to follow output instructions and default to guessing, while reasoning robustness emerges as a function of scale. Our findings offer a crucial roadmap for selecting optimal reasoning strategies based on specific constraints, We open source the benchmark in https://github.com/JamesJunyuGuo/Style_Bench. Large Language Models (LLMs) have demonstrated impressive capabilities across a diverse range of tasks, including mathematical reasoning, code generation, and complex question answering (Imani et al., 2023; Wang & Chen, 2023; Tan et al., 2023). A key insight from prior work is that their performance on challenging problems is not merely a function of scale, but is critically dependent on the methods used to guide reasoning (Huang & Y ang, 2025). This has spurred the development of sophisticated prompting techniques designed to structure the model's internal reasoning process. Notable among these are Chain-of-Thought (CoT) (Wei et al., 2022), which decomposes problems into sequential steps, and more advanced paradigms like Tree-of-Thought (ToT) (Y ao et al., 2023), which explores multiple reasoning paths in parallel, and Rea-sonflux (Y ang et al., 2025b), employing high-level templates to explore potential solutions. Performance remains highly sensitive to prompt phrasing and frequently necessitates iterative feedback to achieve robust results (Sel et al., 2023). In response, recent work has sought to automate reasoning strategy selection.

Recent advances in generalist robot manipulation leverage pre-trained Vision-Language Models (VLMs) and large-scale robot demonstrations to tackle diverse tasks in a zero-shot manner. A key challenge remains: scaling high-quality, action-labeled robot demonstration data, which existing methods rely on for robustness and generalization. To address this, we propose a method that benefits from videos without action labels - featuring humans and/or robots in action - enhancing open-vocabulary performance and enabling data-efficient learning of new tasks. Our method extracts dense, dynamic 3D point clouds at the hand or gripper location and uses a proposed 3D dynamics predictor for self-supervision. This predictor is then tuned to an action predictor using a smaller labeled dataset for action alignment. We show that our method not only learns from unlabeled human and robot demonstrations - improving downstream generalist robot policies - but also enables robots to learn new tasks without action labels (i.e., out-of-action generalization) in both real-world and simulated settings.

Medical imaging provides critical evidence for clinical diagnosis, treatment planning, and surgical decisions, yet most existing imaging models are narrowly focused and require multiple specialized networks, limiting their generalization. Although large-scale language and multimodal models exhibit strong reasoning and multi-task capabilities, real-world clinical applications demand precise visual grounding, multimodal integration, and chain-of-thought reasoning. We introduce Citrus-V, a multimodal medical foundation model that combines image analysis with textual reasoning. The model integrates detection, segmentation, and multimodal chain-of-thought reasoning, enabling pixel-level lesion localization, structured report generation, and physician-like diagnostic inference in a single framework. We propose a novel multimodal training approach and release a curated open-source data suite covering reasoning, detection, segmentation, and document understanding tasks. Evaluations demonstrate that Citrus-V outperforms existing open-source medical models and expert-level imaging systems across multiple benchmarks, delivering a unified pipeline from visual grounding to clinical reasoning and supporting precise lesion quantification, automated reporting, and reliable second opinions.

Mathematical reasoning poses significant challenges for Large Language Models (LLMs) due to its demand for multi-step reasoning and abstract conceptual integration. While recent test-time scaling techniques rely heavily on high-quality, challenging problems, the scarcity of Olympiad-level math problems remains a bottleneck. We introduce CogAtom, a novel cognitive atom-based framework for synthesizing mathematically rigorous and cognitively diverse problems. Unlike prior approaches, CogAtom models problem construction as a process of selecting and recombining fundamental reasoning units, cognitive atoms, extracted from human-authored solutions. A diversity-promoting random walk algorithm enables exploration of the cognitive atom space, while a constraint-based recombination mechanism ensures logical soundness and structural validity. The combinatorial nature of the graph structure provides a near-infinite space of reasoning paths, and the walk algorithm systematically explores this space to achieve large-scale synthesis of high-quality problems; meanwhile, by controlling the number of cognitive atoms, we can precisely adjust problem difficulty, ensuring diversity, scalability, and controllability of the generated problems. Experimental results demonstrate that CogAtom outperforms existing methods in accuracy, reasoning depth, and diversity, generating problems that closely match the difficulty of AIME while exceeding it in structural variation. Our work offers a cognitively grounded pathway toward scalable, high-quality math problem generation.Our code is publicly available at https://github.com/Icarus-1111/CogAtom.

Breast ultrasound (BUS) is an essential tool for diagnosing breast lesions, with millions of examinations per year. However, publicly available high-quality BUS benchmarks for AI development are limited in data scale and annotation richness. In this work, we present BUS-CoT, a BUS dataset for chain-of-thought (CoT) reasoning analysis, which contains 11,439 images of 10,019 lesions from 4,838 patients and covers all 99 histopathology types. To facilitate research on incentivizing CoT reasoning, we construct the reasoning processes based on observation, feature, diagnosis and pathology labels, annotated and verified by experienced experts. Moreover, by covering lesions of all histopathology types, we aim to facilitate robust AI systems in rare cases, which can be error-prone in clinical practice.

This is the third paper of the CayleyPy project applying artificial intelligence to problems in group theory. We announce the first public release of CayleyPy, an open source Python library for computations with Cayley and Schreier graphs. Compared with systems such as GAP and Sage, CayleyPy handles much larger graphs and performs several orders of magnitude faster. Using CayleyPy we obtained about 200 new conjectures on Cayley and Schreier graphs, focused on diameters and growth. For many Cayley graphs of symmetric groups Sn we observe quasi polynomial diameter formulas: a small set of quadratic or linear polynomials indexed by n mod s. We conjecture that this is a general phenomenon, giving efficient diameter computation despite the problem being NP hard. We propose a refinement of the Babai type conjecture on diameters of Sn: n^2/2 + 4n upper bounds in the undirected case, compared to previous O(n^2) bounds. We also provide explicit generator families, related to involutions in a square with whiskers pattern, conjectured to maximize the diameter; search confirms this for all n up to 15. We further conjecture an answer to a question posed by V M Glushkov in 1968 on directed Cayley graphs generated by a cyclic shift and a transposition. For nilpotent groups we conjecture an improvement of J S Ellenberg's results on upper unitriangular matrices over Z/pZ, showing linear dependence of diameter on p. Moreover. Some conjectures are LLM friendly, naturally stated as sorting problems verifiable by algorithms or Python code. To benchmark path finding we created more than 10 Kaggle datasets. CayleyPy works with arbitrary permutation or matrix groups and includes over 100 predefined generators. Our growth computation code outperforms GAP and Sage up to 1000 times in speed and size.

Robotic manipulation policies are commonly initialized through imitation learning, but their performance is limited by the scarcity and narrow coverage of expert data. Reinforcement learning can refine polices to alleviate this limitation, yet real-robot training is costly and unsafe, while training in simulators suffers from the sim-to-real gap. Recent advances in generative models have demonstrated remarkable capabilities in real-world simulation, with diffusion models in particular excelling at generation. This raises the question of how diffusion model-based world models can be combined to enhance pre-trained policies in robotic manipulation. In this work, we propose World4RL, a framework that employs diffusion-based world models as high-fidelity simulators to refine pre-trained policies entirely in imagined environments for robotic manipulation. Unlike prior works that primarily employ world models for planning, our framework enables direct end-to-end policy optimization. World4RL is designed around two principles: pre-training a diffusion world model that captures diverse dynamics on multi-task datasets and refining policies entirely within a frozen world model to avoid online real-world interactions. We further design a two-hot action encoding scheme tailored for robotic manipulation and adopt diffusion backbones to improve modeling fidelity. Extensive simulation and real-world experiments demonstrate that World4RL provides high-fidelity environment modeling and enables consistent policy refinement, yielding significantly higher success rates compared to imitation learning and other baselines. More visualization results are available at https://world4rl.github.io/.

While large audio language models excel at tasks like ASR and emotion recognition, they still struggle with complex reasoning due to the modality gap between audio and text as well as the lack of structured intermediate supervision. To address this, we propose a unified knowledge distillation framework to transfer reasoning capabilities from a high-capacity textual teacher model to a student audio models while preserving its acoustic competence. Our method introduces two key dimensions: source-wise distillation, which leverages both textual and acoustic teachers to provide complementary modality-specific supervision; and layer-wise distillation, which aligns teacher signals with appropriate student layers to improve transfer efficiency. This dual-dimensional strategy enables fine-grained control over the distillation process, effectively bridging the gap between symbolic reasoning and speech representations. Experimental results show significant improvements in audio reasoning performance, demonstrating the effectiveness of our framework as a reasoning transfer solution for audio modeling.

Large language models (LLMs) show promise for diagnostic reasoning but often lack reliable, knowledge grounded inference. Knowledge graphs (KGs), such as the Unified Medical Language System (UMLS), offer structured biomedical knowledge that can support trustworthy reasoning. Prior approaches typically integrate KGs via retrieval augmented generation or fine tuning, inserting KG content into prompts rather than enabling structured reasoning. We explore an alternative paradigm: treating the LLM as a reward model of KG reasoning paths, where the model learns to judge whether a candidate path leads to correct diagnosis for a given patient input. This approach is inspired by recent work that leverages reward training to enhance model reasoning abilities, and grounded in computational theory, which suggests that verifying a solution is often easier than generating one from scratch. It also parallels physicians' diagnostic assessment, where they judge which sequences of findings and intermediate conditions most plausibly support a diagnosis. We first systematically evaluate five task formulation for knowledge path judging and eight training paradigm. Second, we test whether the path judging abilities generalize to downstream diagnostic tasks, including diagnosis summarization and medical question answering. Experiments with three open source instruct-tuned LLMs reveal both promise and brittleness: while specific reward optimization and distillation lead to strong path-judging performance, the transferability to downstream tasks remain weak. Our finding provides the first systematic assessment of "reward model style" reasoning over clinical KGs, offering insights into how structured, reward-based supervision influences diagnostic reasoning in GenAI systems for healthcare.

In this paper, we present the Scrapbook framework, a novel methodology designed to generate extensive datasets for probing the learned concepts of artificial intelligence (AI) models. The framework focuses on fundamental concepts such as object recognition, absolute and relative positions, and attribute identification. By generating datasets with a large number of questions about individual concepts and a wide linguistic variation, the Scrapbook framework aims to validate the model's understanding of these basic elements before tackling more complex tasks. Our experimental findings reveal that, while contemporary models demonstrate proficiency in recognizing and enumerating objects, they encounter challenges in comprehending positional information and addressing inquiries with additional constraints. Specifically, the MobileVLM-V2 model showed significant answer disagreements and plausible wrong answers, while other models exhibited a bias toward affirmative answers and struggled with questions involving geometric shapes and positional information, indicating areas for improvement in understanding and consistency. The proposed framework offers a valuable instrument for generating diverse and comprehensive datasets, which can be utilized to systematically assess and enhance the performance of AI models.