arXiv:2609.12265v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly asked to reason over structured data such as graphs, yet how reliably they can carry out multi-step graph algorithms in language remains unclear. Existing evaluations tend to use simple tasks on small graphs, to score code generation rather than reasoning over the graph itself, or to fix a single input format. We introduce Graph Theory Bench (GT Bench), a benchmark covering 24 classical graph problems in 44 task-structure settings, with over 100,000 examples across four representations: natural language, structured language, adjacency list, and adjacency matrix. Evaluating eight LLMs on GT Bench shows that accuracy is strongly tied to the input representation, that the best representation shifts with graph density, size, and topology as well as with the model, and that this sensitivity persists, attenuated, in the strongest reasoning models. Building on these observations, we propose the Graph Theory Agent (GTA), which pairs a preference-trained representation selector with plan-and-decompose scaffolding around a frozen executor LLM. GTA lifts Phi-4 from 53.5% to 69.1% on the benchmark's easy split and from 33.0% to 41.5% on its hard split, outperforming eight prompting and agent baselines, and transfers without retraining to GraCoRe and NLGraph. Code for benchmark generation and evaluation: https://github.com/xzx34/GTA. The project homepage is available at https://xzx34.github.io/gta/.

arXiv:2609.12851v1 Announce Type: new Abstract: Medical benchmarks are dominated by single-turn, multiple-choice clinical cases that poorly reflect real consultations. Practically, clinicians elicit evidence interactively and patient communication varies widely. We introduce MedRoundsQA, a multi-turn diagnostic benchmark derived from 1,387 board-exam cases across 17 specialties. Each case is converted into a structured 24-slot clinical record, and then instantiated as controlled doctor-patient dual-agent dialogues under varying patient personas, with the underlying clinical content held fixed. We further classify cases by difficulty using model-based uncertainty to enable easy-to-hard analysis. Evaluations of fifteen LLM doctor agents show that (i) moving from a single-turn diagnosis on the standardized records to multi-turn consultations causes large degradations of roughly 13-39 points; (ii) more turns reliably improves question relevance, but diagnostic accuracy exhibits diminishing returns and typically plateaus after 6-12 turns; and (iii) patient persona differences can shift diagnosis accuracy by about 7-8 points (lowest to highest education), highlighting equity risks that single-turn benchmarks miss.

arXiv:2605.24636v2 Announce Type: new Abstract: While large language models (LLMs) hold transformative potential for medicine, their reasoning robustness and safety in real-world clinical scenarios remain critically underexplored, particularly in dentistry. Here we introduce GlobalDentBench, the first multinational dental benchmark, featuring a taxonomy that encompasses 14 dental specialties across 88 countries and regions spanning six continents. The benchmark comprises 8,978 expert-validated questions across three formats (multiple-choice, short-answer, and case-based questions) and assesses three progressive reasoning levels: knowledge recall (L1), routine reasoning (L2), and individualized reasoning (L3). To ensure data quality, the automated construction framework was calibrated by six senior dentists, achieving expert agreement rates of 99.98% for multiple-choice and short-answer questions and 96.78% for the more complex case-based questions. Evaluation of 12 frontier LLMs on GlobalDentBench revealed a sharp, stepwise performance degradation with increasing reasoning complexity. Specifically, accuracy plummeted from 81.34% on multiple-choice to 64.53% on short-answer and 22.34% on case-based questions, while declining markedly from 74.01% at L1 to 55.64% at L2 and 35.71% at L3. More critically, risk analysis of real-world dental cases demonstrated an alarming overall unsafe rate of 31.01% in LLM-generated clinical recommendations, with 4.51% posing risks of irreversible patient harm and risks particularly pronounced in specialties such as orthodontics. These findings expose fundamental limitations in the medical reasoning and safety of current LLMs. Consequently, GlobalDentBench provides a scalable foundation for trustworthy clinical AI evaluation, underscoring the urgent need for rigorous validation before the safe deployment of these models in healthcare.

arXiv:2605.25861v2 Announce Type: cross Abstract: 3D human mesh recovery and 3D clothed human reconstruction are inherently related, yet they have long been studied in isolation, thereby overlooking the potential gains of joint optimization. To overcome this limitation, we propose to address these two tasks within a unified framework, which allows their mutual dependencies to be effectively exploited. Building on this idea, we propose MuNet, a mutualistic network for joint 3D human mesh recovery and 3D clothed human reconstruction from single images. First, we adopt 2-manifold graphs as a unified representation for all 3D models, enabling consistent modeling across 3D human mesh recovery and clothed human reconstruction. Second, we design an end-to-end graph convolutional network that progressively deforms an initial graph into a 3D human mesh and refines it into a detailed 3D clothed human model. Third, we introduce a mutualistic mechanism that allows reciprocal interaction between the two tasks {during training}, where 3D human mesh recovery provides guidance for 3D clothed human reconstruction, and reconstruction feedback refines the 3D human mesh recovery. We extensively evaluate MuNet on six benchmark datasets for 3D human mesh recovery and 3D clothed human reconstruction, including Human3.6M, 3DPW, MPI-INF-3DHP, THuman2.0, CAPE, and RenderPeople. Experimental results demonstrate that MuNet achieves state-of-the-art performance on both tasks across all datasets. The code of MuNet is released for research purposes at https://github.com/starVisionTeam/MuNet.

arXiv:2604.01988v1 Announce Type: new Abstract: Large language models often default to step-by-step computation even when efficient numerical shortcuts are available. This raises a basic question: do they exhibit number sense in a human-like behavioral sense, i.e., the ability to recognize numerical structure, apply shortcuts when appropriate, and avoid them when they are not? We introduce SenseMath, a controlled benchmark for evaluating structure-sensitive numerical reasoning in LLMs. SenseMath contains 4,800 items spanning eight shortcut categories and four digit scales, with matched strong-shortcut, weak-shortcut, and control variants. It supports three evaluation settings of increasing cognitive demand: Shortcut Use (whether models can apply shortcuts on shortcut-amenable problems); Applicability Judgment (whether they can recognize when a shortcut is appropriate or misleading); and Problem Generation (whether they can generate new problem items that correctly admit a given type of shortcut). Our evaluation across five LLMs, ranging from GPT-4o-mini to Llama-3.1-8B, shows a consistent pattern: when explicitly prompted, models readily adopt shortcut strategies and achieve substantial accuracy gains on shortcut-amenable items (up to 15%), yet under standard chain-of-thought prompting they spontaneously employ such strategies in fewer than 40% of cases, even when they demonstrably possess the requisite capability. Moreover, this competence is confined to the Use level; models systematically over-generalise shortcuts to problems where they do not apply, and fail to generate valid shortcut-bearing problems from scratch. Together, these results suggest that current LLMs exhibit procedural shortcut fluency without the structural understanding of when and why shortcuts work that underlies human number sense.

arXiv:2604.02296v1 Announce Type: cross Abstract: Existing video object removal methods excel at inpainting content "behind" the object and correcting appearance-level artifacts such as shadows and reflections. However, when the removed object has more significant interactions, such as collisions with other objects, current models fail to correct them and produce implausible results. We present VOID, a video object removal framework designed to perform physically-plausible inpainting in these complex scenarios. To train the model, we generate a new paired dataset of counterfactual object removals using Kubric and HUMOTO, where removing an object requires altering downstream physical interactions. During inference, a vision-language model identifies regions of the scene affected by the removed object. These regions are then used to guide a video diffusion model that generates physically consistent counterfactual outcomes. Experiments on both synthetic and real data show that our approach better preserves consistent scene dynamics after object removal compared to prior video object removal methods. We hope this framework sheds light on how to make video editing models better simulators of the world through high-level causal reasoning.

arXiv:2603.29386v1 Announce Type: cross Abstract: The rapid democratization of prompt-based AI image editing has recently exacerbated the risks associated with malicious content fabrication and misinformation. However, forgery localization methods targeting these emerging editing techniques remain significantly under-explored. To bridge this gap, we first introduce a fully automated mask annotating framework that leverages keypoint alignment and semantic space similarity to generate precise ground-truth masks for edited regions. Based on this framework, we construct PromptForge-350k, a large-scale forgery localization dataset covering four state-of-the-art prompt-based AI image editing models, thereby mitigating the data scarcity in this domain. Furthermore, we propose ICL-Net, an effective forgery localization network featuring a triple-stream backbone and intra-image contrastive learning. This design enables the model to capture highly robust and generalizable forensic features. Extensive experiments demonstrate that our method achieves an IoU of 62.5% on PromptForge-350k, outperforming SOTA methods by 5.1%. Additionally, it exhibits strong robustness against common degradations with an IoU drop of less than 1%, and shows promising generalization capabilities on unseen editing models, achieving an average IoU of 41.5%.

arXiv:2412.00547v4 Announce Type: replace-cross Abstract: Recent advances in video generation have shown promise for generating future scenarios, critical for planning and control in autonomous driving and embodied intelligence. However, real-world applications demand more than visually plausible predictions; they require reasoning about object motions based on explicitly defined boundary conditions, such as initial scene image and partial object motion. We term this capability Boundary Conditional Motion Reasoning. Current approaches either neglect explicit user-defined motion constraints, producing physically inconsistent motions, or conversely demand complete motion inputs, which are rarely available in practice. Here we introduce Motion Dreamer, a two-stage framework that explicitly separates motion reasoning from visual synthesis, addressing these limitations. Our approach introduces instance flow, a sparse-to-dense motion representation enabling effective integration of partial user-defined motions, and the motion inpainting strategy to robustly enable reasoning motions of other objects. Extensive experiments demonstrate that Motion Dreamer significantly outperforms existing methods, achieving superior motion plausibility and visual realism, thus bridging the gap towards practical boundary conditional motion reasoning. Our webpage is available: https://envision-research.github.io/MotionDreamer/.

arXiv:2603.06648v1 Announce Type: cross Abstract: Recent advances in multimodal large language models (MLLMs) offer a promising approach for natural language-based scene change queries in virtual reality (VR). Prior work on applying MLLMs for object state understanding has focused on egocentric videos that capture the camera wearer's interactions with objects. However, object state changes may occur in the background without direct user interaction, lacking explicit motion cues and making them difficult to detect. Moreover, no benchmark exists for evaluating this challenging scenario. To address these challenges, we introduce ObjChangeVR-Dataset, specifically for benchmarking the question-answering task of object state change. We also propose ObjChangeVR, a framework that combines viewpoint-aware and temporal-based retrieval to identify relevant frames, along with cross-view reasoning that reconciles inconsistent evidence from multiple viewpoints. Extensive experiments demonstrate that ObjChangeVR significantly outperforms baseline approaches across multiple MLLMs.

arXiv:2508.03346v2 Announce Type: replace Abstract: Large Language Models (LLMs) using Chain-of-Thought (CoT) prompting excel at complex reasoning but generate verbose thought processes with considerable redundancy, leading to increased inference costs and reduced efficiency. We introduce a novel CoT compression framework based on step entropy, a metric that quantifies \emph{the informational contribution of individual reasoning steps} to identify redundancy. Through theoretical analysis and extensive empirical validation on mathematical reasoning benchmarks, we demonstrate that steps with low entropy are indeed highly redundant. Our experiments reveal that an astonishing 80\% of low-entropy intermediate steps can be pruned with minor degradation in the final answer accuracy across DeepSeek-R1-7B, 14B and Qwen3-8B. This finding sharply contrasts with random or high-entropy pruning, which severely impairs reasoning performance. Building on this, we propose a novel two-stage training strategy combining Supervised Fine-Tuning (SFT) and Group Relative Policy Optimization (GRPO) reinforcement learning. This approach enables LLMs to autonomously learn to generate compressed COTs during inference by strategically incorporating [SKIP] tokens. Our method significantly improves LLM inference efficiency while preserving accuracy, paving the way for more scalable LLM deployments and a better understanding of their internal reasoning. The code and data are released in https://github.com/staymylove/COT_Compresstion_via_Step_entropy.