Reinforcement learning (RL) is credited with teaching reasoning models to write {wait} before reconsidering a step, yet …

Spatial reasoning remains a persistent weakness of vision-language models (VLMs), because RGB inputs do not directly pro…

Video-language models commonly assume that more temporal observations lead to more reliable reasoning. We question this …

Skeleton-based reasoning prompting is a promising training-free approach for structuring LLM reasoning, but prior work l…

Large language models (LLMs) are increasingly relied upon to support ambient documentation and clinical reasoning. Here …

Reasoning traces improve large language models (LLMs), but current models are trained to reason mostly in English. It ha…

Biological reasoning models use post-training to connect LLMs to biological foundation model representations and biologi…

Vision-Language Models (VLMs) have shown strong multimodal reasoning capabilities, yet whether they truly capture the ph…

While Large Language Models (LLMs) advertise million-token context windows, reasoning quality often collapses as inputs …

Long-horizon reasoning remains a central challenge for large language models (LLMs) under sparse-reward regimes. We argu…

Compositional 3D scene reconstruction has recently been explored from two directions: agentic reasoning that provides se…

Spatial reasoning is essential for vision-language models (VLMs) to understand and act in the physical world. Reasoning …

Large Reasoning Models (LRMs) achieve strong performance on complex tasks but exhibit systematic inefficiency: they ofte…

LLM assistants are widely used for daily social advice, yet evaluating their social reasoning in such consultation setti…

A core goal of efficient reasoning is to improve the accuracy-efficiency frontier. However, jointly improving reasoning …

Specialist distillation effectively transfers domain expertise to student models via teacher-generated reasoning traject…

Reasoning language models have made substantial advances on a variety of complex tasks, yet their capabilities remain ov…

Reinforcement Learning with Verifiable Rewards (RLVR) has been central to the recent success of Large Reasoning Models. …

Chain-of-Thought (CoT) improves the reasoning ability of Large Language Models (LLMs) but incurs substantial computation…

Large language models (LLMs) are often post-trained on pre-collected reasoning trajectories to improve their reasoning c…

Latent visual reasoning aims to perform multimodal reasoning through hidden-state computation rather than explicit textu…

Reasoning in large language models unfolds through diverse functional operations, such as problem formulation, goal deco…

Large Reasoning Models (LRMs) achieve superior problem-solving through extended Chain-of-Thought (CoT) generation, but t…

A reasoning model can improve from its own on-policy experience, but this inner loop is fragile: terminal verifiers prov…

Tool-using voice agents often leave users waiting after speech ends, even when actionable information arrives earlier in…

Chemical chain-of-thought can contain hallucinated structural and property claims. We thereby introduce MolLean, a proce…

Drag-based image editing provides an intuitive interface for spatially controlled image manipulation by allowing users t…

!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…

Real-world embodied tasks, from everyday activities to professional procedures, require agents to act under physical con…

Foundation models can serve as clinical agents through tool-use harnesses. However, conventional medical benchmarks asse…

We study on-policy distillation (OPD) through the lens of reinforcement learning, establishing a connection between the …

Reliable confidence estimation is increasingly central to the trustworthy deployment of language models: a calibrated es…

Masked diffusion language models (dLLMs) generate text by iteratively denoising masked tokens with bidirectional attenti…

Can financial vision-language models (VLMs) turn chart evidence into reliable action recommendations? Existing hallucina…

A central tenet of human cognition is systematicity, the principle that understanding one concept is inherently tied to …

Grounding natural-language instructions into reliable and executable actions remains a fundamental challenge for vision-…

Autonomous agent systems increasingly depend on reusable skill abstractions for consolidating experiential knowledge and…

Despite the remarkable prowess of Vision-Language Models (VLMs) in general multimodal tasks, they remain fundamentally `…

Multimodal entity linking grounds entity mentions in text and images to knowledge-base entries. These systems degrade on…

Representing a 3D scene as multi-view images allows 2D VLMs to reason in 3D by reusing priors from pre-training, sideste…

Invasive coronary angiography (CAG) is the gold standard for diagnosing coronary artery disease, but interpretation vari…

Recent advances in wearable sensing enable continuous monitoring of physiological and behavioral signals, yet existing b…

Visual fluency in generated video does not imply physical reliability, and a scalar quality score alone is incapable of …

该论文提出跨领域基准 RuleTrek，通过结构化规则图与增量组合子场景的构建流程，评估智能体在信息分散于多文件场景中的规则识别与应用能力。

论文从电路复杂度角度证明：在温和的正则性条件下，标准流匹配采样器的轨迹可被常数轮并行模型评估模拟，因此单纯增加采样步数无法提升固定深度骨干模型的表达能力，并提出自条件化以实现深度串行推理。

Multimodal language models (MLLMs) exhibit promising spatial reasoning capabilities, yet the internal mechanisms support…

Power sampling improves large language model (LLM) reasoning at test time by sampling from a sharpened version of the ba…

Multimodal large language models (MLLMs) are rapidly evolving toward continuous audio--visual reasoning, creating an urg…

On-policy distillation (OPD) strengthens language-model reasoning, yet whether students acquire new factual knowledge or…

On-policy reinforcement learning has become a central paradigm for improving the reasoning abilities of large language m…