Search: “reasoning”

arXiv:2604.03701v2 Announce Type: replace Abstract: Video-based numerical reasoning provides a premier arena for testing whether Vision-Language Models (VLMs) truly 'understand' real-world dynamics, a

arXiv:2605.08011v1 Announce Type: new Abstract: Recent efforts to improve the reasoning abilities of Large Language Models (LLMs) have focused on integrating formal logic solvers within neurosymbolic

arXiv:2602.20338v2 Announce Type: replace Abstract: Chain-of-Thought (CoT) prompting significantly improves reasoning in Large Language Models, yet the temporal dynamics of the underlying representati

arXiv:2605.06671v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated strong potential for many mathematical problems. However, their performance on graph algorithmic tasks is

arXiv:2603.01586v3 Announce Type: replace Abstract: Emerging unified editing models have demonstrated strong capabilities in general object editing tasks. However, it remains a significant challenge t

arXiv:2605.07315v1 Announce Type: new Abstract: Chain-of-thought (CoT) reasoning improves large language models (LLMs) on difficult tasks, but it also makes inference expensive because every intermedi

arXiv:2602.05359v2 Announce Type: replace Abstract: The advancement of multimodal large language models (MLLMs) has enabled impressive perception capabilities. However, their reasoning process often r

arXiv:2605.06758v1 Announce Type: cross Abstract: Relative spatial relations provide a compact representation of spatial structure and are fundamental to relative spatial reasoning in 3D layout genera

arXiv:2605.07334v1 Announce Type: new Abstract: Video Reasoning Segmentation (VRS) aims to segment target objects in videos based on implicit instructions that convey human intent and temporal logic.

arXiv:2605.07139v1 Announce Type: cross Abstract: When distilling reasoning from large language models (LLMs) into smaller ones, teacher rationales for similar problems often vary wildly in structure

arXiv:2605.07339v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities in orchestrating tools for reasoning tasks. However, existing methods rely on a s

arXiv:2605.08070v1 Announce Type: new Abstract: A standard technique for scaling inference-time reasoning is Self-Consistency, whereby multiple candidate answers are sampled from an LLM and the most c

Introducing GPT-Realtime-2 in the API: our most intelligent voice model yet, bringing GPT-5-class reasoning to voice agents. Voice agents are now real-time collaborators that can listen, reason, and s

arXiv:2605.03361v2 Announce Type: new Abstract: As multimodal content continues to expand at a rapid pace, audio retrieval has emerged as a key enabling technology for media search, content organizati

arXiv:2603.10384v2 Announce Type: replace Abstract: Evaluating LLM reliability via scalar probabilities often fails to capture the structural dynamics of reasoning. We introduce TRACED, a framework th

arXiv:2605.02910v1 Announce Type: cross Abstract: Recent advances in large language models have led to strong performance on reasoning and environment-interaction tasks, yet their ability for creative

arXiv:2605.03050v1 Announce Type: new Abstract: Millions of users turn to AI models for their information needs. It is conceivable that a large number of user queries contain assumptions that may be f

arXiv:2601.04809v5 Announce Type: replace Abstract: Reinforcement learning (RL) offers a principled way to enhance the reasoning capabilities of large language models, yet its effectiveness hinges on

Today we're releasing ZAYA1-8B, a reasoning MoE trained on @AMD and optimized for intelligence density. With <1B active params, it outperforms open-weight models many times its size on math and reason

arXiv:2605.01657v1 Announce Type: new Abstract: Vision-Language Models (VLMs) typically rely on static initial frames for video reasoning, restricting their ability to incorporate essential dynamic in

arXiv:2605.01324v1 Announce Type: new Abstract: Although reinforcement learning (RL) has significantly advanced reasoning capabilities in large multimodal language models (MLLMs), its efficacy remains

arXiv:2510.09883v2 Announce Type: replace Abstract: Large reasoning models (LRMs) achieve state-of-the-art performance on challenging benchmarks by generating long chains of intermediate steps, but th

arXiv:2601.17467v2 Announce Type: replace Abstract: Large reasoning models (LRMs) often generate long, seemingly coherent reasoning traces yet still produce incorrect answers, making hallucination det

arXiv:2605.01489v1 Announce Type: cross Abstract: Frontier scientific reasoning is rapidly emerging as a key foundation for advancing AI agents in automated scientific discovery. Deep research agents

arXiv:2605.01939v1 Announce Type: new Abstract: Static benchmarks for LLMs are increasingly compromised by contamination and overfitting especially on knowledge intensive reasoning tasks While recent

arXiv:2605.01111v1 Announce Type: cross Abstract: In this work, we introduce DUET (Dual-model Efficient Two-stage inference), a collaborative inference framework in which a capable model and a lightwe

arXiv:2504.10368v4 Announce Type: replace Abstract: This paper explores the system 1 thinking capability of Large Reasoning Models (LRMs), the intuitive ability to respond efficiently with minimal tok

arXiv:2508.07630v2 Announce Type: replace Abstract: We introduce InterChart, a diagnostic benchmark that evaluates how well vision-language models (VLMs) reason across multiple related charts, a task

arXiv:2510.26020v2 Announce Type: replace Abstract: Multi-tool-integrated reasoning enables LLM-empowered tool-use agents to solve complex tasks by interleaving natural-language reasoning with calls t

arXiv:2605.00380v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) enhances reasoning of Large Language Models (LLMs) but usually exhibits limited generation diver

arXiv:2510.00072v2 Announce Type: replace Abstract: Training robust reasoning vision-language models (VLMs) in rare domains (such as geospatial) is fundamentally constrained by supervision scarcity. W

arXiv:2604.27960v1 Announce Type: new Abstract: Recent large language models (LLMs) have achieved impressive reasoning milestones but continue to struggle with high computational costs, logical incons

arXiv:2604.27375v1 Announce Type: new Abstract: Reasoning photo retouching has gained significant traction, requiring models to analyze image defects, give reasoning processes, and execute precise ret

arXiv:2604.26288v1 Announce Type: cross Abstract: Chest X-ray interpretation is one of the most frequently performed diagnostic tasks in medicine and a primary target for AI development, yet current v

arXiv:2603.12249v2 Announce Type: replace-cross Abstract: Constructing scientific multimodal document reasoning datasets for foundation model training involves an inherent trade-off among scale, faith

arXiv:2604.25800v1 Announce Type: cross Abstract: Chain-of-Thought (CoT) has been shown to empirically improve Transformers' performance, and theoretically increase their expressivity to Turing comple

arXiv:2604.25907v1 Announce Type: new Abstract: Adapting reasoning models to new tasks during post-training with only output-level supervision stalls under reinforcement learning from verifiable rewar

arXiv:2603.08592v2 Announce Type: replace Abstract: While Multimodal Large Language Models (MLLMs) have achieved remarkable success in 2D visual understanding, their ability to reason about 3D space r

arXiv:2601.14952v2 Announce Type: replace-cross Abstract: While large language models now handle million-token contexts, their capacity for reasoning across entire document repositories remains largel

arXiv:2604.23348v1 Announce Type: cross Abstract: Recent multimodal large language models (MLLMs) have shown strong capabilities in perception, reasoning, and generation, and are increasingly used in

arXiv:2512.23213v3 Announce Type: replace-cross Abstract: We propose LLM-PeerReview, an unsupervised LLM Ensemble method that selects the most ideal response from multiple LLM-generated candidates for

arXiv:2604.23198v1 Announce Type: new Abstract: Current video moment retrieval excels at action-centric tasks but struggles with narrative content. Models can see extit{what is happening} but fail to

arXiv:2411.08027v3 Announce Type: replace-cross Abstract: Most learning-based approaches to complex physical reasoning sidestep the crucial problem of parameter identification (e.g., mass, friction) t

arXiv:2604.21495v1 Announce Type: cross Abstract: Numerical reasoning over expert-domain tables often exhibits high in-domain accuracy but limited robustness to domain shift. Models trained with super

arXiv:2604.21253v1 Announce Type: cross Abstract: While LLMs demonstrate remarkable fluency in narrative generation, existing methods struggle to maintain global narrative coherence, contextual logica

arXiv:2604.21346v1 Announce Type: new Abstract: Vision--language models (VLMs) often fail on abstract visual reasoning benchmarks such as Bongard problems, raising the question of whether the main bot