Search: “reasoning”

arXiv:2510.25065v3 Announce Type: replace Abstract: Recent advances in sparse reward policy gradient methods have enabled effective reinforcement learning (RL)-based language model post-training. Howe

arXiv:2602.05472v2 Announce Type: replace Abstract: The quest for expert-level reasoning in Large Language Models (LLMs) has been hampered by a persistent extit{reward bottleneck}: traditional reinfor

arXiv:2605.23384v1 Announce Type: cross Abstract: Recent RL methods have substantially improved the reasoning abilities of LLMs. Existing reward designs mainly follow two paradigms: (1) Reinforcement

arXiv:2510.00319v2 Announce Type: replace Abstract: Large Language Models (LLMs) have been demonstrating strong reasoning capability with their chain-of-thoughts (CoT), which are routinely used by hum

arXiv:2605.22072v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has emerged as a promising paradigm for advancing complex reasoning in large language models, and

arXiv:2605.17770v1 Announce Type: new Abstract: The advancement of Large Reasoning Models (LRMs) has catalyzed a paradigm shift from reactive ``fast thinking'' text generation to systematic, step-by-s

arXiv:2605.16385v1 Announce Type: cross Abstract: Geometric problem solving, as a typical multimodal reasoning problem, has attracted much attention and made great progress recently, however most of w

arXiv:2505.23678v3 Announce Type: replace Abstract: While reinforcement learning (RL) over chains of thought has significantly advanced language models in tasks such as mathematics and coding, visual

arXiv:2605.14054v1 Announce Type: new Abstract: Achieving robust perception-reasoning synergy is a central goal for advanced Vision-Language Models (VLMs). Recent advancements have pursued this goal v

arXiv:2605.14665v1 Announce Type: new Abstract: Legal reasoning is not semantic similarity search. A court judgment encodes constrained symbolic reasoning: precedent propagation, procedural state tran

arXiv:2605.14098v1 Announce Type: cross Abstract: Chain-of-thought (CoT) reasoning with self-consistency improves performance by aggregating multiple sampled reasoning paths. In this setting, correctn

arXiv:2605.13534v1 Announce Type: new Abstract: Deep search agents have proven effective in enhancing LLMs by retrieving external knowledge during multi-step reasoning. However, existing methods often

arXiv:2605.06638v2 Announce Type: replace Abstract: Reinforcement learning (RL) has been applied to improve large language model (LLM) reasoning, yet the systematic study of how training scales with t

arXiv:2605.08094v1 Announce Type: cross Abstract: Accurate clinical diagnosis requires extensive domain knowledge and complex clinical reasoning capabilities. Although large language models (LLMs) hol

arXiv:2510.09592v2 Announce Type: replace Abstract: Real-time Spoken Language Models (SLMs) struggle to leverage Chain-of-Thought (CoT) reasoning due to the prohibitive latency of generating the entir

arXiv:2605.08625v1 Announce Type: cross Abstract: Time Series Foundation Models (TSFMs) excel at numerical forecasting but operate as black boxes lacking qualitative reasoning. Conversely, applying LL

arXiv:2605.10805v1 Announce Type: new Abstract: Reasoning-capable large language models (LLMs) have recently been adopted as automated judges, but their benefits and costs in LLM-as-a-Judge settings r

arXiv:2605.07353v1 Announce Type: new Abstract: Large reasoning models often reach correct answers through flawed intermediate steps, creating a gap between final accuracy and reasoning reliability. E

arXiv:2605.07307v1 Announce Type: new Abstract: Modern reasoning language models generate dense, sequential chain-of-thought traces implicitly assuming that every token contributes and that steps must

arXiv:2510.09472v2 Announce Type: replace Abstract: Despite the remarkable progress in neural models, their ability to generalize, a cornerstone for applications such as logical reasoning, remains a c

arXiv:2601.21214v2 Announce Type: replace Abstract: Chain-of-thought (CoT) reasoning has become the standard paradigm for enabling Large Language Models (LLMs) to solve complex problems. However, rece

arXiv:2602.03141v3 Announce Type: replace Abstract: While Large Reasoning Models (LRMs) have demonstrated impressive capabilities in solving complex tasks through the generation of long reasoning chai

arXiv:2506.02515v4 Announce Type: replace-cross Abstract: Multi-step symbolic reasoning is essential for robust financial analysis; yet, current benchmarks largely overlook this capability. Existing d

arXiv:2604.25477v1 Announce Type: new Abstract: Recent image editing models have achieved strong visual fidelity but often struggle with tasks requiring complex reasoning. To investigate and enhance t

arXiv:2509.00084v2 Announce Type: replace-cross Abstract: Test-time scaling (TTS) has gained widespread attention for enhancing LLM reasoning. Existing approaches such as Best-of-N and majority voting

arXiv:2604.21593v1 Announce Type: new Abstract: As LLMs reduce English-centric bias, a surprising trend emerges: non-English responses sometimes outperform English on reasoning tasks. We hypothesize t

arXiv:2604.21396v1 Announce Type: cross Abstract: The advancement of Large Vision-Language Models (LVLMs) requires precise local region-based reasoning that faithfully grounds the model's logic in act

arXiv:2602.10312v2 Announce Type: replace Abstract: We propose R2RAG-Flood, a training-free retrieval-augmented generation framework for flood damage nowcasting with reinforced reasoning. The framewor

arXiv:2604.20755v1 Announce Type: new Abstract: We introduce V-tableR1, a process-supervised reinforcement learning framework that elicits rigorous, verifiable reasoning from multimodal large language

arXiv:2601.11038v2 Announce Type: replace Abstract: We study the reasoning behavior of large language models (LLMs) under limited computation budgets. In such settings, producing useful partial soluti

arXiv:2507.20409v2 Announce Type: replace Abstract: Chain-of-Thought (CoT) prompting helps models think step by step. But naive CoT breaks down in visually grounded social tasks, where models must per

arXiv:2604.17555v1 Announce Type: cross Abstract: Agentic search -- the task of training agents that iteratively reason, issue queries, and synthesize retrieved information to answer complex questions

arXiv:2601.03154v2 Announce Type: replace Abstract: Reasoning-tuned LLMs utilizing long Chain-of-Thought (CoT) excel at single-answer tasks, yet their ability to model Human Label Variation--which req

arXiv:2604.16778v1 Announce Type: new Abstract: LLM-powered agents often reason from scratch when presented with a new problem instance and lack automatic mechanisms to transfer learned skills to othe

arXiv:2601.06803v2 Announce Type: replace Abstract: While Chain-of-Thought empowers Large Vision-Language Models with multi-step reasoning, explicit textual rationales suffer from an information bandw

arXiv:2601.16504v3 Announce Type: replace Abstract: Commonsense reasoning often involves evaluating multiple plausible interpretations rather than selecting a single atomic answer, yet most benchmarks

arXiv:2604.17282v1 Announce Type: new Abstract: Process-Level Reward Models (PRMs) are essential for guiding complex reasoning in large language models, yet existing PRM benchmarks cover only general

arXiv:2604.18486v1 Announce Type: cross Abstract: Chain-of-Thought (CoT) reasoning has become a powerful driver of trajectory prediction in VLA-based autonomous driving, yet its autoregressive nature

arXiv:2511.05993v3 Announce Type: replace Abstract: Reinforcement learning with verifiable rewards (RLVR) has emerged as a prominent paradigm for enhancing the reasoning capabilities of large language

arXiv:2604.17385v1 Announce Type: new Abstract: Spatial intelligence, which refers to the ability to reason about geometric and physical structure from visual observations, remains a core challenge fo

arXiv:2601.00514v2 Announce Type: replace-cross Abstract: Do reasoning models have 'Aha!' moments? Prior work suggests that models like DeepSeek-R1-Zero undergo sudden mid-trace realizations that lead

arXiv:2604.16060v1 Announce Type: cross Abstract: Multimodal Reasoning Models (MRMs) leveraging Chain-of-Thought (CoT) based thinking have revolutionized mathematical and logical problem-solving. Howe

arXiv:2604.15670v1 Announce Type: new Abstract: Reasoning segmentation has recently expanded from ground-level scenes to remote-sensing imagery, yet UAV data poses distinct challenges, including obliq

arXiv:2510.06953v3 Announce Type: replace Abstract: The Uniform Information Density (UID) hypothesis proposes that effective communication is achieved by maintaining a stable flow of information. In t

arXiv:2604.15705v1 Announce Type: new Abstract: Reinforcement Fine-Tuning (RFT) has established itself as a critical paradigm for the alignment of Multi-modal Large Language Models (MLLMs) with comple

arXiv:2604.14214v1 Announce Type: new Abstract: Large Language Models utilizing reasoning techniques improve task performance but incur significant latency and token costs due to verbose generation. E