Search: “reasoning”

arXiv:2609.13808v1 Announce Type: new Abstract: Structured knowledge fact checking aims to determine the truthfulness of natural language claims by reasoning over structured evidence. Recent program-g

arXiv:2601.04260v2 Announce Type: replace Abstract: Understanding how Large Language Models (LLMs) perform logical reasoning internally remains a fundamental challenge. While prior mechanistic studies

arXiv:2609.06251v1 Announce Type: new Abstract: Grounding natural-language instructions into reliable and executable actions remains a fundamental challenge for vision-language-action (VLA) systems on

arXiv:2609.07258v1 Announce Type: new Abstract: Despite the rapid progress of Multimodal Large Language Models (MLLMs) in 2D vision-language tasks, robust multi-view spatial reasoning remains a fundam

arXiv:2602.02028v3 Announce Type: replace Abstract: Enabling artificial intelligence systems, particularly large language models, to update knowledge and flexibly apply it during reasoning remains a c

arXiv:2609.02805v1 Announce Type: new Abstract: Root cause analysis (RCA) is a critical task in telecom network operations, but diagnosing performance degradations in modern 5G and emerging 6G network

arXiv:2602.01695v2 Announce Type: replace Abstract: Latent reasoning reduces the token-generation cost of chain-of-thought reasoning by replacing explicit intermediate tokens with continuous latent tr

arXiv:2608.30413v1 Announce Type: new Abstract: Defeasible reasoning is a type of reasoning where inferences are drawn from plausible current evidence, but can be retracted upon the introduction of ne

arXiv:2608.29880v1 Announce Type: new Abstract: Open-world geo-localization requires models to reason over ambiguous visual cues through multi-step reasoning and external knowledge grounding. While re

arXiv:2608.30716v1 Announce Type: new Abstract: Recent advances in Large Multimodal Models (LMMs) have greatly improved video understanding, yet their ability to reason about human-centered social sit

arXiv:2510.13394v4 Announce Type: replace Abstract: Spatial reasoning ability is crucial for Vision Language Models (VLMs) to support real-world applications in diverse domains including robotics, aug

arXiv:2601.03506v2 Announce Type: replace-cross Abstract: Recent large reasoning models (LRMs) have achieved strong performance on complex reasoning tasks by generating a long chain-of-thought (Long-C

arXiv:2608.13667v1 Announce Type: new Abstract: LLM agents in the ReAct paradigm alternate between reasoning, acting, and observing, but deliberate reasoning is confined to the Thought phase: while th

arXiv:2608.12877v1 Announce Type: new Abstract: Multi-hop fact verification, which verifies claims by reasoning over multiple pieces of evidence, is critical for combating misinformation on social med

arXiv:2608.07987v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have demonstrated significant potential in complex spatial scene understanding and reasoning tasks. However, th

Stealing Reasoning Traces from Proprietary LLM APIs A vanity domain name (stolen-thoughts.com) for a neat paper: Anthropic, OpenAI, and Google return encrypted chain-of-thought blocks to clients that

arXiv:2607.29211v1 Announce Type: new Abstract: Large language models generate computationally expensive yet semantically void reasoning on beyond-capability tasks, creating risks where plausible-soun

arXiv:2607.28374v1 Announce Type: new Abstract: Multimodal agents for visual question answering increasingly operate as multi-step trajectories that interleave perception, retrieval, and reasoning, ye

arXiv:2602.01348v3 Announce Type: replace Abstract: Retrieval-augmented generation (RAG) can achieve strong answer accuracy on multi-hop questions, but outcome-level rewards often leave reasoning trac

arXiv:2607.21722v1 Announce Type: new Abstract: While Large Vision-Language Models (LVLMs) exhibit strong perceptual capabilities, they remain vulnerable in visual reasoning tasks. Existing benchmarks

arXiv:2607.05199v1 Announce Type: new Abstract: Physics reasoning fails structurally in small language models: an error at any step propagates forward, corrupting every inference that follows. Limited

arXiv:2606.26986v1 Announce Type: cross Abstract: Open Relation Extraction (OpenRE) requires a model to extract unseen relations between head and tail entities from unstructured text for real-world ap

arXiv:2606.22565v1 Announce Type: cross Abstract: Chain-of-Thought (CoT) has become a standard method for improving reasoning capabilities in large language models (LLMs) by eliciting step-by-step thi

arXiv:2606.09248v1 Announce Type: new Abstract: Multi-modal Large Language Models (MLLMs) have achieved remarkable progress in video temporal grounding with reinforcement learning for generating reaso

arXiv:2606.06188v1 Announce Type: new Abstract: Recent work has sought to understand Large Language Models (LLMs) reasoning, yet a principled, model-intrinsic signal that captures its layer-wise reaso

arXiv:2606.02248v1 Announce Type: new Abstract: Large language models solve complex problems by generating lengthy chains of explicit reasoning tokens. While effective, this makes reasoning expensive,

arXiv:2605.28678v1 Announce Type: new Abstract: Speculative reasoning has recently been proposed as a means to accelerate reasoning-intensive generation in large multimodal models, but its effectivene

arXiv:2509.21128v2 Announce Type: replace Abstract: Large language models (LLMs) are typically trained by reinforcement learning (RL) with verifiable rewards (RLVR) and supervised fine-tuning (SFT) on

arXiv:2605.08776v1 Announce Type: new Abstract: Reasoning-centric large language models (LLMs) achieve strong performance by generating intermediate reasoning trajectories, but often incur excessive t

arXiv:2601.18832v3 Announce Type: replace-cross Abstract: Scaling test-time compute enhances long chain-of-thought (CoT) reasoning, yet existing approaches face a fundamental trade-off between computa

arXiv:2604.25120v1 Announce Type: new Abstract: We study clinical trial table reasoning, where answers are not directly stored in visible cells but must be reasoned from semantic understanding through

arXiv:2508.07101v2 Announce Type: replace Abstract: Large reasoning models achieve strong performance through test-time scaling, but this incurs substantial computational overhead due to long decoding

arXiv:2604.23270v1 Announce Type: new Abstract: Chain-of-Thought (CoT) prompting has emerged as a simple and effective way to elicit step-by-step solutions from large language models (LLMs). However,

arXiv:2604.21190v1 Announce Type: new Abstract: Understanding visual scenes requires not only recognizing objects but also reasoning about their spatial relationships. Unlike general vision-language t

arXiv:2604.19036v1 Announce Type: new Abstract: Defeasible statements are statements that are likely, or probable, or usually true, but may occasionally be false. Plausible reasoning makes conclusions

arXiv:2601.04562v2 Announce Type: replace Abstract: Generative recommendation with large language models (LLMs) reframes prediction as sequence generation, yet existing LLM-based recommenders remain l

arXiv:2602.07529v3 Announce Type: replace Abstract: Large language models (LLMs) have demonstrated strong performance and rapid progress in a wide range of medical reasoning tasks. However, their sequ

arXiv:2601.02902v2 Announce Type: replace-cross Abstract: Symbolic logical reasoning is a critical yet underexplored capability of large language models (LLMs), providing reliable and verifiable decis

arXiv:2601.11340v2 Announce Type: replace Abstract: Chain-of-Thought reasoning has significantly enhanced the problem-solving capabilities of Large Language Models. Unfortunately, current models gener

arXiv:2509.25758v2 Announce Type: replace Abstract: The remarkable capabilities of modern large reasoning models are largely unlocked through post-training techniques such as supervised fine-tuning (S

arXiv:2604.11741v1 Announce Type: new Abstract: Vision-language models (VLMs) have shown impressive capabilities in perceptual tasks, yet they degrade in complex multi-hop reasoning under multiplayer

arXiv:2601.06767v2 Announce Type: replace-cross Abstract: We present a Bengali mathematical reasoning model called GanitLLM (named after the Bangla word for mathematics, 'Ganit'), together with a new

arXiv:2506.13331v3 Announce Type: replace Abstract: Human cognitive behavior arises from the interaction of specialized brain networks dedicated to distinct functions, such as language, logic, and soc

arXiv:2604.09580v1 Announce Type: new Abstract: Standard Chain-of-Thought (CoT) prompting empowers Large Language Models (LLMs) with reasoning capabilities, yet its reliance on linear natural language

arXiv:2604.04415v2 Announce Type: replace Abstract: Human understanding of video dynamics is typically grounded in a structured mental representation of entities, actions, and temporal relations, rath

arXiv:2604.10788v1 Announce Type: cross Abstract: Tool-Integrated Reasoning (TIR) has emerged as a promising direction by extending Large Language Models' (LLMs) capabilities with external tools durin