Search: “reasoning”

arXiv:2510.03988v2 Announce Type: replace Abstract: Distilling long-form reasoning from teacher models into smaller students requires selecting which candidate solutions to train on. Recent work argue

arXiv:2601.11047v2 Announce Type: replace Abstract: Large Language Models (LLMs) have demonstrated remarkable reasoning capabilities but often grapple with reliability challenges like hallucinations.

arXiv:2511.02627v2 Announce Type: replace Abstract: We introduce DecompSR, decomposed spatial reasoning, a large benchmark dataset (over 5m datapoints) and generation framework designed to analyse com

arXiv:2604.12133v1 Announce Type: new Abstract: Historical approaches to Table Representation Learning (TRL) have largely adopted the sequential paradigms of Natural Language Processing (NLP). We argu

arXiv:2510.01544v2 Announce Type: replace Abstract: Diffusion-based large language models offer a non-autoregressive alternative for text generation, but enabling them to perform complex reasoning rem

arXiv:2604.10973v1 Announce Type: new Abstract: Reasoning over tabular data is a crucial capability for tasks like question answering and fact verification, as it requires models to comprehend both fr

arXiv:2509.25866v2 Announce Type: replace Abstract: The 'thinking with images' paradigm represents a pivotal shift in the reasoning of Vision Language Models (VLMs), moving from text-dominant chain-of

arXiv:2604.11556v1 Announce Type: cross Abstract: LLM-assisted software development has become increasingly prevalent, and can generate large-scale systems, such as compilers. It becomes crucial to st

arXiv:2604.10517v1 Announce Type: new Abstract: Modern vision-language models achieve strong performance in static perception, but remain limited in the complex spatiotemporal reasoning required for e

arXiv:2604.11502v1 Announce Type: cross Abstract: Contextual causal reasoning is a critical yet challenging capability for Large Language Models (LLMs). Existing benchmarks, however, often evaluate th

arXiv:2412.04272v5 Announce Type: replace-cross Abstract: In recent years, table reasoning has garnered substantial research interest, particularly regarding its integration with Large Language Models

arXiv:2604.11435v1 Announce Type: cross Abstract: Character description generation is an important capability for narrative-focused applications such as summarization, story analysis, and character-dr

arXiv:2604.09511v1 Announce Type: new Abstract: Universal image restoration (UIR) aims to recover clean images from diverse and unknown degradations using a unified model. Existing UIR methods primari

arXiv:2604.06268v1 Announce Type: new Abstract: RL training of multi-turn LLM agents is inherently unstable, and reasoning quality directly determines task performance. Entropy is widely used to track

arXiv:2604.06995v1 Announce Type: new Abstract: Existing Graphical User Interface (GUI) reasoning tasks remain challenging, particularly in UI understanding. Current methods typically rely on direct s

arXiv:2604.08281v1 Announce Type: new Abstract: Large reasoning models (LRMs) have achieved strong performance enhancement through scaling test time computation, but due to the inherent limitations of

arXiv:2610.18878v1 Announce Type: new Abstract: Post-training reasoning LLMs often requires making a tradeoff between costly supervision and compute inefficiency: supervised finetuning typically requi

arXiv:2610.14073v1 Announce Type: cross Abstract: Large language models (LLMs) remain unreliable when reasoning about the future. Existing models often overlook the difference among future states, com

arXiv:2610.15259v1 Announce Type: new Abstract: Low-bit quantization reduces the cost of serving reasoning models but can substantially degrade long chains of thought. Each step reads cached keys and

arXiv:2610.19644v1 Announce Type: new Abstract: Typed decision models need an interface that can use additional reasoning while retaining candidate outputs. We train a shared candidate-answer reader o

arXiv:2610.17131v2 Announce Type: cross Abstract: Dynamic spatial audio reasoning requires a model to associate changing acoustic observations with the correct source and recover its spatial state at

arXiv:2610.18694v1 Announce Type: new Abstract: Vision-language models (VLMs) struggle with metric and multi-view relationships that remain implicit in RGB observations. Geometry foundation models rec

arXiv:2610.16357v1 Announce Type: new Abstract: Agentic video reasoning systems gather and assess video evidence across stages, selecting relevant spans as visual evidence for answering questions. New

arXiv:2610.16811v1 Announce Type: new Abstract: Chest X-ray (CXR) interpretation often requires integrating visual findings with task-specific evidence rather than relying on direct visual recognition

arXiv:2610.13672v1 Announce Type: cross Abstract: Large language models struggle to reliably identify and correct errors in their own reasoning. Unlike prior training-based approaches that fine-tune a

arXiv:2610.12881v1 Announce Type: new Abstract: Understanding and manipulating spatial relations is fundamental to AI systems that reason about physical environments and construct grounded world model

arXiv:2610.13832v1 Announce Type: cross Abstract: When solving complex spatial reasoning tasks, ordinary humans naturally revisit the scenes from task-relevant viewpoints and mentally reconstruct the

arXiv:2610.10641v1 Announce Type: cross Abstract: Large language models (LLMs) offer promising potential for next-visit diagnosis prediction, owing to their ability to integrate longitudinal clinical

arXiv:2510.04532v2 Announce Type: replace Abstract: Vision-Language Model (VLM) driving agents promise explainable end-to-end autonomy by first producing natural-language reasoning and then predicting

arXiv:2407.14562v3 Announce Type: replace Abstract: Large language models have demonstrated remarkable capabilities as general-purpose assistants, excelling in a wide range of reasoning tasks and supp

arXiv:2610.09733v1 Announce Type: new Abstract: Multilingual LLMs answer the same multi-hop reasoning question across languages, but we lack a mechanistic account of whether they share an internal cir

arXiv:2610.09780v1 Announce Type: new Abstract: Diffusion models excel at image synthesis, but they remain limited in their ability to reliably satisfy structured spatial reasoning constraints. In con

arXiv:2610.09360v1 Announce Type: cross Abstract: Real-world documents distribute evidence across text, tables, figures, and captions within complex page layouts. Answering complex questions over such

arXiv:2610.08561v1 Announce Type: new Abstract: Reinforcement learning (RL) has become a standard tool for post-training language models on reasoning tasks, where the policy is updated by reward feedb

arXiv:2610.08659v1 Announce Type: cross Abstract: Model merging provides a training-free way to transfer reasoning capabilities from language models to vision-language models (VLMs), but endpoint-base

arXiv:2610.05630v1 Announce Type: cross Abstract: Visual entailment (VE) asks whether an image supports, contradicts, or leaves undecided a textual hypothesis. Strong results come from fine-tuning lar

arXiv:2610.06439v1 Announce Type: new Abstract: What happens when a legal AI model learns to look like a lawyer instead of reasoning like one? We fine tune Qwen3-8B with Group Relative Policy Optimisa

arXiv:2507.07297v2 Announce Type: replace Abstract: Recent advances in large vision-language models have led to impressive performance in visual question answering and multimodal reasoning. However, i

arXiv:2610.04594v1 Announce Type: cross Abstract: Chain-of-Thought (CoT) faithfulness detectors are widely used to audit reasoning models, yet a detector is itself a predictor whose verdicts are treat

arXiv:2610.06666v1 Announce Type: new Abstract: Latent reasoning lets a large language model (LLM) think in a continuous space and verbalize only the answer. We argue that an effective latent thought

arXiv:2601.09879v2 Announce Type: replace-cross Abstract: Recent progress in medical vision-language models (VLMs) has achieved strong performance on image-level text-centric tasks such as report gene

arXiv:2610.00399v1 Announce Type: new Abstract: Metacognition involves reasoning about cognitive processes themselves. An example is in resource allocation where we choose how much time and effort to

arXiv:2609.33149v2 Announce Type: replace Abstract: A common principle of effective learning is to practice material that is neither already mastered nor too difficult to permit progress. We ask how t

arXiv:2609.38829v1 Announce Type: new Abstract: Multi-path reasoning methods such as self-consistency (SC) sample K reasoning paths and choose the most frequent answer. However, their gains quickly pl

arXiv:2609.38879v1 Announce Type: cross Abstract: Large language models rely heavily on human text, which often conveys surface answers rather than the spatial and structural logic behind them. Protei

arXiv:2609.37203v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed for natural-language logical reasoning, where the final answer is easy to check but the proof beh