Knowledge catalogue
arXiv:2605.30651v1 Announce Type: cross Abstract: We study trajectory selection for reasoning distillation, where teacher-generated reasoning trajectories are selectively used as supervision for a stu
arXiv:2605.31584v1 Announce Type: cross Abstract: Long-context reasoning remains a central challenge for large language models, which often fail to locate and integrate key information in extensive di
arXiv:2605.30391v1 Announce Type: cross Abstract: Human reasoning has long been theorised to operate socially, not through isolated individual cognition, but through collective adversarial discourse,
arXiv:2602.02103v2 Announce Type: replace-cross Abstract: Chain-of-thought (CoT) reasoning has become a central mechanism for eliciting multi-step reasoning in Large Language Models (LLMs). Yet recent
arXiv:2605.30327v1 Announce Type: cross Abstract: Frontier reasoning models are produced by posttraining base language models with reinforcement learning. Recent work has challenged this by showing th
arXiv:2605.28192v1 Announce Type: new Abstract: Multi-hop audio-visual reasoning remains challenging for Omni-LLMs, as relevant evidence is often sparse, temporally dispersed, and distributed across b
arXiv:2605.28742v1 Announce Type: new Abstract: Language models can use verifiable rewards to improve at a wide variety of reasoning tasks. However, both parametric (e.g. RLVR) and non-parametric (e.g
arXiv:2504.04540v2 Announce Type: replace-cross Abstract: 3D Large Language Models (LLMs) leveraging spatial information in point clouds for 3D spatial reasoning attract great attention. Despite some
arXiv:2510.13217v2 Announce Type: replace-cross Abstract: Search systems are increasingly used for reasoning-intensive queries, where what makes a document relevant requires understanding or reasoning
arXiv:2605.26352v1 Announce Type: new Abstract: Retrieval is increasingly moving from one-shot matching toward interactive reasoning, where language agents iteratively inspect evidence, reformulate qu
arXiv:2506.17629v2 Announce Type: replace-cross Abstract: Embodied Visual Reasoning (EVR) seeks to follow complex, free-form instructions based on egocentric video, enabling semantic understanding and
arXiv:2605.24867v1 Announce Type: new Abstract: Chain-of-Thought (CoT) prompting has shown promise in enhancing the reasoning capabilities of large language models (LLMs) on text-attributed graphs (TA
arXiv:2605.26038v1 Announce Type: cross Abstract: Lightweight vision-language models perform competitively on standard benchmarks yet fail systematically in dense-scene reasoning, where multiple objec
arXiv:2605.24636v1 Announce Type: new Abstract: While large language models (LLMs) hold transformative potential for medicine, their reasoning robustness and safety in real-world clinical scenarios re
arXiv:2605.25443v1 Announce Type: new Abstract: Post-training has significantly enhanced the reasoning capability of Large Reasoning Models (LRMs), especially with Reinforcement Learning (RL) like Gro
arXiv:2605.05226v2 Announce Type: replace-cross Abstract: The central challenge of reinforcement learning for reasoning lies not only in the sparsity of outcome-level supervision, but more fundamental
arXiv:2605.25566v1 Announce Type: new Abstract: Clinical decision-making requires reasoning over incomplete, imprecise, and linguistically expressed patient narratives. While large language models (LL
The raw reasoning stream can be accessed through the message.thinking field in the API response or the thinking endpoint field, which contains the reasoning trace separately from the final answer. Use
arXiv:2505.17123v3 Announce Type: replace Abstract: Recent advances in Large Language Models (LLMs) have shown promising results in complex reasoning tasks. However, current evaluations predominantly
arXiv:2605.22658v1 Announce Type: new Abstract: While large language models provide strong compositional reasoning, existing reasoning segmentation pipelines fail to transparently connect this reasoni
arXiv:2508.08636v2 Announce Type: replace Abstract: Large language models (LLMs) have revolutionized artificial intelligence by enabling complex reasoning capabilities. While recent advancements in re
arXiv:2605.20201v1 Announce Type: new Abstract: Recent large language models support inputs of up to 10 million tokens, yet they perform poorly on long-context tasks that require complex reasoning. Su
arXiv:2605.20867v1 Announce Type: cross Abstract: Multimodal sarcasm detection requires reasoning over cross-modal incongruities between literal expression and intended meaning, yet the specific analy
arXiv:2605.19485v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) have demonstrated remarkable capabilities in solving complex problems by generating structured, step-by-step reasoning con
arXiv:2605.19433v1 Announce Type: cross Abstract: Large language models (LLMs) have achieved remarkable success in complex reasoning tasks via long chain-of-thought (CoT), yet their immense computatio
arXiv:2505.11628v4 Announce Type: replace Abstract: Supervised fine-tuning with expert demonstrations often produces models that imitate outputs without internalizing the reasoning processes needed fo
arXiv:2601.22530v2 Announce Type: replace Abstract: Large Language Models (LLMs) struggle with multi-step reasoning over structured tables. The primary reason is the lack of explicit supervision for i
arXiv:2605.18500v1 Announce Type: new Abstract: Large language models (LLMs) have increasingly leveraged tool invocation to enhance their reasoning capabilities. However, existing approaches typically
arXiv:2601.22297v2 Announce Type: replace Abstract: The reasoning abilities of large language models (LLMs) have been substantially improved by reinforcement learning with verifiable rewards (RLVR). A
arXiv:2605.18549v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) introduce new opportunities for safety monitoring through their Chain of Thought (CoT) reasoning. However, CoT is not alwa
arXiv:2602.08324v3 Announce Type: replace Abstract: Chain-of-Thought (CoT) reasoning successfully enhances the reasoning capabilities of Large Language Models (LLMs), yet it incurs substantial computa
arXiv:2605.15198v1 Announce Type: cross Abstract: Visual reasoning, often interleaved with intermediate visual states, has emerged as a promising direction in the field. A straightforward approach is
arXiv:2602.08874v2 Announce Type: replace Abstract: Long-context LLMs can infer objectives that are not stated explicitly. This capability is useful for reasoning over documents, code, retrieved evide
arXiv:2601.03630v2 Announce Type: replace Abstract: This paper presents the first systematic comparison investigating whether Large Reasoning Models (LRMs) are superior judges to non-reasoning LLMs. O
arXiv:2605.14908v1 Announce Type: new Abstract: Video reasoning segmentation requires localizing objects across video frames from natural language expressions, often involving spatial reasoning and im
arXiv:2605.14358v1 Announce Type: new Abstract: Language models often generate long chain-of-thought traces, but it remains unclear how much of this reasoning is necessary for preserving the final pre
arXiv:2602.17555v3 Announce Type: replace Abstract: Video reasoning requires a fine-grained understanding of the temporal dependencies and event-level relations between objects and events in videos. C
arXiv:2605.13213v1 Announce Type: new Abstract: Multi-modal multi-agent systems (MM-MAS) have gained increasing attention for their capacity to enable complex reasoning and coordination across diverse
arXiv:2605.12524v1 Announce Type: cross Abstract: We introduce ProofGrid, a benchmark suite for evaluating LLM reasoning through machine-checkable proofs rather than final answers alone. ProofGrid con
arXiv:2605.11629v1 Announce Type: new Abstract: Recent multimodal large language models (MLLMs) have shown strong chain-of-thought (CoT) reasoning ability on vision-language tasks, but their direct de
arXiv:2605.11906v1 Announce Type: new Abstract: Preference optimization has become an important post-training paradigm for improving the reasoning abilities of large language models. Existing methods
arXiv:2601.02950v3 Announce Type: replace Abstract: Current Large Language Model reasoning systems process queries independently, discarding valuable cross-instance signals such as shared reasoning pa
arXiv:2605.09292v1 Announce Type: new Abstract: Large language models now achieve high final-answer accuracy on mathematical reasoning benchmarks, but accuracy alone does not capture reasoning flexibi
arXiv:2605.10195v1 Announce Type: new Abstract: Tree-of-Thought (ToT) reasoning structures Large Language Model (LLM) inference as a tree-based search, demonstrating strong potential for solving compl
arXiv:2605.08735v1 Announce Type: new Abstract: Recent 'Thinking with Video' approaches use Video Generation Models (VGMs) for visual reasoning by producing temporally coherent Chain-of-Frames as reas
arXiv:2509.26574v4 Announce Type: replace Abstract: While large language models (LLMs) with reasoning capabilities are progressing rapidly on high-school math competitions and coding, can they reason
arXiv:2506.04289v3 Announce Type: replace Abstract: Transformer-based models have demonstrated remarkable reasoning abilities, but the mechanisms underlying relational reasoning remain poorly understo
arXiv:2602.01698v3 Announce Type: replace Abstract: Large Reasoning Models (LRMs) have recently achieved strong mathematical and code reasoning performance through Reinforcement Learning (RL) post-tra
arXiv:2605.10187v1 Announce Type: new Abstract: Scientific reasoning is a key aspect of human intelligence, requiring the integration of multimodal inputs, domain expertise, and multi-step inference a
arXiv:2602.03916v3 Announce Type: replace-cross Abstract: Spatial reasoning is a fundamental aspect of human cognition, yet it remains a major challenge for contemporary vision-language models (VLMs).
arXiv:2605.08412v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have made rapid progress in single-video understanding, yet their ability to reason across multiple independent
arXiv:2605.09883v1 Announce Type: cross Abstract: As current Multimodal Large Language Models rapidly saturate canonical visual reasoning benchmarks, a key question emerges: do these strong scores gen
arXiv:2605.10325v1 Announce Type: new Abstract: Reinforcement learning from verifiable rewards (RLVR) has improved the reasoning abilities of large language models (LLMs), but most existing approaches
arXiv:2507.03167v3 Announce Type: replace-cross Abstract: Chat models without chain-of-thought (CoT) reasoning must decide whether to refuse a harmful request before generating their first response to
arXiv:2605.07817v1 Announce Type: cross Abstract: Human visual reasoning is governed by active vision, a process where metacognitive control drives top-down goal-directed attention, dynamically routin
arXiv:2605.07316v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards improves LLM reasoning but often induces overthinking, where models generate unnecessarily long reasoning
arXiv:2506.06856v3 Announce Type: replace Abstract: Visual reasoning is crucial for understanding complex multimodal data and advancing Artificial General Intelligence. Existing methods enhance the re
arXiv:2508.15202v2 Announce Type: replace Abstract: Process Reward Models (PRMs) supervise intermediate reasoning steps in large language models (LLMs), but existing PRMs are mainly trained on general
arXiv:2604.05134v2 Announce Type: replace Abstract: We study how reasoning evolves in a language model -- from supervised fine-tuning (SFT) to reinforcement learning (RL) -- by analyzing how a set of
arXiv:2605.01327v1 Announce Type: cross Abstract: Existing reinforcement learning approaches for Large Language Models typically perform policy optimization at the granularity of individual tokens or