Knowledge catalogue
arXiv:2605.21856v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated impressive reasoning abilities across a wide range of tasks, but data contamination undermines the object
arXiv:2508.03556v3 Announce Type: replace Abstract: Process Reward Model (PRM) is widely used in the post-training of Large Language Model (LLM) because it can perform fine-grained evaluation of the r
arXiv:2605.22734v1 Announce Type: new Abstract: Biomedical knowledge graphs (KGs) treat disease associations as static facts, but temporal information is crucial for clinical reasoning, e.g., a sympto
arXiv:2605.20467v1 Announce Type: new Abstract: Neural networks can be trained to rank the choices made by logical reasoners, resulting in more efficient searches for answers. A key step in this proce
arXiv:2605.21917v1 Announce Type: new Abstract: Training Vision Language Models (VLMs) for video event reasoning requires high-quality structured annotations capturing not only what happened, but when
arXiv:2605.20942v1 Announce Type: new Abstract: Structured road understanding of lane geometry, topology, and traffic element relationships is foundational to safe autonomous driving. While vision-lan
arXiv:2605.21235v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has become an effective paradigm for improving reasoning language models on tasks such as mathemat
arXiv:2605.19944v1 Announce Type: cross Abstract: While empirical scaling laws for LLM reasoning are well-documented, the theoretical mechanisms governing out-of-distribution (OOD) generalization rema
arXiv:2605.18871v1 Announce Type: cross Abstract: When Large Language Models produce structured outputs such as travel plans, code solutions, or multi-step proofs, individual reasoning steps may appea
arXiv:2605.19824v1 Announce Type: new Abstract: Recent attempts to support high-level scene interpretation and planning in Autonomous Vehicles (AVs) using ensembles of Large Language Models (LLMs) and
arXiv:2605.20006v1 Announce Type: new Abstract: Geospatial reasoning requires solving image-grounded problems over the complex spatial structure of a scene. However, developing this capability is hind
arXiv:2605.18956v1 Announce Type: new Abstract: Recent motion-language models unify tasks like comprehension and generation but operate at a coarse granularity, lacking fine-grained understanding and
arXiv:2503.19877v2 Announce Type: replace Abstract: As language model (LM) outputs get more and more natural, it is becoming more difficult than ever to evaluate their quality. Simultaneously, increas
arXiv:2603.01993v2 Announce Type: replace Abstract: Recent advances in generative AI have significantly enhanced the realism of multimodal media manipulation, thereby posing substantial challenges to
arXiv:2601.11956v2 Announce Type: replace-cross Abstract: Reliable reasoning in Large Language Models (LLMs) is challenged by their propensity for hallucination. While augmenting LLMs with Knowledge G
arXiv:2508.07292v3 Announce Type: replace Abstract: Endoscopic diagnosis is an iterative process in which clinicians progressively acquire, compare, and verify local visual evidence before reaching a
arXiv:2605.16371v1 Announce Type: cross Abstract: Large Multimodal Models (LMMs) often struggle with geometric reasoning due to visual hallucinations and a lack of mathematically precise Chain-of-Thou
arXiv:2605.12987v2 Announce Type: replace Abstract: BACKGROUND: Coding Motivational Interviewing (MI) sessions is essential for understanding client behaviors and predicting outcomes, but it requires
arXiv:2601.21468v5 Announce Type: replace Abstract: Long-horizon agentic reasoning necessitates effectively compressing growing interaction histories into a limited context window. Most existing memor
arXiv:2510.10528v3 Announce Type: replace Abstract: Large reasoning models (LRMs) have demonstrated remarkable proficiency in tackling complex tasks through step-by-step thinking. However, this length
arXiv:2605.17648v1 Announce Type: new Abstract: Generative recommendation treats next-item prediction as autoregressive item-identifier generation. Specifically, items are encoded as semantic identifi
arXiv:2605.17949v1 Announce Type: new Abstract: Remote sensing vision-language models commonly rely on pretrained visual encoders to convert images into semantic features before language-model reasoni
arXiv:2605.18209v1 Announce Type: cross Abstract: Spatial question answering over egocentric video is a challenging task that requires Vision-Language Models (VLMs) to reason about 3D object positions
arXiv:2605.15513v1 Announce Type: new Abstract: Parallel reasoning, where a generator samples many candidate solutions and an aggregator selects the best, is one of the most effective forms of test-ti
arXiv:2605.15997v1 Announce Type: new Abstract: Recent progress in deep learning has significantly advanced CT image analysis, particularly for segmentation tasks. However, these advances are largely
arXiv:2602.01970v2 Announce Type: replace Abstract: Reinforcement learning enhances the reasoning capabilities of large language models but often involves high computational costs due to rollout-inten
arXiv:2605.14163v1 Announce Type: new Abstract: Can a committee of weak reasoning-model calls reach the performance of much stronger models? We study verifier-backed committee search as inference-time
arXiv:2605.14068v1 Announce Type: new Abstract: We introduce CurveBench, a benchmark for hierarchical topological reasoning from visual input. CurveBench consists of extbf{756 images} of pairwise non-
arXiv:2602.02427v2 Announce Type: replace Abstract: Large language Models (LLMs) have achieved significant breakthroughs across diverse domains; however, they can still produce unreliable or misleadin
arXiv:2512.12772v2 Announce Type: replace-cross Abstract: Understanding videos inherently requires reasoning over both visual and auditory information. To properly evaluate Omni-Large Language Models
arXiv:2511.13026v3 Announce Type: replace Abstract: Self-reflection mechanisms that rely on purely text-based rethinking processes perform well in most multimodal tasks. However, when directly applied
arXiv:2605.14619v1 Announce Type: new Abstract: Multi-run chain-of-thought reasoning is usually collapsed to final-answer aggregates, which discard howsampled trajectories share, split, and rejoin thr
arXiv:2605.14636v1 Announce Type: new Abstract: Large language models (LLMs) often fail to reason under temporal cutoffs: when prompted to answer from the standpoint of an earlier time, they exploit k
arXiv:2605.12545v1 Announce Type: cross Abstract: Aesthetic image cropping aims to enhance the aesthetic quality of an image by improving its composition through spatial cropping. Previous methods oft
arXiv:2512.01707v3 Announce Type: replace-cross Abstract: Streaming video understanding requires models not only to process temporally incoming frames, but also to anticipate user intention for realis
arXiv:2605.13772v1 Announce Type: cross Abstract: Large language models hallucinate during multi-step reasoning, but most existing detectors operate at the trace level: they assign one confidence scor
arXiv:2605.11609v1 Announce Type: cross Abstract: On-policy self-distillation, where a student is pulled toward a copy of itself conditioned on privileged context (e.g., a verified solution or feedbac
arXiv:2510.17062v2 Announce Type: replace Abstract: While reasoning-based large language models excel at complex tasks through an internal, structured thinking process, a concerning phenomenon has eme
arXiv:2605.12400v1 Announce Type: new Abstract: We study {on-policy self-distillation} (OPSD), where a language model improves its reasoning ability by distilling privileged teacher distributions alon
arXiv:2605.12466v1 Announce Type: cross Abstract: Looped Transformers offer a promising alternative to purely feed-forward computation by iteratively refining latent representations, improving languag
arXiv:2605.11599v1 Announce Type: new Abstract: Fixed reasoning benchmarks evaluate canonical prompts, but semantically valid changes in presentation can still change model behavior. Studies of prompt
arXiv:2605.09496v1 Announce Type: new Abstract: Large language models represent the same reasoning in vastly different surface forms -- English prose, Python code, mathematical notation -- yet whether
arXiv:2605.08888v1 Announce Type: new Abstract: Evaluating whether Multimodal Large Language Models can produce trustworthy, verifiable reasoning over long, visually rich documents requires evaluation
arXiv:2605.09042v1 Announce Type: new Abstract: Evaluating pragmatic reasoning in large language models (LLMs) remains challenging because model behavior can vary depending on evaluation methods. Prev
arXiv:2605.08930v1 Announce Type: new Abstract: While explicit Chain-of-Thought (CoT) empowers large reasoning models (LRMs), it enables the generation of riskier final answers. Current alignment para
arXiv:2605.09252v1 Announce Type: new Abstract: Tool-augmented LLM agents tend to call tools indiscriminately, even when the model can answer directly. Each unnecessary call wastes API fees and latenc
arXiv:2605.09270v1 Announce Type: cross Abstract: Supervised Fine-Tuning (SFT) is widely used for task-specific adaptation, yet recent work shows it systematically undermines reasoning generalization.
arXiv:2605.08221v1 Announce Type: cross Abstract: This paper presents NoisyCoconut, a novel inference-time method that enhances large language model (LLM) reliability by manipulating internal represen
arXiv:2605.09490v1 Announce Type: new Abstract: Reasoning LLMs produce thousands of chain-of-thought tokens whose KV cache must reside in scarce GPU HBM. The dominant response -- permanently evicting
arXiv:2602.03190v3 Announce Type: replace-cross Abstract: Reinforcement learning algorithms such as group-relative policy optimization (GRPO) have shown strong potential for improving the mathematical
arXiv:2511.00371v2 Announce Type: replace Abstract: In Socratic debugging, instructors guide students towards identifying and fixing a bug on their own, instead of providing the bug fix directly. Most
arXiv:2605.09346v1 Announce Type: cross Abstract: The Chain-of-Thought (CoT) paradigm, while enhancing the interpretability of Large Language Models (LLMs), is constrained by the inefficiencies and ex
arXiv:2605.09544v1 Announce Type: new Abstract: Tool-integrated reasoning has emerged as a promising paradigm for enhancing large language models with external computation, retrieval, and execution ca
arXiv:2605.10373v1 Announce Type: cross Abstract: Large language models have significantly improved natural language interfaces to databases by translating user questions into executable queries. In p
arXiv:2605.08709v1 Announce Type: new Abstract: Unified face attack detection (UAD) requires recognizing physical spoofing and digital forgery within a shared decision space, yet existing discriminati
arXiv:2605.08201v1 Announce Type: cross Abstract: Neurosymbolic systems promise to combine deep neural network's (DNN) processing of raw sensor inputs with few-shot performance of symbolic artificial
arXiv:2605.07137v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has become a highly effective method for improving the reasoning abilities of Large Language Mod
arXiv:2605.07926v1 Announce Type: new Abstract: As LLM-based agents increasingly rely on external tools, it is important to evaluate their ability to sustain tool-grounded reasoning beyond familiar wo
arXiv:2601.15050v4 Announce Type: replace Abstract: Current evaluation methods for Retrieval Augmented Generation (RAG) suffer from extit{factual myopia}: they relentlessly emphasize factual accuracy
arXiv:2601.21699v2 Announce Type: replace Abstract: Multi-turn reasoning agents solve complex questions by decomposing them into intermediate retrieval or tool-use steps, for accumulating supporting e