Knowledge catalogue
arXiv:2604.18892v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) improves multimodal reasoning by rewarding verifiable final answers. Yet answer-correct trajectori
arXiv:2601.05543v2 Announce Type: replace Abstract: Although Speech Large Language Models have achieved notable progress, a substantial modality reasoning gap remains: their reasoning performance on s
arXiv:2601.03682v2 Announce Type: replace Abstract: Recent studies reveal that large language models (LLMs) exhibit limited logical reasoning abilities in mathematical problem-solving, instead often r
arXiv:2604.18307v1 Announce Type: new Abstract: Language models often solve complex tasks by generating long reasoning chains, consisting of many steps with varying importance. While some steps are cr
arXiv:2601.05053v2 Announce Type: replace-cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has proven effective in enhancing the reasoning of large language models (LLMs). Monte C
arXiv:2604.16256v1 Announce Type: cross Abstract: Reasoning in vision-language models (VLMs) has recently attracted significant attention due to its broad applicability across diverse downstream tasks
arXiv:2604.15726v1 Announce Type: new Abstract: This position paper argues that large language model (LLM) reasoning should be studied as latent-state trajectory formation rather than as faithful surf
LLM agents loop, drift, and get stuck on hard reasoning tasks up to 30% of the time. Current fixes are either too blunt (hard step limits) or too expensive (LLM-as-judge adding 10-15% overhead per ste
arXiv:2604.14631v1 Announce Type: new Abstract: Effective code generation requires both model capability and a problem representation that carefully structures how models reason and plan. Existing app
arXiv:2601.04442v2 Announce Type: replace-cross Abstract: Large Vision-Language Models (LVLMs) have exhibited strong reasoning capabilities through chain-of-thought mechanisms that generate step-by-st
arXiv:2604.13065v1 Announce Type: new Abstract: LLMs can execute every step of chain-of-thought reasoning correctly and still produce wrong final answers. We introduce the Novel Operator Test, a bench
arXiv:2506.08125v3 Announce Type: replace-cross Abstract: Large language models (LLMs) show strong reasoning abilities but often produce unnecessarily long explanations that reduce efficiency. Althoug
arXiv:2507.06448v5 Announce Type: replace Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has proven to be a highly effective strategy for endowing Large Language Models (LLMs) with ro
arXiv:2601.10775v2 Announce Type: replace Abstract: We propose a novel LLM-based framework for reasoning in discrete, game-theoretic tasks, illustrated with Tic-Tac-Toe. The method integrates in-conte
arXiv:2604.09704v1 Announce Type: new Abstract: Recent advances in reasoning-induced image quality assessment (IQA) have demonstrated the power of reinforcement learning to rank (RL2R) for training vi
arXiv:2604.08539v1 Announce Type: cross Abstract: Group Relative Policy Optimization (GRPO) has emerged as the de facto Reinforcement Learning (RL) objective driving recent advancements in Multimodal
arXiv:2610.21030v1 Announce Type: cross Abstract: Reasoning-conditioned embeddings can improve retrieval by progressively refining semantic constraints. However, additional reasoning may introduce ove
arXiv:2610.21286v1 Announce Type: new Abstract: We investigate whether variation in information density across chain-of-thought (CoT) reasoning steps predicts answer correctness and can serve as a con
arXiv:2610.16133v1 Announce Type: cross Abstract: Puzzles offer a natural testbed for Large Language Models (LLMs) reasoning because they pose verifiable goals under partial information and require mu
arXiv:2601.03822v2 Announce Type: replace Abstract: Large language models (LLMs) can achieve strong reasoning performance with sufficient computation, but they do not inherently know how much computat
arXiv:2610.13996v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards improves mathematical reasoning when a final answer can be checked, but a correct answer does not certify
arXiv:2610.12927v1 Announce Type: new Abstract: Large language models (LLMs) excel across diverse tasks, benefiting from knowledge priors, in-context reasoning, and test-time computation. Despite thes
arXiv:2610.12769v1 Announce Type: cross Abstract: Unlearning in large reasoning models (LRMs) requires removing forget-set information from both the reasoning trace and the final answer. Existing appr
arXiv:2607.17575v3 Announce Type: replace Abstract: We propose ARBITER, a novel LLM guardrail framework that introduces two key ideas: (i) dual-hypothesis reasoning, a reasoning method for LLM guardra
arXiv:2610.10639v1 Announce Type: cross Abstract: Visible Chain-of-Thought (CoT) is often treated as a broadly useful reasoning instruction, yet analytics code generation combines natural-language amb
arXiv:2610.08528v1 Announce Type: cross Abstract: Clinical diagnosis is inherently a structured reasoning process, yet existing deep learning models often bypass this structure by mapping image featur
arXiv:2610.00559v1 Announce Type: new Abstract: Vision-Language Models (VLMs) have shown strong multimodal reasoning capabilities, yet whether they truly capture the physical consistency underlying re
arXiv:2610.01892v1 Announce Type: cross Abstract: Multimodal agents commonly generate free-form reasoning before each action. For small models, limited model capacity can result in lengthy reasoning t
arXiv:2606.13603v2 Announce Type: replace-cross Abstract: Chain-of-thought (CoT) reasoning is the dominant paradigm for inference-time scaling in language models, yet the causal influence of individua
arXiv:2609.39220v1 Announce Type: new Abstract: Process reward models (PRMs) have demonstrated notable effectiveness in test-time scaling and reinforcement learning by providing fine-grained signals f
arXiv:2609.39346v1 Announce Type: new Abstract: Large language models (LLMs) offer strong reasoning capabilities but are often costly to access through commercial APIs, while small language models (SL
arXiv:2609.39109v1 Announce Type: cross Abstract: Parameter-efficient reinforcement learning aims to improve reasoning with a compact trainable interface to a pretrained model. We introduce the Thalam
arXiv:2609.37054v1 Announce Type: new Abstract: Ensuring the safety of reasoning large language models (LLMs) across languages is essential for their reliable deployment. However, when exposed to jail
arXiv:2509.23140v2 Announce Type: replace Abstract: Recent advancements have endowed Large Language Models with impressive general reasoning capabilities. However, these reasoning models often perform
arXiv:2609.32690v1 Announce Type: new Abstract: Recent multimodal large language models (MLLMs) advance visual reasoning by strengthening both perception and reasoning, implicitly assuming a process t
arXiv:2609.34277v1 Announce Type: new Abstract: Pathological assessment relies on recognizing fine-grained visual details in histological images. Vision-language models (VLMs) increasingly support pat
arXiv:2609.27288v1 Announce Type: new Abstract: The Abstraction and Reasoning Corpus (ARC) has become a prominent benchmark for evaluating general abstract reasoning and fluid intelligence in AI model
arXiv:2609.24831v1 Announce Type: new Abstract: Agents have attracted considerably increasing attention due to the power of executing both Reasoning and Acting (ReAct) in open and dynamic environments
arXiv:2609.24710v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used in cybersecurity, where accurate analysis often requires multi-step and context-dependent reasoning
arXiv:2510.09302v2 Announce Type: replace-cross Abstract: While Multimodal Large Language Models (MLLMs) have achieved remarkable success in difficult purely textual mathematical reasoning tasks, even
arXiv:2609.14066v1 Announce Type: cross Abstract: Although existing multi-agent Retrieval-Augmented Generation (RAG) systems have demonstrated promise on complex multimodal reasoning tasks, they remai
arXiv:2609.14708v1 Announce Type: new Abstract: A core goal of efficient reasoning is to improve the accuracy-efficiency frontier. However, jointly improving reasoning accuracy and inference efficienc
arXiv:2609.14823v1 Announce Type: new Abstract: Multimodal clinical decision-making requires reliable reasoning over heterogeneous evidence from electronic health records, medical images, and physiolo
arXiv:2609.13267v1 Announce Type: new Abstract: Scientific charts encode quantities in axes, legends, and geometric marks, yet large vision-language models still treat them as natural photographs. Vis
arXiv:2609.04194v1 Announce Type: new Abstract: Reasoning traces from chain-of-thought models appear to offer a legible window into how a model arrives at its answer. A growing body of work treats the
I want to share a short paper just published exploring a simple but surprisingly effective optimization for sparse MoE reasoning models. The idea: Instead of retraining anything, we just tweak the rou
arXiv:2603.10359v2 Announce Type: replace Abstract: Distilling reasoning capabilities from Large Reasoning Models (LRMs) into smaller models is typically constrained by the limitations of rejection sa
arXiv:2510.15144v4 Announce Type: replace Abstract: Simulating human reasoning in open-ended tasks has long been a central aspiration in AI and cognitive science. While large language models now appro
arXiv:2608.28600v1 Announce Type: new Abstract: Large language models (LLMs) achieve strong performance on mathematical reasoning benchmarks, yet the mathematically meaningful skills underlying their
arXiv:2602.08336v3 Announce Type: replace Abstract: Unified multimodal models (UMMs) aim to integrate multimodal understanding and generation within a unified architecture, yet it remains unclear to w
arXiv:2509.22737v3 Announce Type: replace Abstract: Visual comparison reasoning is a fundamental capability of vision-language models (VLMs), covering judgments of object quantity, geometric dimension
arXiv:2608.26836v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable proficiency in natural language understanding, yet they struggle with strict multi-step reason
arXiv:2608.24082v1 Announce Type: cross Abstract: Large Language Models (LLMs) have shown strong capabilities in table reasoning, but their effectiveness degrades as tables grow in size and complexity
arXiv:2608.22637v1 Announce Type: new Abstract: Recent vision-language models (VLMs) show strong capabilities in robotic perception and spatial reasoning, yet their ability to reason about complex mec
arXiv:2608.22971v1 Announce Type: new Abstract: Embodied Reasoning constitutes a fundamental capability of embodied intelligence, serving as the basis for autonomous perception, reasoning, and interac
arXiv:2506.16633v3 Announce Type: replace-cross Abstract: Multimodal reasoning is a process of understanding, integrating and inferring information across different data modalities. It has recently at
arXiv:2608.19408v1 Announce Type: new Abstract: On-policy distillation (OPD) has emerged as an effective framework for post-training language models by pairing student-generated trajectories with dens
arXiv:2608.18591v1 Announce Type: new Abstract: Uniformly allocating inference reasoning budgets to LLMs is expensive and prone to over-thinking penalties; especially in document tasks where visual la
arXiv:2608.15006v1 Announce Type: cross Abstract: Although visual reasoning is crucial for solving complex geometry tasks, existing vision-language models rely heavily on text-only reasoning. Some rec
arXiv:2608.14290v1 Announce Type: new Abstract: We introduce Mobius-v0, an architecture that comprises a globally shared Memory (FFN) that stores knowledge vectors and multiple Reasoners (Self-Attn) t