Search: “reasoning”

arXiv:2607.13069v1 Announce Type: new Abstract: Large language models produce chain-of-thought (CoT) reasoning that appears logically sound yet may not genuinely depend on its stated premises. We intr

Introduction RxBrain (Hy-Embodied-RxBrain-1.0) is a unified multimodal foundation model for embodied cognition — a single model that couples language reasoning with visual imagination to deliver three

arXiv:2607.07405v1 Announce Type: new Abstract: Tool-using LLM agents can violate the very policies they are deployed to enforce while appearing to complete the task successfully. In policy-permissive

arXiv:2607.05168v1 Announce Type: new Abstract: Why do intelligent systems need to perform explicit symbolic reasoning? Computer science has traditionally regarded symbolic reasoning as a defining com

arXiv:2602.20094v2 Announce Type: replace Abstract: As large language models (LLMs) witness increasing deployment in complex, high-stakes decision-making scenarios, it becomes imperative to ground the

arXiv:2606.27721v1 Announce Type: new Abstract: Compositional generalization, the ability to solve complex problems by combining solutions to simpler sub-problems, is a fundamental capability of both

Gary Marcus argues that large language models based on transformers quickly reach their limitations, prompting developers to add external tools as workarounds, while neurosymbolic AI—which combines ne

arXiv:2606.06679v1 Announce Type: cross Abstract: Court judgments are central to legal practice and jurisprudence, yet discourse analysis of Hong Kong judgments has received limited attention, owing l

arXiv:2606.05983v1 Announce Type: cross Abstract: Generative AI makes answers easy and understanding hard, and uncritical use invites cognitive offloading. Schools still measure unaided performance, y

arXiv:2606.02054v1 Announce Type: new Abstract: While Large Language Models (LLMs) achieve impressive performance on multi-step reasoning tasks, their reliability is persistently hindered by critical

arXiv:2605.28084v1 Announce Type: cross Abstract: Laughter is a complex social signal that conveys communicative intent beyond amusement. While prior work has focused on isolated laughter analysis tas

arXiv:2605.26918v1 Announce Type: new Abstract: Video generation models (VGMs) are rapidly entering classrooms, yet existing benchmarks evaluate only perceptual quality, intrinsic faithfulness, generi

arXiv:2605.14709v1 Announce Type: new Abstract: Recent unified models integrate multimodal understanding and generation within a single framework. However, an 'understanding-generation gap' persists,

arXiv:2510.03206v2 Announce Type: replace-cross Abstract: Diffusion language models, especially masked discrete diffusion models, have achieved great success recently. While there are some theoretical

arXiv:2605.09679v1 Announce Type: cross Abstract: Medical vision-language models (VLMs) and AI agents have made significant progress in learning to analyze and reason about clinical images. However, e

I can see this appears to be a social media post about a perceived shift in online discourse or cultural sentiment, but the truncated title and unavailable URL prevent me from accessing the full conte

arXiv:2605.04064v1 Announce Type: cross Abstract: Reasoning capabilities are crucial for reliable medical visual question answering (VQA); however, existing datasets rarely include reasoning explanati

arXiv:2601.06160v2 Announce Type: replace Abstract: Large Language Models (LLMs) often suffer from ''Reasoning Collapse'' on challenging mathematical reasoning tasks, where stochastic sampling produce

arXiv:2510.10930v2 Announce Type: replace-cross Abstract: Reasoning is not just about solving problems -- it is also about evaluating which problems are worth solving at all. Evaluations of artificial

arXiv:2604.23351v1 Announce Type: cross Abstract: Whether intermediate reasoning is computationally useful or merely explanatory depends on whether chain-of-thought (CoT) tokens contain task-relevant

arXiv:2510.10254v2 Announce Type: replace Abstract: Recent advances in large generative models have shown that simple autoregressive formulations, when scaled appropriately, can exhibit strong zero-sh

arXiv:2601.08919v2 Announce Type: replace-cross Abstract: A good deal of recent research has focused on how Large Language Models (LLMs) may be used as judges in place of humans to evaluate the qualit

arXiv:2604.21794v1 Announce Type: new Abstract: Multi-agent systems built on large language models have shown strong performance on complex reasoning tasks, yet most work focuses on agent roles and or

arXiv:2510.20505v4 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) remains brittle on multi-step questions and heterogeneous evidence sources, trading accuracy against late

arXiv:2604.20050v1 Announce Type: cross Abstract: Can Large Language Models (AI agents) aggregate dispersed private information through trading and reason about the knowledge of others by observing pr

arXiv:2604.19488v1 Announce Type: new Abstract: Large language models (LLMs) have achieved substantial advances in logical reasoning, yet they continue to lag behind human-level performance. In-contex

arXiv:2602.07794v3 Announce Type: replace Abstract: Large language models (LLMs) exhibit emergent behaviors suggestive of human-like reasoning. While recent work has identified structured conceptual r

arXiv:2604.15830v1 Announce Type: new Abstract: Reinforcement learning has become a powerful approach for enhancing large language model reasoning, but faces a fundamental dilemma: training on easy pr

arXiv:2604.14856v1 Announce Type: new Abstract: Understanding climate change requires reasoning over complex causal networks. Yet, existing causal discovery datasets predominantly capture explicit, di

Agentic AI orchestration has become the engine of enterprise AI success, but technology alone won’t get it there. The real differentiator is business-led execution that ties AI workflows directly to o

arXiv:2604.10660v1 Announce Type: cross Abstract: Recent research has devoted considerable effort to verifying the intermediate reasoning steps of chain-of-thought (CoT) trajectories using process rew

arXiv:2604.11699v1 Announce Type: cross Abstract: This work aims to improve the generalization of logic-based legal reasoning systems by integrating recent advances in NLP with legal-domain adaptive f

arXiv:2506.05014v2 Announce Type: replace-cross Abstract: We propose a novel, flexible, and efficient framework for designing Concept Bottleneck Models (CBMs) that enables practitioners to explicitly

arXiv:2604.10739v1 Announce Type: new Abstract: Scaling test-time compute through extended chains of thought has become a dominant paradigm for improving large language model reasoning. However, exist

arXiv:2604.09025v1 Announce Type: cross Abstract: Vision-language models (VLMs) have shown a promising ability in image geolocation, but they still lack structured geographic reasoning and the capacit

arXiv:2603.19714v2 Announce Type: replace Abstract: Looped language models (LoopLMs) perform iterative latent computation to refine internal representations, offering an alternative to explicit chain-

arXiv:2610.17473v1 Announce Type: new Abstract: Generative safety guards must classify requests correctly and return outputs that applications can parse. Reasoning guards can improve classification ac

arXiv:2610.19378v1 Announce Type: cross Abstract: We seek a hierarchical resolution of residual error under a composite learning objective as a principled mechanism for identifying and exploiting addi

arXiv:2610.14258v1 Announce Type: new Abstract: Regularization-based continual learning protects each parameter in proportion to an estimate of its importance, yet these estimates come from finite sam

arXiv:2610.11578v1 Announce Type: cross Abstract: Historical pull requests record the design decisions, compatibility constraints, and implementation patterns behind a codebase's current state. Experi

arXiv:2610.11223v1 Announce Type: cross Abstract: Large Reasoning Language Models (LRLMs) enable multi-step reasoning for robotic task planning, but continued reasoning can overwrite valid intermediat

arXiv:2610.12417v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) struggle with spatial, embodied, physical, and temporal reasoning. We hypothesize that these failures reflect

arXiv:2610.06950v1 Announce Type: cross Abstract: Injecting skills into a frozen language model currently costs a million parameters and a reinforcement-learning pipeline. We introduce method{}, a Sys

arXiv:2610.01458v1 Announce Type: new Abstract: Verifier-free reinforcement learning with probability-based rewards offers a promising way to train LLMs on general reasoning tasks where external verif

arXiv:2609.30151v1 Announce Type: cross Abstract: Asked to choose between candidates and explain the choice, a language model often rejects a rival by naming a fact its profile lacks: no director, no

arXiv:2609.27517v1 Announce Type: new Abstract: Negation does not carry a uniform interpretation across domains. In legal, regulatory, and medical reasoning, the intended interpretation depends on the