Search: “reasoning”

arXiv:2608.08960v1 Announce Type: new Abstract: Multi-step language-model agents repeatedly process growing interaction histories, leading to substantial context costs. Vision--text compression reduce

Every few decades, someone announces that science has reached its end. In 1903, the revered physicist Albert Michelson wrote that the “facts of physical science have all been discovered.” In the 1980s

arXiv:2608.05832v1 Announce Type: new Abstract: Large language models (LLMs) excel in structured tasks but struggle with dynamic social interactions, where success requires long-term goal coordination

arXiv:2608.04457v1 Announce Type: cross Abstract: As 'AI Scientists' emerge to drive research via the Model Context Protocol (MCP), systems relying on ephemeral scripts will fail. The sheer scale of s

arXiv:2608.04452v1 Announce Type: cross Abstract: High-resolution pixels and crop or zoom tools give multimodal large language models the ability to inspect an image, but they do not provide a reliabl

arXiv:2608.04309v1 Announce Type: new Abstract: We present a structured large-language-model (LLM) architecture for zero-shot human--robot coordination in a cooperative construction task with private

arXiv:2608.04175v1 Announce Type: new Abstract: Edge platforms used for aerial observation must interpret aircraft imagery under limited memory, limited compute, and intermittent connectivity. This se

arXiv:2608.03161v1 Announce Type: new Abstract: Lecture videos distribute knowledge across speech, slide text, diagrams, equations, and presentation order, which transcript-only retrieval does not ful

arXiv:2608.02615v1 Announce Type: cross Abstract: Cancer diagnosis and characterization require integrating complementary evidence from radiology, pathology, genomics, and clinical metadata. However,

arXiv:2608.01463v2 Announce Type: replace Abstract: Multi-agent debate commonly exchanges complete rationales even when disagreements concern only a few intermediate claims. We introduce Localized Mul

arXiv:2602.10880v2 Announce Type: replace Abstract: Vision-Language Models (VLMs) have shown promise in generating plotting code from chart images, yet achieving structural fidelity remains challengin

arXiv:2608.02392v1 Announce Type: new Abstract: A wearable assistant should both answer questions about its visual history and recognize when that history is useful to the present situation. Existing

arXiv:2608.01954v1 Announce Type: new Abstract: Fixed-layout indoor furniture styling requires selecting assets that form a coherent room without changing the prescribed furniture categories, position

arXiv:2607.27069v1 Announce Type: new Abstract: Closed yes/no spatial benchmarks can reward a correct answer even when the image adds little support beyond no-image contexts. Under a fixed forced-choi

arXiv:2607.25600v1 Announce Type: cross Abstract: Retrieval-augmented generation improves knowledge-intensive question answering, but indiscriminate retrieval can introduce irrelevant evidence and unn

arXiv:2607.25962v1 Announce Type: new Abstract: Recent generative models can produce images with few obvious visual artifacts, weakening detectors and explanations that rely only on surface appearance

arXiv:2607.25789v1 Announce Type: new Abstract: Sentimental Image Captioning (SIC) requires balancing emotional expression with visual fidelity. Existing methods often struggle with this trade-off, le

arXiv:2607.21558v1 Announce Type: new Abstract: Building socially calibrated large language models, which can learn from others without simply yielding to them, requires more than reducing sycophancy

arXiv:2607.20056v1 Announce Type: cross Abstract: Aspect-based sentiment analysis (ABSA) in Arabic must recover both explicitly stated aspects and implicit aspects that are never named in the text. Im

arXiv:2601.02023v2 Announce Type: replace-cross Abstract: As Large Language Models (LLMs) increasingly utilize massive context windows as working memory for autonomous tasks, their reliability fluctua

arXiv:2607.06764v1 Announce Type: new Abstract: Recent progress on ARC-AGI-1 from disclosed architectures has come broadly from two regimes: heavy test-time compute over frontier models (evolutionary

arXiv:2607.06757v1 Announce Type: new Abstract: Agent-based modeling (ABM) has the capability to model millions of individuals and their interactions, which is useful for policy making. However, ABMs

arXiv:2607.07674v1 Announce Type: cross Abstract: Group Relative Policy Optimization (GRPO) stalls on a model's hardest problems: when no rollout in a group succeeds, the group-relative advantages van

arXiv:2607.07316v1 Announce Type: new Abstract: This article offers a comprehensive overview of mechanistic interpretability, an emerging field that seeks to reverse-engineer the internal algorithms o

arXiv:2607.07395v1 Announce Type: cross Abstract: Reliable confidence estimation remains a key limitation of test-time adaptation in vision-language models (VLMs), where prompt tuning improves zero-sh

arXiv:2606.14948v2 Announce Type: replace-cross Abstract: LLMs have substantially improved software engineering yet real-world development requires architectural understanding. Such understanding is p

arXiv:2607.05428v1 Announce Type: cross Abstract: We present Charlie, an on-premise multi-agent Retrieval-Augmented Generation (RAG) system for structured evidential processing in digital forensic env

arXiv:2607.05493v1 Announce Type: new Abstract: Natural-language queries about 3D environments become actionable when responses are verifiable and metric. Verifiability requires explicit grounding to

arXiv:2607.03166v1 Announce Type: cross Abstract: Template-based contrastive synthesis is scalable, but its candidates often differ only in a few entity-slots while sequence-level optimization spreads

arXiv:2607.02175v1 Announce Type: new Abstract: Multiple-choice medical benchmarks are increasingly saturated, and recent rubric-based evaluations such as HealthBench have shown that open-ended clinic

arXiv:2603.28545v2 Announce Type: replace Abstract: Vision-Language-Action (VLA) models and world-action models have emerged as central paradigms for general-purpose robotic intelligence, yet their em

arXiv:2607.00434v1 Announce Type: new Abstract: Vision-language models (VLMs) have become a paradigm for multimodal learning, yet remain unstable due to object hallucination, weak visual grounding, an

arXiv:2607.01223v1 Announce Type: new Abstract: When should an AI system's answer be trusted? Formal proof assistants offer certainty but cannot reach most of the problem distribution; scalar LLM judg

arXiv:2607.00447v1 Announce Type: new Abstract: Large language models often produce hallucinated answers that violate prompt-level constraints. A key diagnostic question is whether these failures refl

arXiv:2506.17294v3 Announce Type: replace-cross Abstract: The advent of artificial intelligence has propelled AI-Generated Game Commentary (AI-GGC) into a rapidly expanding research area, offering adv

arXiv:2606.31260v1 Announce Type: new Abstract: Embodied task planning asks an agent to turn a natural-language instruction into an executable sequence of actions in a physical scene, and is a buildin

arXiv:2606.30686v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) systems, built on pretrained vision-language models (VLMs), have shown rapidly improving performance on robot manipulatio

arXiv:2606.29194v1 Announce Type: new Abstract: Automated alpha mining holds the scoring function fixed and varies the search algorithm over it. A search that converges against a fixed scorer overfits

arXiv:2606.29689v1 Announce Type: new Abstract: Open-ended aesthetic critique is a challenge for multimodal large language models (MLLMs): unlike multiple-choice aesthetic benchmarks, it has no single

arXiv:2606.30627v1 Announce Type: cross Abstract: Conservative offline training is widely advocated as a safe foundation for subsequent online adaptation: if a policy stays close to well-supported beh

arXiv:2602.22284v3 Announce Type: replace Abstract: Recent advancements in deep learning have actively addressed complex challenges within the Computer-Aided Design (CAD) domain.However, most existing

arXiv:2606.26366v1 Announce Type: new Abstract: Standard chain-of-thought on moral dilemmas exhibits two failure modes: stakeholder collapse (the trace names at most one party with a stake in the outc

arXiv:2606.24948v1 Announce Type: new Abstract: Knowledge graph embedding (KGE) models predict single-hop links well but have no mechanism for zero-shot compositional queries: multi-hop questions whos

arXiv:2606.24950v1 Announce Type: new Abstract: Financial decision-making is contextual: forecasting prices, valuing companies, and assessing event exposure weigh price history, accounting fundamental

arXiv:2606.25206v1 Announce Type: cross Abstract: Long-term robot deployment requires a compact and scalable memory that preserves fine-grained visual semantics, grounds observations in space and time

arXiv:2606.24235v1 Announce Type: new Abstract: Spatial proteomics enables single-cell-resolution characterization of protein expression within tissue architecture, playing a critical role in understa