Live intelligence

Latest AI updates

1,750 updates

Research Editor selected

BLPO: Beyond-Local Policy Optimization for Long-Horizon LLM Agents

BLPO is a new reinforcement learning method for long-horizon LLM agents that estimates task-progress advantages from shared experience across tasks and updates, avoiding the need for a learned critic or extra rollouts. It summarizes trajectory prefixes into task-progress states and abstracts actions by function, using a global memory with balanced aggregation to control bias. Experiments on ALFWorld and WebShop with 1.5B and 7B policies show improved task success and faster learning under matched training budgets.

Why it matters: This paper introduces a concrete algorithmic improvement for training LLM agents on long-horizon tasks, with empirical gains on standard benchmarks, making it valuable for researchers and practitioners.

arxiv5d agoScore 85

LLM agentsreinforcement learninglong-horizon tasks

Research

Q-CamTuning: Multimodal LLM for Fine-Grained Quality Reasoning in Livestreaming Camera Tuning

The paper introduces Q-CamTuning, a multimodal large language model designed for automatic camera tuning in livestreaming. It addresses limitations of existing IQA methods by enabling fine-grained quality comparison and providing reasoning-based adjustment suggestions. The authors built a new instruction tuning dataset, FGLive-Comments, and a progressive perception-evidence-guidance framework. Experiments show Q-CamTuning outperforms existing IQA models in quality scoring and pair ranking, with user studies confirming its practical suggestions.

arxiv5d agoScore 78

Multimodal Large Language ModelsImage Quality AssessmentCamera Tuning

Research Editor selected

Global pooling beats per-ship and adaptation models for ship fuel consumption prediction

A comparative study of 11 fuel oil consumption prediction methods on 21 vessels finds that global pooling—one model using ship identity and specifications—outperforms per-ship and adaptation-based approaches in all settings. Global LightGBM achieves 8.92% MAPE vs 11.14% for per-ship LightGBM, and global models of five architectures including a Transformer beat federated models. The global model also supports zero-shot prediction for new vessels, with accuracy comparable to vessel-specific adaptation after adding first records.

Why it matters: Provides a rigorous, fair comparison showing global models are superior for fleet-wide fuel prediction, with practical implications for voyage planning and new vessel deployment.

arxiv5d agoScore 88

ship fuel predictionglobal modelszero-shot prediction

Research

VideoEditor-MoE: Scaling Complex Video Editing with Mixture of Experts

VideoEditor-MoE is an open-source mixture-of-experts framework for complex video editing, introducing MoE-Attention with routed key-value experts to expand attention capacity. It scales from a 5B base model to 14B and 56B parameters with about 8B active per token, showing benefits over explicit expert guidance and MLP-only architectures. Analyses reveal that routing is driven by content and noise levels rather than human-defined categories, and decoupled weight decay stabilizes expert scaling.

arxiv5d agoScore 78

Video EditingMixture of ExpertsModel Scaling

Research

LLM Pipeline for Flexible Information Extraction from Criminal Court Decisions

This paper presents an LLM-based pipeline for structuring criminal verdicts into datasets for empirical legal research, using attribute exploration, span extraction, and value normalization guided by expert-refinable instructions. Evaluated on DUI and DDB traffic offenses, it shows that revising instructions improved extraction accuracy from 52% to 70% and increased human annotator agreement. The study also highlights that model consistency does not guarantee correctness)Skip, and disagreement between annotators and models can reveal unclear instructions.

arxiv5d agoScore 72

Large Language ModelsLegal Text MiningData Annotation

Research Editor selected

PRIME: Predictive Routing of Interventions for Scientific Ideation

PRIME is a plug-and-play decision layer that improves LLM-generated scientific ideas by routing feedback to the right revision scope. It addresses the diagnosis-intervention mismatch where the location of a weakness doesn't determine the best revision target. PRIME uses structural attribution, counterfactual routing, and intervention execution, showing gains across benchmarks and ideators.

Why it matters: This paper introduces a novel method to improve AI-driven scientific ideation, with concrete validation and clear performance gains, making it valuable for researchers and practitioners.

arxiv5d agoScore 82

AI researchscientific discoveryLLM evaluation

Research Editor selected

Networked AI: A New Architecture for Scalable, Adaptive Intelligence

This paper introduces Networked AI, a system of interacting, heterogeneous AI agents organized in a hierarchical layered architecture (Agent, Interaction, Regulation layers). It synthesizes data science, signal processing, and control theory to achieve near-linear scaling in resource demand, unlike exponential growth in monolithic systems. The framework enables online adaptation to novel environments and autonomous evolution toward application-specific intelligence, with applications in IoT, embodied, spatial, and industrial intelligence.

Why it matters: Presents a concrete architectural and theoretical framework addressing scalability and adaptability limitations of current AI, with broad application implications.

arxiv5d agoScore 85

AI architecturemulti-agent systemsscalability

Research Editor selected

Towards a Trustworthy and Governable Internet of Agentics: An Architectural Perspective

This perspective paper proposes an architectural framework for the Internet of Agentics (IoA), treating heterogeneous AI agents as governable service participants. It organizes the landscape into a three-layer progression from fragmented ecosystems to interoperable agents and trustworthy autonomy, covering protocol stacks (MCP, A2A, AGENTS.md), systems abstractions (orchestration, gateways, registries), and services computing principles. The paper argues that agentic systems reinterpret SOA and microservices concerns at the level of cognitive capabilities.

Why it matters: Provides a structured architectural view of emerging agent interoperability and governance standards, valuable for researchers and practitioners navigating the agent ecosystem.

arxiv5d agoScore 82

agent interoperabilityagent governanceservice-oriented architecture

Research Editor selected

PACERec: Progressive Adaptation of LLM Item Embeddings with Collaborative Evidence for Recommendation

PACERec is an ID-free framework that adapts static LLM item embeddings for sequential recommendation by learning a shared velocity field via frequency-weighted flow matching. It transfers interaction contexts from frequent to long-tail items, improving recommendation across the catalog. Experiments on three datasets show gains over baselines in overall and long-tail performance.

Why it matters: This paper presents a concrete, novel method addressing a known limitation of LLM embeddings in recommendation, with experimental validation.

arxiv5d agoScore 85

Large Language ModelsRecommendation SystemsEmbedding Adaptation

Research

MIRA: Reinforcing Multimodal Reasoning via Deceptive Contextual Augmentation

MIRA is a training framework that improves multimodal reasoning robustness by injecting deceptive visual contexts during training, creating 'hard traps' that stress-test models against misleading information. It also introduces a group-wise reflection-triggering mechanism for autonomous error detection and correction. Experiments show an average 7% improvement on in-domain benchmarks without human annotations.

arxiv5d agoScore 78

multimodal reasoningreinforcement learningrobustness

Research

Avatar Intelligence: A Paradigm for Persistent Personal Agents

This paper proposes Avatar Intelligence, a paradigm for persistent personal AI agents that represent users' goals, values, and constraints through sustained decision delegation. It introduces a maturity roadmap from human-directed execution to autonomous operation and an Agentic Oversight Index (AOI) for evaluating value against oversight burden. The authors identify three core research challenges: identity-continuous personalization, user-situated evolution via Rehearsal Engineering, and safety mechanisms combining technical control with accountability.

arxiv5d agoScore 78

AI agentshuman-AI interactionagentic oversight

Research

Hybrid Retrieval, NLI and Open-source LLMs for Scientific Claim Verification

This experimental study evaluates claim verification on scientific texts using a hybrid retrieval method (semantic + BM25) and compares an NLI baseline (DeBERTa) with three open-source LLMs (Llama 3.1, Qwen3, Mistral). Qwen3 achieves the highest Macro-F1 (0.7937), while the NLI baseline lags at 0.3157. A conservative fusion rule that requires agreement between NLI and LLM degrades performance, as correct LLM predictions are often overturned by NLI disagreements.

arxiv5d agoScore 78

scientific claim verificationnatural language inferencelarge language models

Research Editor selected

Fine-Grained Hierarchy and Benchmark for State Tracking in Language Models

This paper introduces a hierarchy of word problems for state tracking, from simple immutable assignments to general finite-state tracking, and proves that transformers cannot length-generalize on all aperiodic problems while Gated DeltaNet can. The authors build StateBench, a 4-tier benchmark, and show that both trained and pretrained models, including frontier ones, fail to robustly solve even soluble state tracking.

Why it matters: Provides a new theoretical hierarchy and benchmark that clarifies architectural differences in state tracking, with practical implications for model evaluation and development.

arxiv5d agoScore 85

state trackinglanguage model architectureslength generalization

Research Editor selected

LUCA: A Synthetic World for Evaluating Experimental Reasoning in AI Agents

LUCA is a configurable synthetic environment that tests AI agents' experimental reasoning by having them learn unknown regulatory systems through budgeted experimentsholistically. It separates evaluation of experiment selection, prediction, diagnosis, and intervention, revealing that these capabilities dissociate sharply across frontier LLMs. For example, diagnosis varies 7x across models while prediction varies only 1.4x, and agents often rescue systems while misdiagnosing faults. The framework exposes hidden failures like performing the right experiment but failing to use the evidence.

Why it matters: Provides a novel benchmark for dissecting AI agent reasoning processes, with concrete findings on capability dissociation and failure modes, valuable for AI safety and evaluation research.

arxiv5d agoScore 82

AI evaluationexperimental agentsLLM capabilities

Research Editor selected

Multimodal Prompt Learning with Dual-Granularity Contrastive Alignment for Preoperative Prediction of Lung Adenocarcinoma Invasiveness Using 3D CT

This paper presents a multimodal prompt-learning framework that combines 3D CT images with text prompts derived from clinical reports to predict lung adenocarcinoma invasiveness. The method uses a 3D ResNet-CBAM encoder and a frozen RadBERT with learnable prompts, plus global and local contrastive alignment modules. On a test set of 1,593 nodules, it achieved 87.92% accuracy, 87.78% F1-score, and 0.9499 AUC, significantly outperforming an image-only baseline. The framework requires only CT images at inference, preserving clinical usability.

Why it matters: The paper reports a concrete, recent AI development with strong quantitative results and a practical CT-only inference workflow, offering clear value for medical imaging and multimodal learning readers.

arxiv5d agoScore 82

Multimodal AIMedical Image AnalysisPrompt Learning

Research Editor selected

SCOPE: Progressive Skill Exploration for Long-Horizon LLM Web Agents

SCOPE is a short-to-long learning framework that decomposes complex web task exploration into gradual skill discovery, orchestration, and expansion. It iteratively builds skill chains from local skills and failure experiences, then distills them into policy parameters. Experiments on WebArena, WebVoyager, and WebShop show relative gains of 3.9% to 18.6% over strong baselines.

Why it matters: Provides a concrete, novel method with benchmark results for improving LLM web agents on long-horizon tasks, valuable for researchers and practitioners.

arxiv5d agoScore 85

LLM web agentsskill acquisitionlong-horizon tasks

Research Editor selected

ComplianceAtlas: A Taxonomy-Driven Agentic AI Framework for Automated AI Act Gap Analysis and Remediation

The paper introduces ComplianceAtlas, a taxonomy-driven agentic framework for automating AI Act compliance gap analysis. It uses two specialized agents—Gap Extraction and Remediation Planning—to identify and rank remediation actions. Evaluated on 9 AI systems, it achieves a gap-type F1 of 0.831 and remediation P@5 of 0.872, outperforming baselines. The framework supports human-in-the-loop compliance workflows.

Why it matters: Provides a concrete, novel AI framework with strong benchmark results for regulatory compliance, a high-value application area.

arxiv5d agoScore 85

AI regulationagentic AIcompliance automation

Research Editor selected

CUA-Master: Recursive Improvement Framework for Computer-Use Agents

CUA-Master introduces a nested double-loop recursive improvement framework for computer-use agents (CUAs), combining an outer world-data-model flywheel with an inner data-level flywheel that mines authentic workflows from instructional videos and synthesizes diverse, verifiable tasks. The framework includes a feedback-guided snapshot-rollback retry mechanism for reliable trajectory collection. Experiments show CUA-Master-27B achieves competitive scores on OSWorld, WeaveBench, and Agents' Last Exam, with continuous gains across iterations.

Why it matters: This paper presents a novel recursive training framework with concrete benchmark results, addressing key limitations in CUA development and offering practical improvements.

arxiv5d agoScore 85

computer-use agentsrecursive learningdata generation