Explorar

Noticias de IA

27413 elementos — filtrados, clasificados y sin duplicados

arXiv cs.AI Research & Papers
Plan Then Action:High-Level Planning Guidance Reinforcement Learning for LLM Reasoning
arXiv cs.AI Research & Papers
How Chain-of-Thought Works? Tracing Information Flow from Decoding, Projection, and Activ…
arXiv cs.AI Research & Papers
LiPUP-MA: A Residential Experience-centric Multi-Agent Framework for Living-in-the-loop P…
arXiv cs.AI Research & Papers
Risk Averse Alert Prioritization for IDS Using Subnormal Gaussian Fuzzy Models
arXiv cs.AI Research & Papers
Lost in Sampling: Assessing Lexical Reachability in LLMs via the Word Coverage Score (WCS)
arXiv cs.AI Research & Papers
Many Logics, One Methodology: A Plea for Logical Pluralism in Formalised Reasoning (prepr…
arXiv cs.AI Research & Papers
Algebraic Semantics of Governed Execution: Monoidal Categories, Effect Algebras, and Cote…
arXiv cs.AI Research & Papers
Mechanized Foundations of Structural Governance: Machine-Checked Proofs for Governed Inte…
arXiv cs.AI Research & Papers
Mind the Tool Failures: Achieving Synergistic Tool Gains for Medical Agents
arXiv cs.AI Research & Papers
MedCollab: IBIS-Guided Multi-Agent Collaboration with Hierarchical Disease Relation Chain…
arXiv cs.AI Research & Papers
Elias in the Lighthouse, Again? Diagnosing Low Diversity in LLM Stories
arXiv cs.AI Research & Papers
OmniToM: Benchmarking Theory of Mind in LLMs via Explicit Belief Modeling
arXiv cs.AI Research & Papers
Pretraining Data Exposure in Large Language Models: A Survey of Membership Inference, Dat…
arXiv cs.AI Research & Papers
Bridging Classification and Reconstruction: Cooperative Time Series Anomaly Detection
arXiv cs.AI Research & Papers
Yes, Q-learning Helps Offline In-Context RL
arXiv cs.AI Research & Papers
UnityMAS-O: A General RL Optimization Framework for LLM-Based Multi-Agent Systems
arXiv cs.AI Research & Papers
Self-Cascaded Diffusion Models for Arbitrary-Scale Image Super-Resolution
arXiv cs.AI Research & Papers
Generative Animations: A Multi-Model Pipeline for Prompt-Driven Motion Synthesis
arXiv cs.AI Research & Papers
Phase-Type Variational Autoencoders for Heavy-Tailed Data
arXiv cs.AI Research & Papers
Beyond Questions: Evaluating What Large Language Models (Actually) Know
arXiv cs.AI Research & Papers
MedGuideX: Internalizing Decision Logic from Executable Guidelines into Large Language Mo…
arXiv cs.AI Research & Papers
MobileExplorer: Accelerating On-Device Inference for Mobile GUI Agents via Online Explora…
arXiv cs.AI Research & Papers
VesselSim: learning 3D blood vessel segmentation without expert annotations
arXiv cs.AI Research & Papers
CmIVTP: Cross-modal Interaction-based Vessel Trajectory Prediction for Maritime Intellige…
arXiv cs.AI Research & Papers
On the Push-Based Asynchronous Federated Learning: A Bias-Correction Aggregation Approach
arXiv cs.AI Research & Papers
ORLoopBench: Solver-in-the-Loop Benchmarks for Self-Correction and Behavioral Rationality…
arXiv cs.AI Research & Papers
AgentAtlas: Beyond Outcome Leaderboards for LLM Agents
arXiv cs.AI Research & Papers
CogAdapt: Transferring Clinical ECG Foundation Models to Wearable Cognitive Load Assessme…
arXiv cs.AI Research & Papers
TSFMAudit: Data Contamination Auditing in Forecasting Time Series Foundation Models
arXiv cs.AI Research & Papers
Exploiting Local Dynamics Regularity for Reusable Skills in Offline Hierarchical RL