Español

Explorar

Noticias de IA

21272 elementos — filtrados, clasificados y sin duplicados

Todos Models & Releases Research & Papers Funding & M&A Policy & Regulation Product Launches Industry Moves Developer Tooling Opinion & Editorial Security & Safety Other
arXiv cs.AI Research & Papers
S2MAM: Semi-supervised Meta Additive Model for Robust Estimation and Variable Selection
arXiv cs.AI Research & Papers
DynaSchedBench: Calibrated Dynamic Scheduling Benchmarks and Observability Paradox in LLM…
arXiv cs.AI Research & Papers
On the Origin of Synthetic Information by Means of Steganographic Inheritance
arXiv cs.AI Research & Papers
Anomaly as Non-Conformity via Training-Free Graph Laplacian Energy Minimization
arXiv cs.AI Research & Papers
Reward Bias Substitution: Single-Axis Bias Mitigations Redirect Optimization Pressure
arXiv cs.AI Research & Papers
PetroBench: A Benchmark for Large Language Models in Petroleum Engineering
arXiv cs.AI Research & Papers
MolLingo: Molecule-Native Representations for LLM-Powered Scientific Agents
arXiv cs.AI Research & Papers
LACUNA: Safe Agents as Recursive Program Holes
arXiv cs.AI Research & Papers
EgoBench: An Interactive Egocentric Multimodal Benchmark for Tool-Using Agents
arXiv cs.AI Research & Papers
SPARC: Spatial-Aware Path Planning via Attentive Agent Communication
arXiv cs.AI Research & Papers
A Fixed-Budget, Cluster-Aware Standard for LLM-as-a-Judge Evaluation: A Multi-Hop RAG Str…
arXiv cs.AI Research & Papers
A Unified Framework for the Evaluation of LLM Agentic Capabilities
arXiv cs.AI Research & Papers
A Query Engine for the Agents
arXiv cs.AI Research & Papers
Diagnosing Live Within-Policy Instruction Conflicts in LLM Agents with Witnessed Resoluti…
arXiv cs.AI Research & Papers
Relational Semantic Reasoning on 3D Scene Graphs for Open World Interactive Object Search
arXiv cs.AI Research & Papers
Decoupling Reasoning and Confidence: Resurrecting Calibration in Reinforcement Learning f…
arXiv cs.AI Research & Papers
MAVEN A Multi-Agent Framework for Multicultural Text-to-Video Generation
arXiv cs.AI Research & Papers
ArcVQ-VAE: A Spherical Vector Quantization Framework with ArcCosine Additive Margin
arXiv cs.AI Research & Papers
HO-SFL: Hybrid-Order Split Federated Learning with Backprop-Free Clients and Dimension-Fr…
arXiv cs.AI Research & Papers
PEAM: Parametric Embodied Agent Memory through Contrastive Internalization of Experience …
arXiv cs.AI Research & Papers
Sense Representations Are Inducible Interfaces
arXiv cs.AI Research & Papers
Identifying and Understanding Human Values in Text: A Tailorable LLM-based Architecture
arXiv cs.AI Research & Papers
Behavioural Analysis of Alignment Faking
arXiv cs.AI Research & Papers
DeepSciVerify: Verifying Scientific Claim--Citation Alignment via LLM-Driven Evidence Esc…
arXiv cs.AI Research & Papers
Why LLMs Fail at Causal Discovery and How Interventional Agents Escape
arXiv cs.AI Research & Papers
RULER: Representation-Level Verification of Machine Unlearning
arXiv cs.AI Research & Papers
Cyberbullying Governance on Social Media: A Unified Framework from Content Identification…
arXiv cs.AI Research & Papers
Hybrid Neural World Models
arXiv cs.AI Research & Papers
SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces
arXiv cs.AI Research & Papers
A Policy-Driven Runtime Layer for Agentic LLM Serving