Español

Explorar

Noticias de IA

37834 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
GUI-CC: Benchmarking Contextual Consistency of GUI World Models as Agent Environments
arXiv cs.AI Research & Papers
A Formal Analysis of Agent Payment Protocols
arXiv cs.AI Research & Papers
SciTrue: Reliable Scientific Claim Validation with Frontier and Open Language Models at t…
arXiv cs.AI Research & Papers
Do Multimodal LLMs See Before They Read? Diagnosing Contextual Sycophancy
arXiv cs.AI Research & Papers
RePro: Proof-Verified Benchmark Rewriting for Reliable Evaluation of LLM Mathematical Pro…
arXiv cs.AI Research & Papers
RestoreBench: Can AI Agents Restore Power Flow Convergence?
arXiv cs.AI Research & Papers
Runtime-Independent Persistent Agents: Preserving Identity, Memory, and Code Across Model…
arXiv cs.AI Research & Papers
trajectory-judge: What Outcome-Only LLM Judges Miss on Agent Trajectories
arXiv cs.AI Research & Papers
Behaviorally Grounded User Profiles from the Wild for Personalized Alignment and Multi-Pe…
arXiv cs.AI Research & Papers
Asymmetries in Spontaneous and Instructed Deception
arXiv cs.AI Research & Papers
When Features Become Instances: Inverted Contrastive Learning for Unsupervised Feature Se…
arXiv cs.AI Research & Papers
ValueGraph: Value-Signal Guided Graph Pre-training for Contextualized User Representation
arXiv cs.AI Research & Papers
StudyBench: Can Self-Evolution Squeeze Textbooks for Olympiad Capability?
arXiv cs.AI Research & Papers
Don't Let the Model Write the YAML: Deterministic, Minimal-Diff GitOps Remediation from L…
arXiv cs.AI Research & Papers
In-Context Neurofeedback: Can LLMs Control Their Internal Representations through Privile…
arXiv cs.AI Research & Papers
EvoSCM: Scientific Belief Revision Through Causal Model Evolution and Experimentation
arXiv cs.AI Research & Papers
When Prediction Error Is Not Enough: Evaluating Nuisance-Function Prediction for Causal E…
arXiv cs.AI Research & Papers
Different representation learning objectives recover distinct latent structures from the …
arXiv cs.AI Research & Papers
Authority Bias in Conversational Search Engines for Academic Paper Recommendation
arXiv cs.AI Research & Papers
Neurosymbolics for Data Engineering: Achieving Long Context Token Reduction Without Finet…
arXiv cs.AI Research & Papers
Invalidation Contracts for Cross-Episode Agent Memory
arXiv cs.AI Research & Papers
The Irreversibility Budget: Fleet-Level Risk Accounting and Admission Control for Agent O…
arXiv cs.AI Research & Papers
EM^2Mem: Event-Centric Multimodal Memory for Large Language Models
arXiv cs.AI Research & Papers
Denoising Diffusion Generative Models Secretly Calculate Attentions
arXiv cs.AI Research & Papers
Residual Sparsification via Output Importance for Compressing Mixture-of-Experts LLMs
arXiv cs.AI Research & Papers
REVISE: Validity-Guided Recovery for Online Revisions in Agent Workflows
arXiv cs.AI Research & Papers
Same Request, Different Boundary: Evaluating Cybersecurity Assistance across Conversation…
arXiv cs.AI Research & Papers
EULER: Exploring Underused Links with Evidence-Checked Return for Multi-Agent Mathematica…
arXiv cs.AI Research & Papers
Vision Is Not Overhead: One-Pass Block Drafting for Lossless Speculative Decoding in Visi…
arXiv cs.AI Research & Papers
A Mathematical Framework for Legacy, Governance, and Decision Integrity in Enterprise AI