Español

Explorar

Noticias de IA

30329 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
SimpleWikiSearch: A Clean Offline Wikipedia Environment for Agentic Search
arXiv cs.AI Research & Papers
Do Methods Support the Claims? Intra-Paper Verification for Peer Review
arXiv cs.AI Research & Papers
EvoPINN: Agentic Discovery of Executable Algorithms for Physics-Informed Neural Networks
arXiv cs.AI Research & Papers
MultivationBench: A Benchmark for Multimodal Sequential Motivation Reasoning
arXiv cs.AI Research & Papers
UrbanDS: A Graph-Guided LLM Multi-Agent System for Data-Intensive Urban Tasks
arXiv cs.AI Research & Papers
ForgetBench: Benchmarking Forgetting Dynamics of Long-Term Parametric Memory in Language …
arXiv cs.AI Research & Papers
OmegaUse-OfficeVal: Benchmarking LLM Agents on Long-Horizon Office-Suite Tasks with Econo…
arXiv cs.AI Research & Papers
The Art of Not Forgetting A Local Learning Architecture for Continual Learning
arXiv cs.AI Research & Papers
Living-Harness Is an Interactive-Agent Evolver
arXiv cs.AI Research & Papers
Entity Resolution in Practice: Lessons from a Self-Serve Pipeline
arXiv cs.AI Research & Papers
High-Order Markov Blanket Discovery via a k-Order Relaxation of the Faithfulness Assumpti…
arXiv cs.AI Research & Papers
Weight and Height Estimation from a Single Human Image Captured in the Wild
arXiv cs.AI Research & Papers
LLMET: Enabling Cross-Layer Evaluation of Emerging M3D Memories for Energy-Efficient LLM …
arXiv cs.AI Research & Papers
On-Policy Distillation for LLM Safety: A Routing Approach to Template-Robust Realignment
arXiv cs.AI Research & Papers
Pramana: A Composable, Domain-Specific Backend for Empirical Networking Research
arXiv cs.AI Research & Papers
The Age of AI Agents Demands A New Scientific Paradigm To Sustain Trustworthy Science
arXiv cs.AI Research & Papers
FPSGen: Flexible Point Cloud Scene Generation with BEV-Supported Transport Flows
arXiv cs.AI Research & Papers
AgenticCANN: Automated Ascend C Operator Generation via Knowledge-Augmented Agentic Evolu…
arXiv cs.AI Research & Papers
Evidence-Ledger Adjudication for Claim-Evidence Traceability
arXiv cs.AI Research & Papers
Fewer Clarifications, Better Code: Benchmarking Cross-Session Personalized Ambiguity Adap…
arXiv cs.AI Research & Papers
What Does It Take to Detect an AI Agent? Minimal Feature Sets for Behavioral Detection un…
arXiv cs.AI Research & Papers
Rethinking Self-Evolution: A Constrained Exploration-Exploitation Process for Mitigating …
arXiv cs.AI Research & Papers
Do Latent Channels Actually Communicate? A Causal Audit of Latent Multi-Agent LLM
arXiv cs.AI Research & Papers
Automorphism-Induced Non-Canonicity in Top-k Explanations of Graph Neural Networks
arXiv cs.AI Research & Papers
PUDA: An AI-Native Hardware Harness for Self-Driving Laboratories
arXiv cs.AI Research & Papers
Try Again, Don't Look Back: Blind Resampling Outperforms Self-Repair in Small Code Models
arXiv cs.AI Research & Papers
Scientific Knowledge Discovery in the Age of Large Language Models
arXiv cs.AI Research & Papers
(EC)2: Event-Centric Explainability for Cybersecurity Through Multi-Agent LLM Investigati…
arXiv cs.AI Research & Papers
Identifying Implicit Bias in LLM-based Chat AI Toward People with Intellectual Disabiliti…
arXiv cs.AI Research & Papers
TraceCLIP: Recovering Local Semantics from Patch-to-CLS Contributions