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
CoT-Core: Accelerating LLM Evaluation via CoT-Aware Coreset Selection
arXiv cs.AI Research & Papers
Request-Level Energy Attribution for Batched LLM Serving
arXiv cs.AI Research & Papers
RAG-TESTER: Automated End-to-End Testing of Retrieval-Augmented Large Language Models
arXiv cs.AI Research & Papers
Meritocratic Fairness via $K$-Shapley Values in Budgeted Combinatorial Bandits with Full-…
arXiv cs.AI Research & Papers
MEGRAG: Multi-Granular Evidence Graphs for Answer-Aware Multi-Hop RAG
arXiv cs.AI Research & Papers
Scoring Rules! Statistical and Strategic Alignment for Text Evaluation Metrics
arXiv cs.AI Research & Papers
A New Theory of Value for Post-AGI Economics
arXiv cs.AI Research & Papers
TCPO: Turn-Level Credit Policy Optimization
arXiv cs.AI Research & Papers
When Memory Becomes Authority: Benchmarking Authority Collapse at the Memory Consolidatio…
arXiv cs.AI Research & Papers
Beyond Routing Saturation: A Long-Horizon Class-Incremental Perspective on Expert Routing…
arXiv cs.AI Research & Papers
Where Reasoning Diverges: Localized Multi-Agent Debate
arXiv cs.AI Security & Safety
MineGrad: Gradient Inversion Attacks on LoRA Fine-Tuning
arXiv cs.AI Research & Papers
V-Mem: Modality-Routed Retrieval for Long-Term Multimodal Agentic Memory
arXiv cs.AI Research & Papers
Post-Training on Office Work Improves Software Engineering: A Behavioral Account of Cross…
arXiv cs.AI Security & Safety
Salami Attack: Stealthy Collusive Memory Poisoning against OpenClaw
arXiv cs.AI Research & Papers
FRAMES: Guarded and Dual-Objective Skill Evolution for Agents in Policy-Governed Enterpri…
arXiv cs.AI Research & Papers
Rewriting or Reweighting? A Geometric Account in Language Models
arXiv cs.AI Research & Papers
Computing with Agentic Oracles
arXiv cs.AI Research & Papers
Physics-Informed Neural Networks for Complex Eigenfrequency Identification and Mode Struc…
arXiv cs.AI Research & Papers
ReasonCast: Towards Explainable Time Series Forecasting with Reasoning
arXiv cs.AI Research & Papers
Beyond Single-Use Tokens: Durable Authorization State for Replay-Resistant LLM Agent Acti…
arXiv cs.AI Research & Papers
LaCache: Robust Semantic Caching for LLM Serving
arXiv cs.AI Research & Papers
DAPD: Dual-Anchored Policy Distillation
arXiv cs.AI Research & Papers
From Simple QA to Deep Research: A Verifiable Benchmark Constructed through Iterative Tas…
arXiv cs.AI Research & Papers
A Contractualist Argumentation Framework for Moral Decision-Making
arXiv cs.AI Research & Papers
HALT: Verification-Aware Stopping for Retrieval-Augmented Search Agents
arXiv cs.AI Research & Papers
Before Reasoning Fails: Pre-Evidence Procedural Failures in Agentic RAG
arXiv cs.AI Research & Papers
HPFA: Hypergraph-Based Paired Failure Attribution for LLM Reasoning
arXiv cs.AI Research & Papers
Conservation laws determine what physical learning remembers
arXiv cs.AI Research & Papers
GRAIN: Molecules Are Not the Right Granularity -- Active-Ingredient Modeling for Safe Med…