Español

Explorar

Noticias de IA

30239 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
REFLEX: Rethinking MoE Inference as Refinement-Aware Compute Allocation in Diffusion Lang…
arXiv cs.AI Research & Papers
Cognitive Demand Steering for Adaptive Meta-Reasoning in Large Language Models
arXiv cs.AI Research & Papers
CoEvo-Mem: Co-Evolving Retrieval Policy and Memory Bank for LLM Agents
arXiv cs.AI Research & Papers
Less Is More: Tuning Configurable Systems with Imperfect Fidelity
arXiv cs.AI Research & Papers
Open-Set Visual Text Forensics via Sparse-Constraint Rectified Flow
arXiv cs.AI Research & Papers
Linguistic Context Recodes Visual Representations in Vision-Language Models
arXiv cs.AI Research & Papers
Optimization and Constraint Modeling using LLMs with a Retrieval Augmented Generation Pro…
arXiv cs.AI Research & Papers
Constructing Executable Analytical Knowledge Representations for Meta-Analysis Synthesis …
arXiv cs.AI Research & Papers
Shared Organizational Memory for Enterprise Coding Agents: System Design and Deployment S…
arXiv cs.AI Research & Papers
Geometric Analysis of Token Selection in Multi-Head Attention
arXiv cs.AI Research & Papers
Agentic Incident Response through Digital Twin-Enhanced Multiscale Planning
arXiv cs.AI Research & Papers
Trust and Its Betrayal under Three Representational Strategies
arXiv cs.AI Research & Papers
RING: Retrieval-Internalized Generation for Continual Large-Scale Knowledge Injection
arXiv cs.AI Research & Papers
Auditing Discovery Claims: A Two-Sided Criterion for Agentic Science, with the Negative S…
arXiv cs.AI Research & Papers
G-ReAct: Graph-Guided Deep Search via Structure-State Co-Evolution
arXiv cs.AI Research & Papers
Trustworthiness Costs of Domain Adaptation in Small Language Models:A Cross-Architecture …
arXiv cs.AI Research & Papers
Emergence Invariance: From Symbolized Thought to Interface Refinement
arXiv cs.AI Research & Papers
Deferred Exposure of Future Trajectories for Verifiable Reasoning in Autonomous Driving V…
arXiv cs.AI Research & Papers
StructureClaw: Traceable LLM Agents and an Executable Benchmark for Structural Engineerin…
arXiv cs.AI Research & Papers
GABench: A Comprehensive Benchmark for Evaluating LLM Agents on Graph Analysis Tasks
arXiv cs.AI Research & Papers
GISAgentBench: A Practitioner-Sourced Benchmark for Evaluating LLM Agents on GIS Tasks
arXiv cs.AI Research & Papers
LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Lay…
arXiv cs.AI Research & Papers
Allocation Before Ranking: Decoupled Token Compression for OmniLLMs
arXiv cs.AI Research & Papers
AgentSLABench: Evaluating and Benchmarking Agentic Systems Under Resource Constraints
arXiv cs.AI Research & Papers
Geometric Self-Supervised Pre-training for Neural Combinatorial Optimization
arXiv cs.AI Research & Papers
When Memory Updates but Behavior Does Not: Repairing Implicit Stale Dependencies in Perso…
arXiv cs.AI Research & Papers
F-WANDA: Fisher-Reweighted Post-Training Pruning for Sustainable Deployment of Large Lang…
arXiv cs.AI Research & Papers
CrystalMem: Elastic Memory for Self-Evolving LLM Agents via Knowledge Crystallization
arXiv cs.AI Research & Papers
Measurement Without Validity: The Compounding Reliability Problem in Agentic AI Evaluation
arXiv cs.AI Research & Papers
Toward Fine-Grained Forgetting:Attribute Unlearning for Multimodal Large Language Models