Español

Explorar

Noticias de IA

27413 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
A case study of evaluating AI agents on a neuroscience data-to-discovery pipeline
arXiv cs.AI Research & Papers
Why Limit the Residual Stream to Layers and Not Tokens? Persistent Memory for Continuous …
arXiv cs.AI Research & Papers
Automatic Extraction of Structured Information from Brain MRI Reports Using an Open-Weigh…
arXiv cs.AI Research & Papers
Land cover and flood type govern the detection limits of satellite-based flood mapping ac…
arXiv cs.AI Research & Papers
Improving Multimodal Reasoning via Worst Dimension Optimization
arXiv cs.AI Research & Papers
Where Instruction Hierarchy Breaks: Diagnosing and Repairing Failures in Reasoning Langua…
arXiv cs.AI Research & Papers
Joint Structural Pruning and Mixed-Precision Quantization for LLM Compression
arXiv cs.AI Research & Papers
Safety is Contextual, LLM-Judges Are Not: Navigating the Rigid Priors of Evaluators
arXiv cs.AI Research & Papers
Contract2Tool: Learning Preconditions and Effects for Reliable Tool-Augmented LLM Agents
arXiv cs.AI Research & Papers
MemToolAgent overview with a simple restaurant booking scenario where the agent retrieves…
arXiv cs.AI Research & Papers
The CIFAR Synthetic Evidence Corpus for Detecting AI-Generated Evidence
arXiv cs.AI Research & Papers
Unification of Closed-Open Industrial Detection Scenarios: New Large-Scale Benchmarks,Cha…
arXiv cs.AI Research & Papers
Zero-Shot Learning in Industrial Scenarios: New Large-Scale Benchmark, Challenges and Bas…
arXiv cs.AI Research & Papers
Efficient Skill Grounding via Code Refactoring with Small Language Models
arXiv cs.AI Research & Papers
OSMGraphCLIP: Learning Global Location Representations from OpenStreetMap Graphs
arXiv cs.AI Research & Papers
How Small Can You Go? LoRA Fine-Tuning 270M-8B Models for Merchant Information Extraction…
arXiv cs.AI Research & Papers
PACE: Anytime-Valid Acceptance Tests for Self-Evolving Agents
arXiv cs.AI Research & Papers
Cross-LLM Consistency in Inference: Evidence from Shared Interactions
arXiv cs.AI Research & Papers
Decision-Aware Memory Cards: Counterfactual-Inspired Context Selection and Compression fo…
arXiv cs.AI Research & Papers
Online Agent-as-a-Judge: Situation-Generating Evaluation for Interactive Agents
arXiv cs.AI Research & Papers
Traxia: A Framework for Verifiable, Agent-Native Scientific Publishing
arXiv cs.AI Research & Papers
Beyond Agent Architecture: Execution Assumptions and Reproducibility in LLM-Based Trading…
arXiv cs.AI Research & Papers
To Nuke or Not to Nuke: LLMs' (Missing) Ethical Reasoning and Actions in a High-Stakes De…
arXiv cs.AI Research & Papers
Curation of a Cardiology Interface Terminology for Highlighting Electronic Health Records…
arXiv cs.AI Research & Papers
Integrating Deep Learning Demand Forecasting with Multi-Objective Optimization for Circul…
arXiv cs.AI Research & Papers
Benchmarking Open-Ended Multi-Agent Coordination in Language Agents
arXiv cs.AI Research & Papers
TT-DAC-PS: Twin-Target Deterministic Actor-Critic with Policy Smoothing for Optimal Trade…
arXiv cs.AI Research & Papers
Self-Evolving Scientific Agent Discovers Generalizable Physically-Reasoned Fluid Control
arXiv cs.AI Research & Papers
A Variability-Based Framework for Interpretable Naming in Formal and Relational Concept A…
arXiv cs.AI Research & Papers
Testing the Black Box: Structural Barriers to Independent Evaluation of Consumer-Facing H…