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
OpenDebateEvidence: A Massive-Scale Argument Mining and Summarization Dataset
arXiv cs.AI Research & Papers
Fetch-then-Explore: Decoupling Selection from Extraction over a Persistent Workspace for …
arXiv cs.AI Research & Papers
MemArbiter: Decision-Time Memory Arbitration for Long-Horizon LLM Agents
arXiv cs.AI Research & Papers
Beyond Solution-Centric Search: Adaptive Inquiry and Knowledge Revision for Autonomous ML…
arXiv cs.AI Research & Papers
Beyond the Mean: Multi-Moment Policy Optimization for LLM Reasoning
arXiv cs.AI Research & Papers
Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints
arXiv cs.AI Research & Papers
PAC Approximation and DIRECT Optimization for Parametric Markov Models
arXiv cs.AI Research & Papers
MEGRAG: Multi-Granular Evidence Graphs for Answer-Aware Multi-Hop RAG
arXiv cs.AI Research & Papers
Homebot: A Personal AI Agent for Conversational Home Assistance and Automation
arXiv cs.AI Research & Papers
Harness-R1: Learning to Edit Executable Runtime Harnesses from Agent Failure Trajectories
arXiv cs.AI Research & Papers
Shared Prefixes, Better Credit: Adaptive Routing for Multi-Agent Reasoning
arXiv cs.AI Research & Papers
KC-Agent: A Dual-Process Cognitive Architecture for Efficient ML Model Improvement
arXiv cs.AI Research & Papers
Faster-WAM: Do World Action Models Need Deep Action Modules?
arXiv cs.AI Research & Papers
Chess on Ice: Curling Tactical Decision-Making via Backward Induction and Deep Reinforcem…
arXiv cs.AI Research & Papers
Cooperative Coevolution for Resource-Constrained Agentic LLM Post-Training
arXiv cs.AI Research & Papers
xPress: Parallel Refinement for Diffusion Drafters in Speculative Decoding
arXiv cs.AI Research & Papers
Agentic Commerce World: An Auditable and Verifiable Environment for Vibe Commerce
arXiv cs.AI Research & Papers
Right Answer, Wrong Method: Shortcut Hacking Misleads the Evaluation of LLM Reasoning on …
arXiv cs.AI Research & Papers
Infinite Trace Objectives with Finite Trace Techniques: Translating LTL to LTLf+
arXiv cs.AI Research & Papers
Real-Time Detection and Repair of LLM Agent Failures
arXiv cs.AI Research & Papers
CMuon: Accelerating and Stabilizing Diffusion Transformer Training via Chunked Momentum O…
arXiv cs.AI Research & Papers
Abduction Without a Body? Representational Grounding and the Abduction Loop for Scientifi…
arXiv cs.AI Research & Papers
A Taxonomy of Cognitive Capability Gaps in Generative and Agentic AI
arXiv cs.AI Research & Papers
AtumAI: A Principled Framework for Agentic Generation of Datacenter Control-Plane Policies
arXiv cs.AI Research & Papers
Amplitude-Only FFN Intervention for Tool-Structured LLM Inference Method: Gated Evaluatio…
arXiv cs.AI Research & Papers
RubricReviewer: From Direct Critique to Objective and Comprehensive Rubric-Driven Peer Re…
arXiv cs.AI Research & Papers
AgentMemBench: A Systematic Benchmark for Evaluating Long-Term Memory Management Strategi…
arXiv cs.AI Research & Papers
DLLM-TTS: Block Discrete Diffusion Language Model for Text-to-Speech Synthesis
arXiv cs.AI Research & Papers
Obshazard-bench: Benchmarking Multimodal Foundation Models for Real-Time Disaster Intelli…
arXiv cs.AI Research & Papers
CITBench: A Comprehensive Benchmark for Interactive Tabular Data Processing with LLMs