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
IPO Finance Agent: Evaluation of LLM Financial Analysts beyond Finance Agent v2, with Aut…
arXiv cs.AI Research & Papers
From numerical proportions to analogical proportions between probabilities
arXiv cs.AI Research & Papers
A Stackelberg Framework for Resource-Aware LLM Agents: Learning, Repair, and Conditional …
arXiv cs.AI Research & Papers
When Preferences Fail to Become Incentives: A Utility-Behavior Gap in Large Language Mode…
arXiv cs.AI Research & Papers
The Impact of VAE Design on Latent Pose Representations for Diffusion-based Sign Language…
arXiv cs.AI Research & Papers
ENVS: Environment-Native Verified Search for Long-Horizon GUI Agents
arXiv cs.AI Research & Papers
When Agents Commit Too Soon: Diagnosing Premature Commitment in LLM Agents
arXiv cs.AI Research & Papers
AI Scientists as Engines of Discovery: A Case for Development within Reformed Institutions
arXiv cs.AI Research & Papers
Finding the Evidence: Discovering Decision-Supporting Tokens for On-Policy Reasoning Dist…
arXiv cs.AI Research & Papers
Active Inference as the Test-Time Scaling Law for Physical AI Agents
arXiv cs.AI Research & Papers
AI-Assisted Help-Seeking Trajectories in Programming Education from an SRL-Informed Persp…
arXiv cs.AI Research & Papers
A Formula-Driven Survey and Research Agenda for On-Policy Distillation
arXiv cs.AI Research & Papers
Learning Filters with Certainty
arXiv cs.AI Research & Papers
GroundEval: A Deterministic Replacement for LLM-as-Judge in Stateful Agent Evaluation
arXiv cs.AI Research & Papers
Beyond Penalizing Mistakes: Stabilizing Efficiency Training in Large Reasoning Models via…
arXiv cs.AI Research & Papers
Safety-Aware Evaluation of LLM-Generated Driver Intervention Messages through Multi-Task …
arXiv cs.AI Research & Papers
Skin-Deep: A Geometric Diagnostic for Alignment Fragility in Large Language Model Represe…
arXiv cs.AI Research & Papers
AgentLens: Interpretable Safety Steering via Mechanistic Subspaces for Multi-Turn Coding …
arXiv cs.AI Research & Papers
Confident but Conflicted: Internal Uncertainty and Cognitive Dissonance Resolution in LLMs
arXiv cs.AI Research & Papers
SkillAudit: From Fixed-Suite Benchmarking to Skill-Centered Assessment
arXiv cs.AI Research & Papers
PaperClaw: Harnessing Agents for Autonomous Research and Human-in-the-Loop Refinement
arXiv cs.AI Research & Papers
Text2DSL: LLM-Based Code Generation for Domain-Specific Languages
arXiv cs.AI Research & Papers
MacAgentBench: Benchmarking AI Agents on Real-World macOS Desktop
arXiv cs.AI Research & Papers
Governance Decay: How Context Compaction Silently Erases Safety Constraints in Long-Horiz…
arXiv cs.AI Research & Papers
Imagine to Ensure Safety in Hierarchical Reinforcement Learning
arXiv cs.AI Research & Papers
Grounded Scaling: Why Agentic AI Needs Deterministic Environments
arXiv cs.AI Research & Papers
SCOPE: Evolving Symbolic World for Planning in Open-Ended Environments
arXiv cs.AI Research & Papers
PRIME: Evaluating Prompt Resolution Under Incompatible Instructions in LLMs
arXiv cs.AI Research & Papers
The More the Merrier: Combining Properties for ABox Abduction under Repair Semantics in E…
arXiv cs.AI Research & Papers
FoMoE: Breaking the Full-Replica Barrier with a Federation of MoEs