Newest · pág. 20

← primera página

Terminal-RSI: Recursive Self-Improving Terminal Agents via Recursive Self-Rewrite and Policy-Refine
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
AutoSFT: An Agentic System for Automated Data Research in Supervised Fine-Tuning
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
HTN-Orchestrate: A Hierarchical Task Network Framework for Multi-Agent Orchestration
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
GNN-Guided Local Refinement for Efficient Layout Decomposition with DSA-MP
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Shortcut Sensitivity in Agent-Safety Evaluations
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Disagreement-Guided Weak-to-Strong Routing
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
X-RIC: An Agentic RAN-Intelligent Controller Benchmark for Enhancing Reinforcement Learning
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
LEASH: Uncertainty-Aware Weak-to-Strong Escalation and Oversight for Computer-Use Agents
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Improving Environment-Agnostic Coding Agents: The Role of Scaffolding
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
EliteReplay: Preserving Diverse Solutions in RL Post-Training via Quality-Diversity Search
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Private Retrieval Augmented Generation via Random Projection
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
A team of Gemini 4 Argon agents beats Minecraft
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Designing Transformers for Continuous Diffusion Language Models
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
KnowGPO: Knowledge-Grouped Policy Optimization for Search Agents
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Evaluation Awareness Beyond English: Do LLMs Act Differently When Tested in Indic Languages?
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
MLExpert: Towards a Generalist Agentic Model for Autonomous Machine Learning Engineering
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
FDE-Gym: The Last Mile of AI Delivery
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
KULTURE Bench: A Benchmark for Assessing Language Model in Korean Cultural Context
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Active Learning of Fractional-Order Viscoelastic Model Parameters for Realistic Haptic Rendering
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
One Is Not Enough: How People Use Multiple AI Models in Everyday Life
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Bridging the Gap: Converting Read Text to Conversational Dialogue
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Truth for Believable AI: Expressed Doubt, Provenance, and Belief Revision as an Engineerable Stance
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
RICE-Alpha: Reliability-Informed Correction with Event Graphs for LLM-Agent Stock Forecasting
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Real-time Chatbot Romance Scam Detection in Stage Classification
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Exploring the Design Space of Permutation Diffusion LLMs
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
CoTS: Competitive Token Selection for Latent Reasoning in Large Language Models
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Open Benchmark of AI Impact on Humans (ImpactBench): an expert-guided, open platform for the holistic evaluation of AI impact on humans
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
WorldCast: Exploring Intelligent Visual Generation in World State Prediction
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Interpreting Language Model Parameters
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Optimal Hydra: Model Heterogeneous Federated Learning for LLMs using Data-Informed Hydra-Nets
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Reference-Guided Turn-Taking Style Transfer for Full-Duplex Spoken Language Models
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
INFUSE: A Unified Surface Benchmark for Indirect Prompt Injection in Agentic Systems
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Verdict: Encode Once, Decide Many
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
ReasonUni: Reasoning-Augmented Reconstruction Advances Unified Multimodal Models
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Wolof-Adapted Industry-Ready Open-Weight Language Models
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
CoTranslator: Reverse to Forward Chain-of-Thought Translator for Reasoning Distillation
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Amortizing Sequential Experimental Design in Reasoning LLMs
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Probing Negation Understanding in Vision-Language Models With Object Attention
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
SHRED: Self-Play for Heterogeneous Road-Users without Expert Demonstrations
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Wrong Votes, Right Gradients: Why Majority-Vote Rewards Track Verifiable RL
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
TGrasp6D: Task-Informed Vision-Language Priors and Pose Refinement enable Zero-Shot Task-Oriented 6DoF Grasping
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Replicable Dueling Bandits
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Forecast lead time and the timing of crew deployment for weather-driven power outages using AI weather models
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Screwtape: Adversarial Transcript Editing for Monitor Red-Teaming
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Same Context, Different Agents: A Behavioral Study of Semantic Layers, Orchestration and Compaction in Data Agents
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
SOMA: Stack-of-Objects Manipulation using a Quadruped Robot
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
How to Train Your Little Dragon: Teaching a Small Language Model to Construct and Refine GPU Optimization Scripts
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
EigDiff: Eigensample Diffusion - or how to significantly reduce training dataset size with marginal performance variation?
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Learning to Read Out: Unembedding Dynamics in Language Model Pretraining
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
SCARCE: Emergent Institutions in Long-Horizon Multi-Agent Coding Systems
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle