Portada · pág. 23

← primera página

OS-Helix: Unifying GUI Interaction and Code Execution in Native Computer-Using Agents
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Training-Free On-Policy Distillation
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Language Is a Security Surface for Agent Guards
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Librarian Agents: Training LLMs to Curate Long-Context Workspaces that Anticipate Future Queries
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Asking Smarter Questions: Targeted Active Preference Learning for Underspecified Rewards
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Towards Continual Learning: Mitigating Forgetting With Subspace Tuning
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
AI Consilium: a Benchmark of LLM Clinical Multidisciplinary Second Opinions
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Knowledge That Is Linear Before Fine-Tuning Generalizes After It
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Learning to Steer LLM Agents and Multi-Agent Systems
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
AVC-Reward: Event-Centric Audio-Video Consistency Evaluation
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Learning Self-Orchestration in Decentralized Agent Swarms
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Twice Upon a Time: Complementary Representations for Time-Series Reasoning
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
ACEdit: Stable Multi-Turn Image Editing via Asymmetric Conditioning
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Dexterity from Supervised Play
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
3DCodeVerse: Exploring 3D Worlds as Code
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
GeoState: Learning View-Decoupled Geometry States for 3D World Modeling
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Rethinking Routing Exploration in Modern Mixture-of-Experts
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
CoDA: Co-Evolution of Data Engines and Action Policies
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
T2-z: Test-Time Optimization of Environment Latents for Robotic World Models
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Discovering state-of-the-art quantum circuits with large language models
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
LIBERO-PeRM: Benchmarking Personalized Robotic Manipulation
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Atomic Proximal Policy Optimization for Electric Robo-Taxi Dispatch and Charger Allocation
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Generalising from Self-Produced Data: Model Training Beyond Human Constraints
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
GraphCompliance: Structure-Aware Regulatory Compliance through Policy-Context Graph Alignment
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
ChaosBench-Logic: A Benchmark for Logical and Symbolic Reasoning on Chaotic Dynamical Systems
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Agent Skill Framework: Perspectives on the Potential of Small to Medium Language Models in Industrial Environments
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
JEPA-DNA: Grounding Genomic Foundation Models through Joint-Embedding Predictive Architectures
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
WorkflowPerturb: Calibrated Stress Tests for Evaluating Multi-Agent Workflow Metrics
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
BenchPreS: A Benchmark for Context-Aware Personalized Preference Selectivity of Persistent-Memory LLMs
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Towards Better Aligned LLM Judges for Radiology Report Evaluation across Modalities and Anatomies
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Language models recognize dropout and Gaussian noise applied to their activations
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Self-Programmed Execution for Language-Model Agents
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
PREPING: Zero-Task Agent Memory Construction via Self-Practice
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Prospective multi-pathogen disease forecasting using autonomous LLM-guided tree search
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Generative Recursive Reasoning
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Adapting the Interface, Not the Model: Runtime Harness Adaptation for Deterministic LLM Agents
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
PathCal: State-Aware Reflection-Marker Calibration for Efficient Reasoning
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Harness-Bench: Evaluating Agent Harnesses across Models and Realistic Workflows
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
KACE: Knowledge-Adaptive Context Engineering for Mathematical Reasoning
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
SkillDAG: Self-Evolving Typed Skill Graphs for LLM Skill Selection at Scale
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
EvoFlux: Inference-Time Evolution of Executable Tool Workflows for Compact Agents
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
LLM-as-an-Investigator: Evidence-First Agentic Reasoning for Robust Interactive Problem Diagnosis
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Multi-Agent Transactive Memory
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
AI Alignment From Social Choice Perspectives
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
TOPS: First-Principles Visual Token Pruning via Constructing Token Optimal Preservation Sets for Efficient MLLM Inference
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Mind the Delay: Latency-aware Query Routing for Heterogeneous LLM pools
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
ContinualSkillBench: Can LLM Agents Truly Evolve Their Capabilities?
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
AI and Consumer Rights in India Working Paper
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
When Do LLMs Apply the Wrong Law? Diagnosing LLM Failures in Temporal Legal Reasoning
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle
Agent Gym: A Framework for Continuous Evaluation and Evolution of LLM Agents Through Human-in-the-Loop Feedback
arXiv cs.AIarxiv.orgAgregado: 17/10/2026, 2:00:46Publicado: 16/10/2026, 4:00:00detalle