Newest · pág. 2

← primera página

Evaluating Causal Reasoning in LLMs: A Case Study in the Challenges of Procedural Generation
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 11:00:46Publicado: 31/10/2026, 4:00:00detalle
AI-Driven Digital Twin Framework for Warehouse Logistics Automation Optimization
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 11:00:46Publicado: 31/10/2026, 4:00:00detalle
Too Hard, Too Easy, Just Right: Performance-Driven Challenge Adaptation in Virtual Reality Firefighter Training
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 11:00:46Publicado: 31/10/2026, 4:00:00detalle
Post-Training Large Language Models with LLMON
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 11:00:46Publicado: 31/10/2026, 4:00:00detalle
Decompose, Don't Expand: Capability-Independent AI Systems by Construction
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 11:00:46Publicado: 31/10/2026, 4:00:00detalle
SkillCT: A Multidimensional Benchmark and Execution-Free Baseline for Agent Skill Assessment
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 11:00:46Publicado: 31/10/2026, 4:00:00detalle
BridgeRouter: Gain-Aware Instance Routing over Cross-Modal Bridge Portfolios
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 11:00:46Publicado: 31/10/2026, 4:00:00detalle
DecompGym: Benchmarking LLM Agents on Designing Decomposition Algorithms
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 11:00:46Publicado: 31/10/2026, 4:00:00detalle
Prototype-Guided Dynamic Domain Modulation and a Large-Scale Multi-SKU Benchmark for Shampoo Bottle Surface Defect Detection
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 11:00:46Publicado: 31/10/2026, 4:00:00detalle
From Natural Language to Real Schematics: An Automated Workflow for Power Electronics Schematic Synthesis
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 11:00:46Publicado: 31/10/2026, 4:00:00detalle
GAAC: Lossless KV Compression for Bandwidth-Efficient LLM Inference on Personal Devices
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 11:00:46Publicado: 31/10/2026, 4:00:00detalle
Disparity Laundering: Consensus Without Fairness in Clinical Multi-Agent Systems
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 11:00:46Publicado: 31/10/2026, 4:00:00detalle
Rubricon: Automated Rubric Generation and Refinement for LLM Evaluation and Training
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 11:00:46Publicado: 31/10/2026, 4:00:00detalle
FACTS-MAS: A Multi-Agent Architecture for Adaptive Forecasting from Heterogeneous Evidence
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 11:00:46Publicado: 31/10/2026, 4:00:00detalle
Verification-Guided Retrosynthesis: Reaction Feedback and Evidence Timing
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 11:00:46Publicado: 31/10/2026, 4:00:00detalle
Inner-Learning: From Hand-Coded Beliefs to Declarative Knowledge in Trick-Taking Games
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 11:00:46Publicado: 31/10/2026, 4:00:00detalle
Game-Theoretic Foundations for Undiscounted Bisimulation Metrics
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 11:00:46Publicado: 31/10/2026, 4:00:00detalle
CHORD: Cross-Model Hallucination Detection via Relational Graph Discrimination
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 11:00:46Publicado: 31/10/2026, 4:00:00detalle
Can LLMs Faithfully Solve Ontology Engineering Tasks? A Mechanistic Interpretability Study
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 11:00:46Publicado: 31/10/2026, 4:00:00detalle
Investor's Last Exam: Can AI Agents Do Equity Investment Without Seeing the Future?
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 11:00:46Publicado: 31/10/2026, 4:00:00detalle
Encode Once, Answer Many: Internalizing Context via Parametric Flow
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 11:00:46Publicado: 31/10/2026, 4:00:00detalle
Compute Has Shape: Self-Morphing the Internal Computation of Frozen LLMs
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 11:00:46Publicado: 31/10/2026, 4:00:00detalle
SCOPE: Selective Critical-Step On-Policy Self-Distillation for Agentic Reinforcement Learning
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 11:00:46Publicado: 31/10/2026, 4:00:00detalle
Masked Erosion: How Acceptance Gates Lose Redundant Safeguards in Self-Improving Agents
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 11:00:46Publicado: 31/10/2026, 4:00:00detalle
Agent Transfer Protocol: Server-Mediated Agent-to-Agent Communication Architecture for the Agentic Web
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 11:00:46Publicado: 31/10/2026, 4:00:00detalle
Governance-Aware Federated Learning for Multi-Agent AI Systems: A Policy-Driven Framework for Trustworthy Collaborative AI
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 11:00:46Publicado: 31/10/2026, 4:00:00detalle
Predict the Reward, Not the World: World Reward Models for ML Agents
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 11:00:46Publicado: 31/10/2026, 4:00:00detalle
DES-JEPA: Learning a Shared Vocabulary for High-Dimensional Discrete Event Sequences
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 11:00:46Publicado: 31/10/2026, 4:00:00detalle
Accelerating Nonlinear MPC by Behavior Cloning with Separated Timescales: Application to Nuclear Reactor Load-Following
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 11:00:46Publicado: 31/10/2026, 4:00:00detalle
Value Probes: Learned Value Functions for Beam-Search Red Teaming
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 11:00:46Publicado: 31/10/2026, 4:00:00detalle
From Leniency to Suspicion: How an Open Post-Training Recipe Changes Whom LLM Fact-Checkers Believe
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 11:00:46Publicado: 31/10/2026, 4:00:00detalle
An Alignment Benchmark for Enterprise Agents on Era by Eon
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 11:00:46Publicado: 31/10/2026, 4:00:00detalle
PT$^3$: Prototype-Guided Self-Supervised Pretraining for Generalizable mmWave Human Point Cloud Representation
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 11:00:46Publicado: 31/10/2026, 4:00:00detalle
Co-Evolving Policy and Rubric via Capability Awareness for Open-Ended Generation
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 11:00:46Publicado: 31/10/2026, 4:00:00detalle
A-RSI: Adaptive Task Refresh for Zero-Data Multimodal Self-Improvement
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 11:00:46Publicado: 31/10/2026, 4:00:00detalle
CALM: Conflict-Aware Lifecycle Memory Governance for Long-Horizon Language Agents
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 11:00:46Publicado: 31/10/2026, 4:00:00detalle
Think Before You Act: Decision Gate for LLM Agents
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 11:00:46Publicado: 31/10/2026, 4:00:00detalle
Right Numbers, Wrong Questions: Evaluating LLMs on Underspecified Financial Queries
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 11:00:46Publicado: 31/10/2026, 4:00:00detalle
"Close enough?" An investigation into multiplication errors in LLMs
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 11:00:46Publicado: 31/10/2026, 4:00:00detalle
Curriculum-Based Deep Reinforcement Learning for Robust Autonomous Rocket Landing under Atmospheric Uncertainty
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 11:00:46Publicado: 31/10/2026, 4:00:00detalle
Weaken to Strengthen: Weakening-Induced On-Policy Self-Distillation for Large Reasoning Models
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 11:00:46Publicado: 31/10/2026, 4:00:00detalle
Deogen: Automatic Benchmark Generation for Reasoning over Policies
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 11:00:46Publicado: 31/10/2026, 4:00:00detalle
Beyond fabrication: Misattributed numbers in papers written by AI research agents
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 11:00:46Publicado: 31/10/2026, 4:00:00detalle
From Grind to Grasp
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 11:00:46Publicado: 31/10/2026, 4:00:00detalle
Leaving, Staying, or Living There? Duration Commonsense Reasoning with Human-LLM Co-annotations
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 11:00:46Publicado: 31/10/2026, 4:00:00detalle
Learning to Reason from Reference Samples Alone: Reinforced Adversarial Learning for Modern LLM Post-Training
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 11:00:46Publicado: 31/10/2026, 4:00:00detalle
Where You Inject Matters: The Trust Region Effect in LLM Agents
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 11:00:46Publicado: 31/10/2026, 4:00:00detalle
Auditable Belief Updates as a Missing Safety Layer for LLM-Powered Multi-Agent Systems
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 11:00:46Publicado: 31/10/2026, 4:00:00detalle
Aligning Autoresearch: Co-Improvement between Agents and Humans
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 11:00:46Publicado: 31/10/2026, 4:00:00detalle
TreasuryQA Bench: Can AI Agents Work an Archive of Scanned Financial Records?
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 11:00:46Publicado: 31/10/2026, 4:00:00detalle