Portada · pág. 33

← primera página

SafeDiSTL: Decomposing Joint Constraints for Safe Multi-Agent Reinforcement Learning
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Matched-Context Group Policy Optimization for LLM Agent Training
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
When Edge Independence Fails: Joint Graph Diffusion with Latent Sociability Priors
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
DualQuant: Dual-scale Calibration-free Weight-and-Activation Quantization for LLMs
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
ReplaySSM: Cache SSM Inputs, Not State
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Your Discrete Graph Diffusion Model is Secretly Memorizing
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
FORTE: A Production Framework for Feature Evaluation and Deprecation in Industrial Recommender Systems
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Same Query, Different Answer: Run-to-Run Variance in Semantic Query Processing
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
MC-EvoBench: Auditing Experience-Driven Self-Improvement in Minecraft Agents
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
SpatialASM: Internalizing Active Mentalization for Spatial Reasoning
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Task Context Shapes Component Roles in Language Models
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Revisiting Tabular Deep Regression: Objectives and the Limits of Global Early Stopping
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Hide and Seek: HIDE Concepts to SEEK explanations for black box models
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
From the Fluency Fallacy to the Micro-to-Macro Validity Gap: Opportunities and Pitfalls of LLMs in Social Simulation
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
DeltaLLM: Delta-Key Sparse Attention for Edge LLMs
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Global Consistency Repair for Natural-Language Claim Sets
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
CoMMa: Contribution-Aware Medical Multi-Agents for Decentralized Oncology Decision Support
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
AutoControl Arena: Synthesizing Executable Test Environments for Frontier AI Risk Evaluation
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
NeuronSpark: Selective Spiking State Space Models with Adaptive Computation for Language Modeling
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
DEAF: A Benchmark for Diagnostic Evaluation of Acoustic Faithfulness in Audio Language Models
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Can Agents Price a Reaction? Evaluating LLMs on Chemical Cost Reasoning
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
FactoryBench: Evaluating Industrial Machine Understanding
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
UxSID: Semantic-Aware User Interests Modeling for Ultra-Long Sequence
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
MAGE: Multi-Agent Self-Evolution with Co-Evolutionary Knowledge Graphs
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
When Simulation Lies: A Sim-to-Real Benchmark and Domain-Randomized RL Recipe for Tool-Use Agents
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
From SGD to Muon: Adaptive Optimization via Schatten-p Norms
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
MPMMine: Better Benchmarks for Constraint Acquisition
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Latent Reward Steering: An Adaptive Inference-Time Framework that Implicitly Promotes Cognitive Behaviors in Reasoning LLMs
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
EvoDrive: Pareto Evolution for Safety-Critical Autonomous Driving via Self-Improving LLM Agents
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
The Saturation Trap and the Subjectivity of Intervention Timing: Why Affect-Based Triggers and LLM Judges Fail to Time Interventions on Autonomous Agents
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Agents' Last Exam
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Do More Agents Help? Evaluating Accuracy and Cost in LLM Multi-Agent Workflows
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Experience Makes Skillful: Enabling Generalizable Medical Agent Reasoning via Self-Evolving Skill Memory
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
TelcoAgent: A Scalable 5G Multi-KPM Forecasting With 3GPP-Grounded Explainability
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Hierarchical Experimentalist Agents
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Agent Step Value: Auditing Evaluation-Channel Sensitivity in Black-Box Agent Traces
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Who&When Pro: Can LLMs Really Attribute Failures in AI Agents?
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
MIRROR: Learning from the Other View for Multi-Modal Reasoning
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Enhancing Tabular Learners with Context-Aware Semantic Embeddings
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
CASCADE: An Agentic Regulatory Network Framework for Patient-Data-Validated Downstream Perturbation Prediction
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Fast LapSum: Exact Differentiable Top-$k$ at Million Scale
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
ResidencyRL: Reinforcement Learning in Simulated Clinical Environments
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Different Feedback, Different Updates: Selective Self-Learning from User Interactions for Large Language Models
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
From Mastery Profile to Simulated Response: Stochastic Student Knowledge Graphs (SSKG) for Faithful LLM Student Simulation
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
GenCoord: Executable Commitments for Embodied LLM Agents under Private Information
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Preference Elicitation for Policy Optimization and Application to Aligning Heart Transplantation with Human Values
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Can escalation channels redirect reward hacking toward defect disclosure?
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Data-Driven Persona-Conditioned Agents for A/B Test Simulation
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
H2Table: Hierarchical Hypergraph-Enhanced Large Language Models for Complex Table Reasoning
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Multi-Harness Reinforcement Learning for Coding Agents: Training Gains and Harness Dependence
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle