Newest · pág. 36

← primera página

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
SWE-Bench Pro Verified: A Reliable Benchmark for Software Engineering Agents
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
API Benchmark Scores Do Not Reliably Transfer to Chatbot Interfaces
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
The Convention Gap: Beyond Literal Content in Human-AI Cooperation
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
IBBench-Light: A Paired Evaluation of Task-Conditioned Responses to External Directives
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Claim-Gated Source-Risk Auditing for Generative Search
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Hyper Algorithm Design Agent: Evolving Learnable Optimizer from Zero
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
EngiWorld: What Can Frontier Agents Deliver in Professional Engineering Environments?
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
DREAM: Dynamic Resolution Assignment For Multimodal Multi-agent Debate
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
GraphDecisionBench: Benchmarking System One Models on Graph Tasks
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
From Benchmark to Bench: Can Agents Survive Real-World Drug Discovery?
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Learning to Report Unsafe Tasks in a Multi-Agent Game
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Bolzano: From Expert-Guided Proof Search to Automated Open-Problem Solving
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Reasoning-Token Spikes Under Prompted Untruthful Responses in Large Language Models
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Provably Accurate Shapley Value Estimation via Leverage Score Sampling
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Conditional Vendi Score: Prompt-Aware Diversity Evaluation for Generative AI Models and LLMs
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Understanding Transformer-based Vision Models through Inversion
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
CRM: Retrieval Model with Controllable Condition
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
WoundAmbit: Bridging State-of-the-Art Semantic Segmentation and Real-World Wound Care
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Heterogeneity-Aware Client Sampling for Optimal and Efficient Federated Learning
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Auditing Prompt Injection Defenses Before They Reach Users: What Strong Adversaries Reveal
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
ReasoningShield: Safety Detection over Reasoning Traces of Large Reasoning Models
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Breaking the Cloak! Unveiling Chinese Cloaked Toxicity with Homophone Graph and Toxic Lexicon
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Physics-inspired Generative AI models via real hardware-based noisy quantum diffusion
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
UniConFlow: A Unified Constrained Flow-Matching Framework for Certified Motion Planning
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
LLMail-Inject: A Dataset from a Realistic Adaptive Prompt Injection Challenge
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Regression-adjusted Monte Carlo Estimators for Shapley Values and Probabilistic Values
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Towards a Measure Theory of Semantic Information
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Access Paths for Efficient Ordering with Large Language Models
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Discovering Phase Space Structure in Learned Hamiltonian Systems
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
ABLEIST: Intersectional Disability Bias in LLM-Generated Hiring Scenarios
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
A Theory of the Mechanics of Information: Generalization Through Measurement of Uncertainty (Learning is Measuring)
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
HAFixAgent: History-Aware Agentic Program Repair
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Preference-Conditioned Multi-Objective Reinforcement Learning for Tactical Decision Making in Heavy-Duty Vehicles
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
COBALT: Contextual Bandit Learning with Offline Trajectories for Multi-Turn Code Generation
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Beyond State-Wise Mirror Descent: Offline Policy Optimization with Parametric Policies
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
On the Rate of Convergence of GD in Non-linear Neural Networks: An Adversarial Robustness Perspective
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
ITO: Multi-View Alignment and Training-Time Fusion for Image-Text Pretraining
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Agentic Peer-to-Peer Networks: From Content Distribution to Capability and Action Sharing
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
CORE-Seg: Reasoning-Driven Segmentation for Complex Lesions via Reinforcement Learning
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Mixture-Greedy for Online Generative Model Selection: Is UCB Necessary in Diversity-Aware Multi-Armed Bandits?
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
AnomalyAgent: Agentic Industrial Anomaly Synthesis via Tool-Augmented Reinforcement Learning
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Physics-guided surrogate learning enables zero-shot control of turbulent wings
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Convex Optimization of Spiking Neural Networks with Global and Approximation Guarantees
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Beyond Pairs: Your Language Model is Secretly Optimizing a Preference Graph
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
FactoryNet: A Large-Scale Dataset toward Industrial Time-Series Foundation Models
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
MemReread: Enhancing Agentic Long-Context Reasoning via Memory-Guided Rereading
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Sampling-Based Safe Reinforcement Learning
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle