Newest · pág. 4

← primera página

Beyond LLM Wrappers: Context Engineering and the Three-Engine Architecture for Reliable Financial AI
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 19:00:46Publicado: 31/10/2026, 4:00:00detalle
SocialArena: Evaluating Social Intelligence in Large Language Models
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 19:00:46Publicado: 31/10/2026, 4:00:00detalle
Where to Learn and How Far to Roll Out: Efficient Adaptive Training for GUI Agents
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 19:00:46Publicado: 31/10/2026, 4:00:00detalle
Online Dense Reinforcement Learning with Planning-Grounding Agent for UI Navigation on Live IOS Apps
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 19:00:46Publicado: 31/10/2026, 4:00:00detalle
LLM-Assisted Optimization for Simulation-Based Redesign
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 19:00:46Publicado: 31/10/2026, 4:00:00detalle
MemSteer: Turning User Histories into Supervision for Agent Memory Optimization
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 19:00:46Publicado: 31/10/2026, 4:00:00detalle
What Does "Now" Mean to Your Computer-Use Agent? Stale Screenshots, Page Loads, and Which Check to Run Before a Click
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 19:00:46Publicado: 31/10/2026, 4:00:00detalle
Proving and Improving the Platonic Representation Hypothesis with JEPAs
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 19:00:46Publicado: 31/10/2026, 4:00:00detalle
CoToan: Executable Rules and a Representation Contract for Reproducible Game AI Evaluation
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 19:00:46Publicado: 31/10/2026, 4:00:00detalle
Before the Next Rollout: Diagnosing Skill Utility Shifts from Policy Updates
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 19:00:46Publicado: 31/10/2026, 4:00:00detalle
AgentDecept: Benchmarking Deceptive Behavior in Tool-Using LLM Agents under Pressure
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 19:00:46Publicado: 31/10/2026, 4:00:00detalle
Retaining Repair Hypotheses for Cost-Aware Execution
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 19:00:46Publicado: 31/10/2026, 4:00:00detalle
Verifiable LLM-Guided Focal SMT Solving for Quantified Arrays
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 19:00:46Publicado: 31/10/2026, 4:00:00detalle
ATLAS-Bench: An Agentic Tool-Use Benchmark for Local Area Search
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 19:00:46Publicado: 31/10/2026, 4:00:00detalle
Timbre: Reliability-aware harmonic consensus for label-free multimodal test-time rexinforcement learning
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 19:00:46Publicado: 31/10/2026, 4:00:00detalle
Kairos: Semantics-Aware Orchestration of Planning Engines across Classical, Numeric, Temporal and Hybrid PDDL
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 19:00:46Publicado: 31/10/2026, 4:00:00detalle
Does Federated Training Degrade Explainability? A Comparative Analysis of Grad-CAM Faithfulness in Centralized vs. Federated Deepfake Detection
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 19:00:46Publicado: 31/10/2026, 4:00:00detalle
Does Scaling Toward AGI Depend on What System-1 Lets System-2 Execute?
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 19:00:46Publicado: 31/10/2026, 4:00:00detalle
Integrated Feature Selection for classification and Representation Learning with Group-Lasso Siamese Networks
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 19:00:46Publicado: 31/10/2026, 4:00:00detalle
What Breaks When Facts Become Stories? The Distortions Source-Agreement Metrics Miss When Models Retell Real Events
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 19:00:46Publicado: 31/10/2026, 4:00:00detalle
Compile Away Uncertainty: Self-Evolving Agent Skills via Programmatic Compilation
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 19:00:46Publicado: 31/10/2026, 4:00:00detalle
DEG: Diffusion-Enhanced GFlowNet for Solving Vehicle Routing Problems
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 19:00:46Publicado: 31/10/2026, 4:00:00detalle
Category-Anchored Large Language Models for Next POI Recommendation
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 19:00:46Publicado: 31/10/2026, 4:00:00detalle
Non-Zero Radius: The Missing Component of Neural Networks
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 19:00:46Publicado: 31/10/2026, 4:00:00detalle
From Intent to Improvement: Agentic Dataset Search for Better Model Training
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 19:00:46Publicado: 31/10/2026, 4:00:00detalle
Emergence of the transformer architecture as the score of entropic laws of random measures
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 19:00:46Publicado: 31/10/2026, 4:00:00detalle
Letting AI Formulate the Research Question: Autonomous Research Agents
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 19:00:46Publicado: 31/10/2026, 4:00:00detalle
The Real Cost of Context: Predicting Compute Time and Energy Consumption in LLM Prefill and Decode Phases
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 19:00:46Publicado: 31/10/2026, 4:00:00detalle
MoLRSI: A Recursive Self-Improving AI agent for Molecular Discovery
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 19:00:46Publicado: 31/10/2026, 4:00:00detalle
Bank-World: A Benchmark for Evaluating Agents on Banking Workflows
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 19:00:46Publicado: 31/10/2026, 4:00:00detalle
From the Transformer to a Formal Semantics of Coordinated Transformations
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 19:00:46Publicado: 31/10/2026, 4:00:00detalle
PAPERBENCHX: Can AI Reproduce Science Across Disciplines?
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 19:00:46Publicado: 31/10/2026, 4:00:00detalle
Finding Is Not Returning, Returning Is Not Reconstructing: A Multi-Dimensional Evaluation of Agent Social Re-entry
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 19:00:46Publicado: 31/10/2026, 4:00:00detalle
Long-Term Agent Memory through Complementary Curation and Consolidation
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 19:00:46Publicado: 31/10/2026, 4:00:00detalle
The Role of Self-Concept In Language Models
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 19:00:46Publicado: 31/10/2026, 4:00:00detalle
Revisiting Over-refusal in Safety-aligned Large Language Models: A Representation and Optimization Perspective
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 19:00:46Publicado: 31/10/2026, 4:00:00detalle
EvoTeam: Multi-Agent Collaboration via Evolving Teams
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 19:00:46Publicado: 31/10/2026, 4:00:00detalle
AegisFlow: Training-Free Non-Myopic Path-Safe Guided Flow Matching
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 19:00:46Publicado: 31/10/2026, 4:00:00detalle
KARMA: Training-Free Knowledge-Atomic Harness Evolution for Industrial Advertising Agents
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 19:00:46Publicado: 31/10/2026, 4:00:00detalle
Efficient Learning of Mechanism Designs and Compositionality
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 19:00:46Publicado: 31/10/2026, 4:00:00detalle
Human--AI Interactions as First-Class Data: A Formal Interaction Model and Runtime for Explainable AI Collaboration
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 19:00:46Publicado: 31/10/2026, 4:00:00detalle
Cheap Retrieval and Observation Credit Assignment from One Quantity: The Value of Information
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 19:00:46Publicado: 31/10/2026, 4:00:00detalle
Hybrid AI Patterns: Thirteen Ways to Couple Language Models with Rules, and How to Choose Among Them
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 19:00:46Publicado: 31/10/2026, 4:00:00detalle
Agentic process evidence
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 19:00:46Publicado: 31/10/2026, 4:00:00detalle
Reward-Adaptive Co-Evolution of Policy and Rubric
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 19:00:46Publicado: 31/10/2026, 4:00:00detalle
DynaRev: Benchmarking Web Agents under Dynamic Goal Revision
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 19:00:46Publicado: 31/10/2026, 4:00:00detalle
The generative paradox: the Anti-Prompt paradigm for human capability
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 19:00:46Publicado: 31/10/2026, 4:00:00detalle
A Negotiation-Aware Hybrid LLM Framework for Intent Interpretation and Service Discovery
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 19:00:46Publicado: 31/10/2026, 4:00:00detalle
Locating and Closing Information Gaps in Multi-Agent Systems
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 19:00:46Publicado: 31/10/2026, 4:00:00detalle
Bridging Semantics and Structure: A Theoretically Grounded Framework for Link Prediction on TAGs
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 19:00:46Publicado: 31/10/2026, 4:00:00detalle