Newest · pág. 44

← primera página

MagicBeanStalk: Escaping the RLVR Zero Advantage Trap with Recursive Data Synthesis
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Faithful and Complete LLM-Assisted Automated Construction of Hierarchical Hardware Knowledge Graphs
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Representation Alignment from a Few Paired Data via Distilled Optimal Transport
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
EvoBelief: Falsifiable World Models for Self-Improving LLM Agents
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
VEPA: Verified Evolving Formal Policy for Lifelong LLM Agent Guardrails
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Reward Hacking as a Transmissible Strategy in Multi-Agent Coding Systems
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Neural networks are more modular than single neurons suggest
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Towards Defining, Measuring, and Leveraging Creativity in AI Applications
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Mitigating Capability Degradation in LLM Self-Improvement via Representation Geometry Regularization
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Collaborative Theory of Mind: Learning to Self-Revise by Anticipating User Responses
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
One-Step Text Generation by Seq-Drifting
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Mind the Spatial Gap: A Benchmark for Geospatial Reasoning and Constrained Spatial Editing
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
OGPO: Offline Goal-conditioned Policy Optimization for Recoverable Vision-Language-Action Models
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
DeFiRank: Federated Pairwise Ranking for Governance in Decentralized Financial Networks
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
AI-Mediation in Retail Markets: Revenue Effects and Assortment Optimization
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Teaching neural decoders with language
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Collaborative Learning and Reasoning over Model Slices
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Learning More by Training Less: Uncertainty-Guided Progressive Contraction for Efficient Reasoning Post-Training
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
MathVis: Can AI Reason through Drawing? A Benchmark for Mathematical Figure Generation
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
SmartSalesBench: A Resistance-Aware Multi-Turn Benchmark for Evaluating LLM Sales Agents
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Beyond Semantic IDs: Finite-Beam Reachability and Continuous-Query Generation in Generative Recommendation
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Work2Skill: Capturing Human GUI Experience for Reusable Agent Skill Induction
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Benchmarking Embedding Geometries and Clustering Algorithms for Unsupervised Patent Claim Classification
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Hindsight Structured Advice Distillation: Steering Executor Agents with Advisors Trained on Their Failures and Task Characteristics
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Scaling Empowered Agents
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Provenance-Aware Belief Updating in Human-AI Feedback Loops
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
EmbodiedCLBench: Evaluating Continual Learning for Self-Evolving Embodied Agents
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Travel Back To Move Forward: Retrospective Exploration and Evolving for Long Horizon Agents
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
LongHarness: Advancing Agentic Reasoning over 100M-Token Corpora via Stateful Evidence Management
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Attention Sees, MLP Refuses: Tracing the Attention-to-MLP Safety Pathway in LLMs
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
SWEAR: Section-Wise Efficient Audio Reasoning via Self-Rated Difficulty
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
When Faster Decisions Do Not Make Better Agents: An Empirical Study of Jev in Agent Workflows
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
VETR: Execution-Grounded Self-Improving Agent for Symbolic Graphics Reasoning
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Does Location Matter? A Black-Box Causal Audit Reveals Model-Dependent Audio Grounding in LALM Hallucination
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
DRYLAB-Bench: Benchmarking the Biosecurity Risk of Agentic LLM Mutation Design
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Locate, Judge, Read: Role-Specialized Tool Agents over a Knowledge-Point Index for Open-Domain Multimodal Document QA
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Looking Ahead and Back: Anticipatory Generative Modeling for Road-Network Trajectories
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
DP-MIND: Differentially private memory-guided Long context Inference
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Competence-Aware Orchestration for LLM-Based Multi-Agent Systems
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
VIGOR: Verifiable Industrial Geometry Optimization and Repair in Scene Programs
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Quality, Not Just Outcome: A Structural Scoring Framework for Selecting Coding-Agent Trajectories for Supervised Fine-Tuning
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
RoleWorld: Knowledge Transfer in World Modeling with Functional Role Abstractions
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
AdaC-GRPO: Towards Mastering Long-Horizon Visual Sudoku Puzzles via Adaptive Curriculum Learning
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
JANUS: Enhancing Long-Horizon Autonomous Research with Co-Evolving World Models
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Forgetting is Not Always Bad: A Neuro-Inspired Memory Repair Mechanism for Poisoned LLM Agents
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
BoundaryEvo: Data-Model Co-Evolution at the Capability Boundary for Long-Chain Reasoning Distillation
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Masked Diffusion Language Agents for Tool-Integrated Chemical Reasoning
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
AlphaNIST: Emergent Assembly Skills from Binary Task Rewards
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
SWE-Critix: Post-Training Generalist Verifiers for Assessing Coding-Agent Trajectories
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
RegulaTutor: A Theory-Informed Framework for Long-Term Personalized Learning
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle