When Faster Decisions Do Not Make Better Agents: An Empirical Study of Jev in Agent Workflows

Yuchen Ling et al.

#arXiv #cs.AI

Benchmarking Embedding Geometries and Clustering Algorithms for Unsupervised Patent Claim Classification

Sujith Subramanian et al.

#arXiv #cs.AI #cs.CL

Teaching neural decoders with language

Xuan Wen et al.

#arXiv #cs.AI

One-Step Text Generation by Seq-Drifting

Jiayu Liu et al.

#arXiv #cs.AI

EliteTable: Self-Improving Program Search for Executable Control Policies

Stuart Farmer

#arXiv #cs.AI #cs.NE

arXiv is capping submissions to fight the flood of AI-generated slop. #arxiv

Local Diagnostics of Learned Event Representations for Anomaly Detection at the HL-LHC

Donatella Genovese et al.

#arXiv #cs.AI #hep-ex #hep-ph #physics.data-an

RegulaTutor: A Theory-Informed Framework for Long-Term Personalized Learning

Yonggang Li et al.

#arXiv #cs.AI

Quality, Not Just Outcome: A Structural Scoring Framework for Selecting Coding-Agent Trajectories for Supervised Fine-Tuning

Sida Li et al.

#arXiv #cs.AI

Competence-Aware Orchestration for LLM-Based Multi-Agent Systems

Songmiao Wang et al.

#arXiv #cs.AI

SWEAR: Section-Wise Efficient Audio Reasoning via Self-Rated Difficulty

Yixuan Li et al.

#arXiv #cs.AI

Beyond Semantic IDs: Finite-Beam Reachability and Continuous-Query Generation in Generative Recommendation

Yu Sun et al.

#arXiv #cs.AI

Mitigating Capability Degradation in LLM Self-Improvement via Representation Geometry Regularization

Jiaqi Tian, Ting Long

#arXiv #cs.AI

MagicBeanStalk: Escaping the RLVR Zero Advantage Trap with Recursive Data Synthesis

Ximing Lu et al.

#arXiv #cs.AI #cs.LG

Know What You Don't Know: Agentic Data Synthesis by Evolving Generation Space for Closed-Loop Learning

Wei Yang et al.

#arXiv #cs.AI #cs.MA

Local Diagnostics of Learned Event Representations for Anomaly Detection at the HL-LHC

Donatella Genovese et al.

#arXiv #cs.AI #hep-ex #hep-ph #physics.data-an

RegulaTutor: A Theory-Informed Framework for Long-Term Personalized Learning

Yonggang Li et al.

#arXiv #cs.AI

Quality, Not Just Outcome: A Structural Scoring Framework for Selecting Coding-Agent Trajectories for Supervised Fine-Tuning

Sida Li et al.

#arXiv #cs.AI

Competence-Aware Orchestration for LLM-Based Multi-Agent Systems

Songmiao Wang et al.

#arXiv #cs.AI

SWEAR: Section-Wise Efficient Audio Reasoning via Self-Rated Difficulty

Yixuan Li et al.

#arXiv #cs.AI