01. Can You Check That? The Checkability Boundary for Local LLM Network Automation

78% worth reading · novelty 1.8/3 · new method · cs.AI

02. Game Arena: Strategic LLM Evaluation in Competitive Environments

75% worth reading · novelty 1.8/3 · benchmark/eval · cs.AI

03. Multi-agent Scaling Across Disjunctive and Compensatory Tasks

74% worth reading · novelty 1.7/3 · benchmark/eval · cs.AI

04. Compact Documentation for Coding Agents: A Benchmark, an Optimizer, and Why It Does Not Transfer

76% worth reading · novelty 1.5/3 · benchmark/eval · cs.AI

05. DeepEdu-v1: Efficient and Scalable Agentic LLMs for Vietnamese Education

74% worth reading · novelty 1.6/3 · new method · cs.AI

06. User Model Extraction via Belief Self-Distillation

51% worth reading · novelty 2.0/3 · new method · cs.LG

07. Learning to Stop without Learning to Stop: Self-Supervised Confidence Training Improves Reasoning Efficiency

51% worth reading · novelty 1.9/3 · new method · cs.AI

08. New LoRA Skills Should Read but Never Write

49% worth reading · novelty 2.0/3 · new method · cs.LG

09. Prompt Minimization: Reducing Input Redundancy Without Sacrificing Output Fidelity

59% worth reading · novelty 1.2/3 · new method · cs.AI

10. "AI is (not) the new...": A Diagnostic Analogy Framework for Generative AI's Cultural Impacts

47% worth reading · novelty 1.8/3 · survey/position · cs.AI

11. Statistical attribute alignment for black-box generative AI via output post-processing

51% worth reading · novelty 1.5/3 · new method · cs.AI

12. Adapting for AI: How elementary teachers adjust their practices for an AI-integrated curriculum

47% worth reading · novelty 1.2/3 · applied system · cs.AI

13. Trust Guided Decision Transformer

42% worth reading · novelty 1.5/3 · new method · cs.LG

14. EAServe: Encode-Aware Disaggregated Serving for Multimodal Large Language Models

35% worth reading · novelty 1.8/3 · new method · cs.LG

15. Weight Pair Encoding: Inducing a Smaller Grammar in Neural Network Weights

33% worth reading · novelty 2.0/3 · new method · cs.LG

16. Evaluating Cultural Awareness of LLMs for Haitian Creole

35% worth reading · novelty 1.5/3 · benchmark/eval · cs.AI

17. A Flow Matching Framework for Neural Representational Dissimilarity

28% worth reading · novelty 2.0/3 · new method · cs.AI

18. Online Learning via Learned Latent Bayesian Tracking

28% worth reading · novelty 1.9/3 · new method · cs.LG

19. BeatGraph: Self-Supervised Heartbeat Graphs for Infant ECG Representations from the Home Environment

26% worth reading · novelty 2.0/3 · new method · cs.LG

20. UQ-LOB: Uncertainty-Aware Limit Order Book Mid-Price Forecasting

31% worth reading · novelty 1.5/3 · new method · cs.AI