MetaOPD: Meta-Learned Token Weighting for On-Policy Distillation

Zipeng Wang et al.

#arXiv #cs.AI

Where Draft Trees Lose Target Mass: Exit-Guided Speculative Decoding

Shijing Hu et al.

#arXiv #cs.AI

Error-Propagation Modeling for Failure Attribution in LLM-Based Multi-Agent Systems

Jiaqi Liao et al.

#arXiv #cs.AI

Cognition-Oriented Emotion Tracing from Causes to Consequences in Real-World Social Scenes

Hao Li et al.

#arXiv #cs.AI

Writing for the Reviewer: Defensive Writing in GPT Models

Junchi Liao

#arXiv #cs.AI

TokenBank: Financial Infrastructure for AI Services

Cary Chang, Jialin Zhou

#arXiv #cs.AI #cs.CE

On the Clock: Towards Punctual and Productive Time-Budgeted AI Agents

Aaron Wang et al.

#arXiv #cs.AI #cs.LG

Searching for "Harmful Refusal": A Psychometric Audit of an AI Safety Benchmark

Christopher M. Stewart et al.

#arXiv #cs.AI

HANS: A Handwritten Answer Sheet Dataset for Noisy Hybrid Document Parsing

Xiazhen Wu et al.

#arXiv #cs.AI #cs.CV

Can AI Agents Learn Their Way to the Top? Evaluating Heuristic Learning in a Long-Running Game Agent Competition

Kaisen Yang et al.

#arXiv #cs.AI #cs.CL

Day 10 of OCtober is Azatho! A Realm of Mynros Mhoat with a spooky look for October!
Find the Mhoats here: www.mhoats.com
#painted #digital #art #digitalart #OCtober #challenge #tentacles #mhoats #cs

When Has a Bayesian Neural Network Sampled Enough? Adaptive Inference Time with Statistical Guarantees

Fabian Denoodt, Sibylle Hess

#arXiv #cs.AI

Universal Textual Teaching for LLMs

Zhanyi Lu, Huan Wang

#arXiv #cs.AI

Structure Tax: How Structured Output affects LLMs Performance

Vineet Kumar, Kanishka, Bhuvanesh Mandora

#arXiv #cs.AI

MindFlow: Mind Supernet Powered Thinking Flows for Research Idea Innovation

Mengdi Liu et al.

#arXiv #cs.AI #cs.CL #cs.MA

How Is Automated Research Evaluated? A Survey of Benchmarks and Evaluation Practices

Liulei Zhang et al.

#arXiv #cs.AI

Probability-Signature Dynamics: Unpacking Modular Addition Learning Within Two-Layer Networks

Yunji Wang et al.

#arXiv #cs.AI

Safe Actions Alone Do Not Ensure Safe Agents: Identifying Unfulfilled Obligations with Guard Models

Youwei Feng et al.

#arXiv #cs.AI

Scalable AI Uncertainty Quantification via Generalized Laplace Active Subspaces

Wouter N. Edeling, Peter V. Coveney

#arXiv #cs.AI

Evidence-Traceable Dynamic Interviewer Architecture for Expertise-Adaptive Qualitative Interviews Using Local LLMs

Aisvarya Adeseye et al.

#arXiv #cs.AI