University of Notre Dame · 6 records

dateidtitleauthorsvenue↑
2026-10-052609.39820Learning from Runtime Feedback through Failure-Bank Self-Evolution for Vision-Language-Action ModelsMingyue Cui et al.arXiv19
2026-10-012609.34274BIABench: Evaluating AI agents on real-world bioimage analysis tasksZixuan Pan et al.arXiv2
2026-09-152609.12541Agent as Policy for Robotic ManipulationMengzhao Jia et al.arXiv17
2026-05-152605.12243PreScam: A Benchmark for Predicting Scam Progression from Early ConversationsWeixiang Sun et al.arXiv2
2026-05-132605.11518AutoLLMResearch: Training Research Agents for Automating LLM Experiment Configuration -- Learning from Cheap, Optimizing ExpensiveTaicheng Guo et al.arXiv3
2026-05-122605.10664Prompt-Activation Duality: Improving Activation Steering via Attention-Level InterventionsDiancheng Kang et al.arXiv7