You Don’t Know Until You Click: Automated GUI Testing for Production-Ready Software Evaluation
DeepWisdom • Fudan • HKUST(GZ) • UCSD • KAUST • Westlake • Stanford • Yale • NUS
Paper List
Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems
MetaGPT • UdeM • Mila • NTU • ANL • USYD • PSU • MSRA • UIUC • HKUST • USC • Yale • Stanford • UGA • OSU • KAUST • Duke • PolyU • DeepMind • CIFAR
Self-Supervised Prompt Optimization
DeepWisdom • HKUST(GZ) • Independent • Yale
Improving Context Fidelity via Native Retrieval-Augmented Reasoning
UdeM • MetaGPT • McGill • Simpleway.AI
EMNLP 2025 Oral ICML 2025 LCFM 2025
FACT: Examining the Effectiveness of Iterative Context Rewriting for Multi-fact Retrieval
DeepWisdom • UdeM & Mila • Google
NAACL 2025 arXiv
SELA: Tree-Search Enhanced LLM Agents for Automated Machine Learning
DeepWisdom • UC Berkeley • HKUST(GZ) • UCSD • SCNU • Stanford • CUHK-SZ • UdeM & Mila
AFlow: Automating Agentic Workflow Generation
DeepWisdom • HKUST(GZ) • RUC • NJU • Fudan • KAUST • UdeM & Mila • HKUST
Data Interpreter: An LLM Agent For Data Science
DeepWisdom • UdeM & Mila • CUHK-SZ • SZU • Fudan • RUC • SIAT-CAS • KAUST • Notre Dame • HKU • Yale • XMU • ECNU • BJUT • Tsinghua • HHU
MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework
DeepWisdom • AI Initiative • KAUST • XMU • CUHK-SZ • NJU • UPenn • UC Berkeley • IDSIA