Recent advances in large language models (LLMs) have sparked growing interest in agentic workflows, which are structured sequences of LLM invocations intended to solve complex tasks. However, existing approaches often rely on static templates or manually designed workflows, which limit adaptability to diverse tasks and hinder scalability. We propose AdaptFlow, a natural language-based meta-learning framework inspired by model-agnostic meta-learning (MAML). AdaptFlow learns a generalizable workflow initialization that enables rapid subtask-level adaptation. It employs a bi-level optimization scheme: the inner loop refines the workflow for a specific subtask using LLM-generated feedback, while the outer loop updates the shared initialization to perform well across tasks. This setup allows AdaptFlow to generalize effectively to unseen tasks by adapting the initialized workflow through language-guided modifications. Evaluated across question answering, code generation, and mathematical reasoning benchmarks, AdaptFlow consistently outperforms both manually crafted and automatically searched baselines, achieving state-of-the-art results with strong generalization across tasks and models. The source code and data are available at https://github.com/microsoft/DKI_LLM/tree/AdaptFlow/AdaptFlow.
RSIFlow: Adaptive Self-Improvement Workflows with an Evolving Meta-Agent
Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing(未来区块链与隐私计算北京高精尖创新中心);School of Artificial Intelligence(人工智能学院);Beihang University(北京航空航天大学);Tsinghua University(清华大学);Beijing Academy of Artificial Intelligence (BAAI)(北京人工智能研究院)
MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework
DeepWisdom(深度智慧);AI Initiative, King Abdullah University of Science and Technology(阿卜杜拉国王科技大学人工智能计划);Xiamen University(厦门大学);The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳));Nanjing University(南京大学);University of Pennsylvania(宾夕法尼亚大学);University of California, Berkeley(加州大学伯克利分校);The Swiss AI Lab IDSIA/USI/SUPSI(瑞士IDSIA/USI/SUPSI人工智能实验室)
ATWL: A Formal Language for Representing, Comparing, and Reusing Visual Analytics Workflows
Fraunhofer Institute IAIS(弗劳恩霍夫研究所IAIS);Lamarr Institute for Machine Learning and Artificial Intelligence(拉马尔机器学习与人工智能研究所);City St George’s, University of London(伦敦大学城市圣乔治学院);University of Zurich(苏黎世大学);University of Stuttgart(斯图加特大学)
Adaptive Multimodal Agents-Based Framework for Automatic Workflow Execution
Sapienza University of Rome(罗马萨皮恩扎大学);Department of Engineering University of Sannio(萨尼奥大学工程系);Faculty of Jurisprudence Unitelma Sapienza University(法理学院萨皮恩扎大学)
Game-theoretic LLM: Agent Workflow for Negotiation Games
Rutgers University(罗格斯大学);University of California, Santa Barbara(加州大学圣巴巴拉分校);University of Southern California(南加州大学);University of South Florida(南佛罗里达大学);Harvard University(哈佛大学);Institute of Computing Technology(计算技术研究所)