AdaptFlow: Adaptive Workflow Optimization via Meta-Learning
Runchuan Zhu, Bowen Jiang, Lingrui Mei, Fangkai Yang, Lu Wang, Haoxiang Gao, Fengshuo Bai, Pu Zhao
Abstract
Recent advances in large language models (LLMs) have sparked growing interest in agentic workflows—structured sequences of LLM invocations designed 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 uses a bi-level optimization process: the inner loop performs task-specific adaptation via LLM-generated feedback, while the outer loop consolidates these refinements into a shared, generalizable initialization. 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.
BibTeX
@inproceedings{emnlp2025_adaptflowadaptiv,
title = {AdaptFlow: Adaptive Workflow Optimization via Meta-Learning},
author = {Runchuan Zhu and Bowen Jiang and Lingrui Mei and Fangkai Yang and Lu Wang and Haoxiang Gao and Fengshuo Bai and Pu Zhao and Qingwei Lin and Saravan Rajmohan and Dongmei Zhang},
booktitle = {EMNLP 2025},
year = {2025}
}