arXiv:2611.01840 · v1
Self-Evolving Agentic Workflows via Semantic Decomposition of Complex Tasks
摘要
Agentic workflows organize complex tasks into reusable procedures. However, invoking an LLM at every step incurs repeated inference costs and delays. We propose a framework for self-evolving agentic workflows through semantic task decomposition. Each subtask has explicit applicability conditions and a procedure that executes code or invokes a model as needed. An agent uses execution feedback to refine the decomposition and update these procedures. Experiments in the GLEE competition show the framework on bargaining, negotiation and persuasion. Most observed final-decision procedures are implemented in code. Code is available at https://github.com/Applied-Machine-Learning-Lab/NeurIPS2026_SeaFlow.
作者备注：Accepted as a Spotlight at the NeurIPS 2026 Workshop on Interpreting Agent Behavior (IAB), GLEE Competition Track; 1st place in the GLEE competition. 21 pages