# Self-Evolving Agentic Workflows via Semantic Decomposition of Complex Tasks

DevFeed: [Self-Evolving Agentic Workflows via Semantic Decomposition of Complex Tasks](<https://devfeed.tech/articles/self-evolving-agentic-workflows-via-semantic-decomposition-of-complex-tasks-115221.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.01840>)

Author: Zichuan Fu, Junjia Qi, Xian Wu, Wenlin Zhang, Yimin Deng, Kaifeng Guo, Xiangyu Zhao

Published: 2026-11-03T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [Multi-step AI processes](<https://devfeed.tech/topics/multi-step-ai-processes.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Complex AI tasks](<https://devfeed.tech/topics/complex-ai-tasks.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-workflows](<https://devfeed.tech/tags/agentic-workflows.md>), [code](<https://devfeed.tech/tags/code.md>), [competition](<https://devfeed.tech/tags/competition.md>), [complex](<https://devfeed.tech/tags/complex.md>), [costs](<https://devfeed.tech/tags/costs.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [cs-ma](<https://devfeed.tech/tags/cs-ma.md>), [execution](<https://devfeed.tech/tags/execution.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [feedback](<https://devfeed.tech/tags/feedback.md>), [framework](<https://devfeed.tech/tags/framework.md>), [inference](<https://devfeed.tech/tags/inference.md>), [inference-costs](<https://devfeed.tech/tags/inference-costs.md>), [llm](<https://devfeed.tech/tags/llm.md>), [model](<https://devfeed.tech/tags/model.md>), [negotiation](<https://devfeed.tech/tags/negotiation.md>), [semantic](<https://devfeed.tech/tags/semantic.md>), [tasks](<https://devfeed.tech/tags/tasks.md>), [workflows](<https://devfeed.tech/tags/workflows.md>)

## AI overview

The framework aims to reduce repeated LLM inference costs and delays by decomposing complex tasks into subtasks with explicit applicability conditions and reusable procedures. A procedure can execute code or invoke a model; execution feedback guides the agent in refining the decomposition and updating procedures. In GLEE competition experiments involving bargaining, negotiation and persuasion, most observed procedures for final decisions were implemented in code. The supplied excerpt does not report quantitative results or comparisons.

## Source excerpt

arXiv:2611.01840v1 Announce Type: new Abstract: 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.