natural language processing

FlowBot: Inducing LLM Workflows with Bilevel Optimization and Textual Gradients

arXiv:2604.26258

summary

The paper proposes FlowBot, a data‑driven method that automatically creates LLM agent pipelines by using bilevel optimization and textual gradients to structure and fine‑tune each LLM call.

Abstract

LLM workflows, which coordinate structured calls to individual LLMs/agents to achieve a particular goal, offer a promising path towards building powerful AI systems that can tackle diverse tasks. However, existing approaches for building such workflows generally rely on human-crafted pipelines and prompts, which presents a substantial bottleneck in real world deployment. How can we automatically induce LLM-based agents and workflows in a data-driven way? This paper describes a simple data-driven approach for automatically inducing agents and LLM workflows. We formulate workflow induction as a bilevel optimization problem: an outer loop which optimizes a high-level sketch of the workflow (in particular how the LLM calls should be structured), and an inner loop which optimizes each individual LLM call one-by one. Both loops are optimized with ``textual gradients'' where for the inner loop we optimize each component in a modular way through ``backpropagating'' textual gradients layer-by-layer. We find that LLM workflows discovered through our \textsc{FlowBot} (work\textbf{flow} induction through \textbf{b}ilevel \textbf{o}ptimization and \textbf{t}extual gradients) approach performs competitively against strong baselines that make use of human-crafted or generated workflows.

Topics & keywords

#llm workflow induction#bilevel optimization#textual gradients#automated prompting#agent coordinationbilevel optimizationtextual gradientsLLM agentsworkflow inductiongradient‑based prompt optimization
FlowBot: Inducing LLM Workflows with Bilevel Optimization and Textual Gradients · wovepaper