Year: 2026
Type: conference-paper
Abstract: Automatic workflow generation is the process of automatically synthesizing sequences of LLM calls, tool invocations, and postprocessing steps for complex end-to-end tasks.Most prior methods cast this task as an optimization problem with limited theoretical grounding.We propose to cast workflow generation as Bayesian inference over a posterior distribution on workflows, and introduce Bayesian Workflow Generation (BWG), a sampling framework that builds workflows step-by-step using parallel look-ahead rollouts for importance weighting and a sequential inloop refiner for pool-wide improvements.We prove that, without the refiner, the weighted empirical distribution converges to the target posterior.We instantiate BWG as BayesFlow, a training-free algorithm for workflow construction.Across six benchmark datasets, BayesFlow improves accuracy by up to 9 percentage points over SOTA workflow generation baselines and by up to 65 percentage points over zero-shot prompting, establishing BWG as a principled upgrade to search-based workflow design.
Institutions: Georgia Institute of Technology, Amazon (United States)
Language: English
Subfield: Information Systems and Management
Field: Decision Sciences
Domain: Social Sciences
Open Access status: hybrid
OpenAlex ID: W7140077755