Year: 2026
Type: conference-paper
Abstract: Recent studies indicate well-designed LLM-coordinated workflows outperform single models in task-solving. Though more works focus on autonomous workflow construction, most rely only on historical experience, limiting efficiency and adaptability. We propose an a priori dynamic framework for automated workflow construction: it uses Q-table learning to optimize decision-making (utilizing historical experience) and lets agents evaluate task progress for a priori decisions on the next agent, selecting suitable structures. Cold-start, early stopping and pruning are added to boost efficiency. Experiments on four benchmarks validate its feasibility: it outperforms state-of-the-art baselines by 4.1% on average and cuts construction/inference costs to 30.68%–48.31% of existing methods.
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4417081430
FWCI:
Cites:
Cited by:
Related to: