FloWright, which leverages the workflow as a harness to optimize workflows by introducing a hierarchical, structure-aware reward paradigm, and enables one role to self-evolve and two or more roles to co-evolve, with no additional models, labels, or executions.
Abstract
Tackling complex real-world tasks can exceed the capabilities of a single large language model (LLM), motivating the use of multi-agent workflows that coordinate specialized agents to work together on these tasks. Recent methods train LLMs to construct better workflows from execution outcomes, but they optimize only the workflow generator, while the other agents that build or execute each workflow remain fixed even though every outcome depends on all of them. However, extending training beyond the generator is challenging: the agents are coupled, and a workflow's outcome is a single sparse score that cannot tell which agent causes a failure. We propose FloWright, which leverages the workflow as a harness to optimize workflows. By introducing a hierarchical, structure-aware reward paradigm, FloWright enables one role to self-evolve and two or more roles to co-evolve, with no additional models, labels, or executions. Considering the limitation that workflows are commonly trained and evaluated on data that a single agent can already handle, we further propose DataWright, an adaptive data hardening approach that converts existing datasets into workflow-level tasks with increased difficulty. Across document, slide, chart, code, math, and finance tasks, small open models trained with FloWright achieve improved performance by up to $+7.41\%$, with co-evolving ($+5.03\%$) more roles gaining more than optimizing one of them alone ($+2.83\%$). Our project page: https://xhguo7.github.io/FloWright/.
Large language models (LLMs) increasingly construct multi-agent workflows that decompose a complex task and assign specialist agents from a pool. However, building such a workflow well remains challenging: how finely to divide the task, which agent to trust with each subtask, and when to create a new specialist are all...
Xue-Hang Guo, Hao-Yu Wang, Sheng-Yu Chen et al.· 0 citations
MoFlow formulates workflow generation as a multi-objective Markov decision process and solves it by leveraging Convex-Hull Monte Carlo Tree Search with optimistic set-valued backups, where every node stores a set of reachable trade-offs rather than one weighted score.
Yining Lu, Aurélie C. Lozano, Xi Yang et al.· arXiv.org· 0 citations
Large language model agents are increasingly deployed as multi-agent systems rather than as a standalone model operating within a single context. Recent agent harnesses allow the model to instantiate worker agents and to author the executable workflow that coordinates them, shifting the design of system structure from...
Zheng Jiang, Fang Niu, Bo-Kai Peng et al.· 0 citations
Large Language Model (LLM) agents have demonstrated remarkable capabilities in tackling complex tasks through agentic workflows. However, manually designing these workflows is labor-intensive and lacks flexibility to adapt to diverse queries. While automated workflow optimization is a promising direction, existing meth...
Jia-Hang Sun, Zhi-Wei Shang, Zhi-Piao Liu et al.· 0 citations
Large Language Model-based Multi-Agent Systems (LLM-based MAS) have shown remarkable success in solving complex tasks by coordinating specialized agents through multi-step workflows. To overcome the high cost and specificity of manually designed workflows, recent research has shifted toward learning them automatically....
En-Pei Zhang, Fei-Yu Qu, Zheng Huang et al.· 0 citations
This work introduces MAWGE (Multi-Agentic Workflow Generator Engine), a library for generating parametric and synthetic multi-agentic workflows with distinct topologies, compositions and execution characteristics and believes that MAWGE provides a standardized toolkit for generating reproducible synthetic benchmarks on...