arXiv AI
It Takes Workflows to Evolve Better Workflows
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
2d ago
Pay for the Fault, Not the Flow: Label-Free In-Flow Multi-Agent Workflow Optimization
The paper introduces InFlowOp, a label‑free optimization framework that assigns costs to each decision in a multi‑agent workflow, balancing agent competence against execution time. It determines task granularity and agent assignment before execution and corrects faults during execution using the same cost metric. The authors also present Braid, a benchmark for multi‑agent coordination, and show that InFlowOp outperforms single‑agent baselines by up to 11.97% across various domains.
arXiv Machine Learning
Jul 17
FlowBot: Inducing LLM Workflows with Bilevel Optimization and Textual Gradients
arXiv:2604. 26258v3 Announce Type: replace-cross 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.
arXiv AI
Jun 11
FlowBank: Query-Adaptive Agentic Workflows Optimization through Precompute-and-Reuse
arXiv:2606. 11290v1 Announce Type: cross Abstract: Large Language Model (LLM)-based multi-agent systems are increasingly powerful, but current agentic workflow optimization paradigms make an unsatisfying trade-off.
arXiv AI
Aug 21
FlowEvo: Self-Evolving Agents through the Co-Evolution of Workflows and Executable Skills
arXiv:2607. 21596v2 Announce Type: replace Abstract: Large language model agents can adapt to complex tasks by constructing workflows at inference time, but procedures discovered in one episode are usually discarded after execution.
arXiv Computer Vision
Aug 28
OS-Marathon: Benchmarking Computer-Use Agents on Vast-Horizon, Repetitive Tasks
OS-Marathon is a new benchmark that tests computer‑use agents on vast‑horizon, repetitive tasks, covering 100 tasks across five scenarios and ten domains. The study shows that current state‑of‑the‑art agents perform poorly on these tasks, and that simply decomposing workflows into subtasks does not solve the problem. Introducing a cost‑friendly personalization method called GraphDemo, which adapts agents from a single human demonstration, improves performance, highlighting the value of human guidance for these challenging tasks.
arXiv AI
Jun 2
When Does Multi-Agent RL Improve LLM Workflows? Workflow, Scale, and Policy-Sharing Tradeoffs
arXiv:2605. 24202v2 Announce Type: replace Abstract: Multi-agent LLM workflows route inference through specialized roles to lift end-task accuracy, but jointly training those roles with reinforcement learning is unstable in ways that are poorly understood.