WorkflowOps: Learning Agent Collaboration Priors for Multi-Agent Workflow Orchestration

Key points

• Multi-agent systems are increasingly deployed for complex knowledge work, yet their orchestration layers remain largely memoryless: each new task is decomposed, assigned, and executed from scratch with no benefit from prior successful executions.1
• First, a transition probability matrix captures pairwise agent collaboration frequencies from past workflows and applies them as soft guidance during DAG workflow construction through intra-layer ordering optimization, probability-thresholded edge suggestion, and transitive reduction for parallelism maximization.1
• Second, a sufficiency-driven agent creation loop detects capability gaps via semantic matching scores, generates specialized agents through an LLM, and simultaneously injects them into the collaboration matrix, so that newly created agents are immediately usable with predicted collaboration priors.1
• Experiments on mixed code, math, and question-answering suites show that WorkflowOps improves end-to-end pass rates over recent workflow-construction baselines, with the largest gains on structured, decomposable tasks where past agent handoff patterns transfer.1

Sources (1)

• [1]WorkflowOps: Learning Agent Collaboration Priors for Multi-Agent Workflow Orchestration
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 6, 07:01 AM

  We present WorkflowOps, a multi-agent workflow orchestration framework that learns agent collaboration priors from historical workflows and expands its agent pool on demand to cover new capability requirements.

  Multi-agent systems are increasingly deployed for complex knowledge work, yet their orchestration layers remain largely memoryless: each new task is decomposed, assigned, and executed from scratch with no benefit from prior successful executions.

Extractive summary: sentences quoted from the sources.