GraphMind: From Operational Traces to Self-Evolving Workflow Automation

TL;DR

GraphMind is an innovative system that automatically constructs, executes, and self-evolves operational workflow graphs from traces, significantly improving incident investigation efficiency in enterprise cloud services.

Contribution

It introduces a fully automated, multi-phase system that builds, executes, and self-optimizes workflow graphs without human effort, leveraging reinforcement learning from operational feedback.

Findings

Outperforms Trace-RAG baseline in mitigation reach, groundedness, and diagnostic throughput.

Scores 4.95/5 in blind expert review.

Self-optimizing workflow graphs improve over time with reinforcement learning.

Abstract

Complex operational workflows coordinating personnel, tools, and information are central to enterprise operations, yet end-to-end automation remains challenging due to extensive requirements for human inputs and the inability to adapt over time. We present GraphMind, an end-to-end system that constructs, executes, and evolves action-centric workflow graphs without human effort. The system operates in three phases. First, a scalable offline pipeline extracts structured workflow graphs from large volumes of human resolution traces, capturing problems, actions, and their causal relationships. Second, an online multi-agent traversal engine navigates the graph to dynamically construct and execute workflows, combining graph-guided retrieval with LLM-driven reasoning at each step. Third, Adaptive Traversal Reinforcement (ATR) reinforces successful traversal paths and decays stale elements. This closed-loop mechanism enables the graph to self-optimize and adapt to shifting operational conditions. GraphMind has been deployed across four production cloud database services for incident investigation. Evaluated on production data, the system substantially outperforms a Trace-RAG baseline in mitigation reach, groundedness, and diagnostic throughput, scoring 4.95/5 in blind expert review. The ATR layer provides further gains across all metrics, demonstrating that workflow graphs can learn and improve from execution-derived feedback.