arXiv subjects

Qiushi Bai

Publications and source records attributed to Qiushi Bai.

3 recordsLinked to original sources

arXiv2026

GraphMind: From Operational Traces to Self-Evolving Workflow Automation

Complex operational workflows coordinating personnel, tools, and information are central to system operations, yet end-to-end automation remains challenging due to extensive human input requirements and limited ability to adapt over time. We present GraphMind, a system that constructs, executes, and evolves action-centric workflow graphs with minimal 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, enabling execution-informed graph adaptation. GraphMind has been deployed across four production cloud database services for incident investigation. Evaluated on 93 held-out incidents and validated via blind expert review, the system outperforms an Agentic Summary-RAG baseline in mitigation reach, hallucination rate, and diagnostic throughput while requiring 8x less retrieval context. The ATR layer reduces hallucination rate by 26%, demonstrating that workflow graphs can learn from execution feedback. A 12-week field study confirms practical value: 97% of scored conversations yield actionable results within interactive latency.

cs.AI↗

arXiv2023

QueryBooster: Improving SQL Performance Using Middleware Services for Human-Centered Query Rewriting

SQL query performance is critical in database applications, and query rewriting is a technique that transforms an original query into an equivalent query with a better performance. In a wide range of database-supported systems, there is a unique problem where both the application and database layer are black boxes, and the developers need to use their knowledge about the data and domain to rewrite queries sent from the application to the database for better performance. Unfortunately, existing solutions do not give the users enough freedom to express their rewriting needs. To address this problem, we propose QueryBooster, a novel middleware-based service architecture for human-centered query rewriting, where users can use its expressive and easy-to-use rule language (called VarSQL) to formulate rewriting rules based on their needs. It also allows users to express rewriting intentions by providing examples of the original query and its rewritten query. QueryBooster automatically generalizes them to rewriting rules and suggests high-quality ones. We conduct a user study to show the benefits of VarSQL to formulate rewriting rules. Our experiments on real and synthetic workloads show the effectiveness of the rule-suggesting framework and the significant advantages of using QueryBooster for human-centered query rewriting to improve the end-to-end query performance.

cs.DB↗

arXiv2022

Maliva: Using Machine Learning to Rewrite Visualization Queries Under Time Constraints

We consider data-visualization systems where a middleware layer translates a frontend request to a SQL query to a backend database to compute visual results. We study the problem of answering a visualization request within a limited time constraint due to the responsiveness requirement. We explore the optimization options of rewriting an original query by adding hints and/or doing approximations so that the total time is within the time constraint. We develop a novel middleware solution called Maliva based on machine learning (ML) techniques. It applies the Markov Decision Process (MDP) model to decide how to rewrite queries and uses training instances to learn an agent to make a sequence of decisions judiciously for an online request. We give a full specification of the technique, including how to construct an MDP model, how to train an agent, and how to use approximating rewrite options. Our experiments on both real and synthetic datasets show that Maliva performs significantly better than a baseline solution that does not do any rewriting, in terms of both the probability of serving requests interactively and query execution time.

cs.DB↗