HakiCC: LLM-Driven Multi-Agent Design and Optimization of Concurrency Control Protocols

2026-09-30

AI Summary

This study addresses the challenge that selecting concurrency control protocols relies heavily on expert knowledge and struggles to adapt to specific applications. To overcome this, we propose an automated framework based on a large language model (LLM) multi-agent pipeline. This approach introduces a novel two-stage process: it first automatically generates protocols by iteratively repairing and verifying conflict serializability, and subsequently employs evolutionary algorithms to optimize throughput cyclically. Experimental results demonstrate that all ten generated protocols pass correctness verification, achieving average throughput improvements of 50.6% and 92.2% on the TPC-C and AuctionMark benchmarks, respectively. Ultimately, this work realizes the automated design and significant performance breakthroughs of application-specific concurrency control protocols.

Abstract

Large language models (LLMs) have recently been applied in systems research as a tool to reduce human-intensive engineering effort through cost-efficient automation. Decades of research have produced a rich landscape of concurrency control (CC) protocols, each encoding distinct trade-offs in correctness, throughput, and abort behavior. However, most applications in practice default to 2PL or OCC, because selecting and adapting a protocol to a specific application requires expert knowledge that is rarely available to application designers. This is a wasted opportunity, as an application-specific CC protocol can yield significant performance advantages over a generic baseline, but designing one requires deep expertise in CC protocol design. In this paper, we propose HakiCC, an LLM-driven multi-agent pipeline that automatically designs, verifies, and optimizes concurrency control protocols tailored to a given target application. HakiCC provides a two-stage pipeline. In Stage 1, a multi-agent system takes a workload description as input and generates an application-specific CC protocol implementation, which is iteratively repaired and verified for conflict-serializability. In Stage 2, the verified protocol is further optimized for that application through an LLM-driven evolutionary loop targeting correctness and throughput. We evaluate HakiCC on TPC-C and AuctionMark as target workloads, producing and reporting ten application-specific CC protocols. All ten are conflict-serializable after Stage 1; Stage 2 improves throughput for every protocol, with average gains of +50.6% for TPC-C protocols and +92.2% for AuctionMark protocols.

Problem

• Concurrency Control
• Large Language Models
• Protocol Design
• Database Systems
• Performance Optimization

Innovation

• Large Language Models
• Multi-Agent System
• Concurrency Control
• Automated Protocol Design
• Evolutionary Optimization