ATCC: Adaptive Concurrency Control for Unforeseen Agentic Transactions

2026-03-14

AI Summary

Traditional concurrency control mechanisms struggle to handle the unpredictable transactional behavior—such as long execution times and non-deterministic access patterns—induced by large language model–driven data agents, leading to severe performance degradation. This work proposes ATCC, an adaptive concurrency control framework tailored for agent-driven transactions, which, for the first time, integrates runtime behavior awareness with reinforcement learning to dynamically switch between optimistic and pessimistic strategies. ATCC further incorporates a cost-aware priority-based lock scheduling mechanism to reduce tail latency and minimize wasted inference effort. Experimental results demonstrate that under agent-like YCSB and TPC-C workloads, ATCC achieves up to four orders of magnitude higher throughput and reduces tail latency by as much as 90% compared to state-of-the-art approaches.

Technology Category

• Multiagent Systems: Agent Communication
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Search and Optimization: Learning to Search

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Data agents, empowered by Large Language Models (LLMs), introduce a new paradigm in transaction processing. Unlike traditional applications with fixed patterns, data agents run online-generated workflows that repeatedly issue SQL statements, reason over intermediate results, and revise subsequent plans. To ensure data consistency, these SQL statements issued by an agent should be integrated into a transaction, referred to as agentic transactions. Agentic transactions exhibit unforeseen characteristics, including long execution times, irregular execution intervals, and non-deterministic access patterns, breaking the assumptions underlying concurrency control (CC) (e.g., short-lived, predefined). Traditional CC schemes, which rely on fixed policies, fail to capture such dynamic behavior, resulting in inadequate performance. This paper introduces ATCC, an adaptive Concurrency Control for Agentic Transactions. ATCC continuously monitors and interprets the runtime behavior of each agentic transaction, evaluates its interactive phases, and dynamically adapts optimistic or pessimistic execution for each transaction. To ensure precise timing for adaptive switches, ATCC employs a reinforcement learning-based policy to balance immediate blocking against future abort costs. Additionally, to mitigate contention-induced tail latency and wasted reasoning cost caused by abort, a cost-aware priority-based lock scheduling is integrated to prioritize expensive or latency-sensitive transactions. Experimental results under agentic-like YCSB and TPC-C workloads demonstrate that ATCC improves the throughput of agentic transactions by up to four orders of magnitude and reduces tail latency by up to 90% compared to state-of-the-art CC schemes.

Problem

• agentic transactions
• concurrency control
• unforeseen behavior
• LLM-driven agents
• transaction processing

Innovation

• adaptive concurrency control
• agentic transactions
• reinforcement learning
• cost-aware scheduling
• LLM-driven agents