Position: Multi-Agent Systems Should Prioritize Concurrency Control

观点：多智能体系统应优先考虑并发控制

LLM-based multi-agent systems (MAS) promise scalable collaboration, yet adding agents often reduces reliability. This position paper argues that many MAS failures are fundamentally concurrency control problems: agents concurrently read and write shared state, and long LLM inference windows amplify the risk of stale reads, lost updates, and inconsistent outcomes.

基于大语言模型（LLM）的多智能体系统（MAS）展现了可扩展协作的前景，但增加智能体数量往往会降低系统的可靠性。本篇观点论文指出，许多 MAS 的故障从根本上说是并发控制问题：智能体在并发地读取和写入共享状态，而 LLM 漫长的推理窗口放大了脏读（stale reads）、丢失更新（lost updates）以及结果不一致的风险。

Failure modes commonly attributed to coordination or communication breakdowns can be mapped directly onto classical concurrency anomalies. We contend that MAS frameworks should address these failures through explicit concurrency control mechanisms: conflict detection, isolation guarantees, and structured access to shared resources. Concurrency control should be a first-class design concern, not an afterthought.

通常被归因于协调或通信故障的失效模式，实际上可以直接映射到经典的并发异常中。我们主张，MAS 框架应通过显式的并发控制机制来解决这些故障，包括：冲突检测、隔离性保证以及对共享资源的结构化访问。并发控制应当成为系统设计的一等公民，而非事后的补救措施。