Multi-agent LLM systems fail to realize parallel speedups due to costly coordination. We present CodeCRDT, an observation-driven coordination pattern where agents coordinate by monitoring a shared state with observable updates and deterministic convergence, rather than explicit message passing. Using Conflict-Free Replicated Data Types (CRDTs), CodeCRDT enables lock-free, conflict-free concurrent code generation with strong eventual consistency. Evaluation across 600 trials (6 tasks, 50 runs per mode) shows both benefits and trade-offs: up to 21.1% speedup on some tasks, up to 39.4% slowdown on others, and 100% convergence with zero merge failures. The study formalizes observation-driven coordination for stochastic LLM agents, revealing semantic conflict rates (5-10%) and quality-performance tradeoffs, and provides empirical characterization of when parallel coordination succeeds versus fails based on task structure.

翻译：多智能体大语言模型系统因高昂的协调成本而难以实现并行加速。本文提出CodeCRDT——一种观测驱动的协调范式，其通过可观测更新与确定性收敛的共享状态监控实现智能体协调，而非依赖显式消息传递。基于无冲突复制数据类型（CRDTs），CodeCRDT实现了具备强最终一致性的无锁、无冲突并发代码生成。通过600次实验评估（6项任务，每种模式50次运行）揭示了该方法的优势与权衡：部分任务最高获得21.1%加速，部分任务最高出现39.4%减速，收敛率达100%且零合并失败。本研究为随机性大语言模型智能体建立了观测驱动协调的形式化框架，揭示了语义冲突率（5-10%）与质量-性能权衡关系，并通过任务结构特征实证分析了并行协调机制的成功与失效条件。