Large Language Model (LLM)-based multi-agent systems rely on optimized collaboration topologies to balance performance and communication costs. However, current methods struggle with the inherent stability-extensibility trade-off and often misalign computational budgets with query difficulty. We propose \textsc{ATOM}, an adaptive framework that generates budget-controllable collaboration graphs via a novel task-driven reinforcement learning paradigm. Inspired by atomic structures, \textsc{ATOM} employs a nucleus-electron hierarchy: it maintains a stable, offline-learned collaboration backbone (the nucleus) while dynamically activating query-conditioned agents (electrons) during inference. Crucially, a complexity-aware budgeting strategy aligns resource consumption with task demands by estimating query difficulty to strictly regulate electron instantiation. Extensive experiments across six diverse benchmarks demonstrate that \textsc{ATOM} achieves state-of-the-art performance while improving token efficiency by up to $30\%$ compared to strong baselines.

翻译：基于大型语言模型（LLM）的多智能体系统依赖优化的协作拓扑来平衡性能与通信成本。然而，当前方法难以处理固有的稳定性-可扩展性权衡，并且常导致计算预算与查询难度失配。我们提出ATOM，一种通过新颖的任务驱动强化学习范式生成预算可控协作图的自适应框架。受原子结构启发，ATOM采用核-电子层次结构：它维护一个稳定的、离线学习的协作主干（原子核），同时在推理阶段动态激活查询条件驱动的智能体（电子）。关键在于，一种复杂度感知的预算策略通过估计查询难度来严格调控电子实例化，从而将资源消耗与任务需求对齐。在六个不同基准上的广泛实验表明，与强基线相比，ATOM在实现最先进性能的同时，将令牌效率提升了高达30%。