As large language models from diverse providers converge toward comparable benchmark performance, the traditional paradigm of selecting a single best model per task yields diminishing returns. We argue that orchestration topology -- the structural composition of how multiple agents are coordinated, parallelized, and synthesized -- now dominates system-level performance over individual model capability. We present AdaptOrch, a formal framework for task-adaptive multi-agent orchestration that dynamically selects among four canonical topologies (parallel, sequential, hierarchical, and hybrid) based on task dependency graphs and empirically derived domain characteristics. Our framework introduces three key contributions: (1) a Performance Convergence Scaling Law, formalizing conditions under which orchestration selection outweighs model selection; (2) a Topology Routing Algorithm that maps task decomposition DAGs to optimal orchestration patterns in O(|V| + |E|) time; and (3) an Adaptive Synthesis Protocol with provable termination guarantees and heuristic consistency scoring for parallel agent outputs. We validate AdaptOrch across coding (SWE-bench), reasoning (GPQA), and retrieval-augmented generation tasks, demonstrating that topology-aware orchestration achieves 12-23% improvement over static single-topology baselines, even when using identical underlying models. Our results establish orchestration design as a first-class optimization target independent of model scaling.

翻译：随着来自不同供应商的大语言模型在基准测试性能上趋于接近，传统"为每项任务选择单一最佳模型"的范式带来的边际效益日益递减。我们认为，在当前阶段，编排拓扑结构——即多个智能体如何被协调、并行化与合成的结构组合——对系统级性能的影响已超越单个模型能力。本文提出AdaptOrch，一个任务自适应多智能体编排的形式化框架，该框架能依据任务依赖图和实证获得的领域特征，在四种典型拓扑结构（并行、串行、分层与混合）间动态选择。本框架包含三项核心贡献：（1）性能趋同缩放定律，形式化地界定了编排选择优于模型选择的条件；（2）拓扑路由算法，以O(|V| + |E|)时间复杂度将任务分解有向无环图映射至最优编排模式；（3）具备可证明终止保证的自适应合成协议，并为并行智能体输出提供启发式一致性评分。我们在编码（SWE-bench）、推理（GPQA）与检索增强生成任务上验证了AdaptOrch，结果表明：即使使用完全相同的底层模型，拓扑感知的编排相比静态单拓扑基线仍能实现12-23%的性能提升。我们的研究确立了编排设计作为独立于模型缩放的一级优化目标。