重新思考多智能体协作：何时多即是少
Rethinking Multi-Agent Collaboration: When More Is Less
- Shanghai Jiao Tong University（上海交通大学）
- Nanjing University（南京大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本研究通过分析多智能体协作的能力边界，提出基于语义感知增量图演化的SAIGE机制，证明其在长时程稀疏依赖任务中优于单智能体，且更多智能体并不必然提升性能。
AI中文摘要：
大型语言模型和单智能体框架的快速发展重塑了自主系统的格局，引发了一个关键问题：多智能体协作何时能带来真正的价值。随着单个智能体能力的持续扩展，多智能体协作面临收益递减，同时产生不断增长的上下文开销。通过系统性分析，我们描绘了多智能体协作相对于单智能体替代方案的能力边界，表明其在具有稀疏依赖关系的长时程任务中能带来系统性优势，而单智能体框架在紧密耦合的顺序工作流中仍保持优越性。基于这些见解，我们提出了SAIGE，一种基于语义感知增量图演化的轻量级多智能体协作机制。SAIGE将协作建模为动态演化的图，其中节点是按需生成的智能体实例，边通过基于内容的信息检索编码语义依赖关系。在长时程、复杂任务基准上的实验表明，SAIGE在上下文效率与任务性能之间实现了有利的权衡，且扩大智能体池或加深递归级别并不总能改善结果。我们的发现表明，多智能体的优越性受限于任务结构而非普遍适用，更多的智能体并不必然使系统更智能。
英文摘要：
The rapid advancement of large language models and single-agent harnesses has reshaped the landscape of autonomous systems, raising a critical question of when multi-agent collaboration offers genuine value. As individual agent capabilities continue to scale, multi-agent collaboration faces diminishing returns while incurring growing context overhead. Through systematic analysis, we delineate the capability boundaries of multi-agent collaboration relative to single-agent alternatives, showing that it confers systematic benefits specifically in long-horizon tasks with sparse dependencies, while single-agent harnesses remain superior in tightly coupled, sequential workflows. Building on these insights, we propose SAIGE, a lightweight multi-agent collaboration mechanism based on Semantic-Aware Incremental Graph Evolution. SAIGE models collaboration as a dynamically evolving graph, where nodes are agent instances spawned on demand and edges encode semantic dependencies established through content-based information retrieval. Experiments on long-horizon, complex task benchmarks show that SAIGE achieves a favorable trade-off between context efficiency and task performance, and that scaling the agent pool or deepening the recursion level does not consistently improve outcomes. Our findings suggest that multi-agent superiority is bounded by task structure rather than universal, and that more agents do not necessarily make a system more intelligent.
