Rohan Paul@rohanpaul_ai · X斯坦福论文论证，在相等推理令牌预算下，单个LLM解决多跳问题通常比多代理系统更有效。核心在于单代理能保持完整的内部思维链，而多代理需将思维分割为消息传递与交接，每次交接都压缩信息并导致丢失，这以数据处理不等式为形式化解释。实验在多个模型和数据集上验证，预算匹配时单代理表现等同或优于多种多代理设置。多代理的常见增益可能源于额外计算或评估偏差，而非架构优势。论文建议，多跳推理应默认从强单代理开始，仅当单代理上下文受干扰退化时，才将多代理结构作为修复策略使用。
New Stanford paper argues that， under equal reasoning budgets， one LLM usually solves multi-hop problems better than many coordinated ones.
The core point is almost embarrassingly simple.
A single agent keeps the whole problem in one internal chain of thought， while a multi-agent system has to slice that chain into messages， summaries， and handoffs.
Every handoff is a compression step.
And once reasoning is compressed， some information is easier to drop than to recover， which is why the paper leans on the Data Processing Inequality as a formal explanation rather than just an empirical hunch.