让AI学会搜索：用协议蒸馏缩小开源与闭源差距
开源AI模型在需要多步搜索推理的任务上一直落后于闭源模型，因为闭源模型不公开内部逻辑，模仿其回答只会学到表面风格而非推理能力。研究者提出一种新方法：让一个多智能体系统把搜索过程拆解成结构化的JSON协议（包含任务类型、推理计划、事实依据），然后只把这个协议作为额外信号教给学生模型，同时保留强化学习。在7个问答基准上，1.7B参数的小模型平均成功率提升到39.4%，4B模型到44.4%。这不是你明天能直接用的工具，但它展示了如何让开源模型在复杂搜索推理上追上闭源——不靠模仿答案，而是靠学习解题过程的结构。
📄 原文摘要(英文)
Agentic search enables large language models to solve knowledge-intensive tasks by interleaving multi-step reasoning with retrieval, yet optimizing this with outcome-based reinforcement learning (RL) provides only sparse supervision. Knowledge distillation can supply denser guidance, and advanced proprietary models with their strong reasoning capabilities are promising teachers. While distilling from proprietary models can densify this supervisory signal, conventional logit-matching is precluded by hidden logits and mismatched tokenizers, whereas raw natural language trajectory imitation transfers superficial stylistic artifacts rather than core reasoning competence. To address the heterogeneous distillation problem and bridge the distribution gap, we propose Multi-Agent Protocol Distillation (MAPD), a joint distillation and RL framework uses a structured, style-normalized protocol as an intermediate representation. An offline multi-agent system (MAS) decomposes each query, retrieves supporting evidence, repairs failed searches, and converts the resulting exploration trace into a JSON protocol containing the task type, reasoning plan, and extractive grounding facts. During training, the protocol is provided only to a privileged branch of the student policy, whose token distributions furnish a dense distillation signal alongside the sparse RL objective. Extensive evaluations across seven QA benchmarks demonstrate that MAPD consistently outperforms competitive distillation and RL, achieving average success rates of 39.4\% on Qwen3-1.7B and 44.4\% on Qwen3-4B. Crucially, the framework generalizes robustly across diverse proprietary teachers while effectively mitigating the student policy from style drift and verbosity degeneration.