{"slug": "distilling-proprietary-model-reasoning-into-open-source-search-agents", "title": "Distilling proprietary model reasoning into open-source search agents", "summary": "Researchers propose Multi-Agent Protocol Distillation (MAPD), a framework that distills reasoning from proprietary large language models into open-source search agents using a structured JSON protocol as an intermediate representation, achieving average success rates of 39.4% on Qwen3-1.7B and 44.4% on Qwen3-4B across seven QA benchmarks.", "body_md": "# Computer Science > Artificial Intelligence\n\n[Submitted on 27 Jul 2026]\n\n# Title:From Proprietary to Open-Source: Bridging the Distribution Gap via Multi-Agent Protocol Distillation in Agentic Search\n\n[View PDF](/pdf/2607.24280)\n\n[HTML (experimental)](https://arxiv.org/html/2607.24280v1)\n\nAbstract: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.\n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer\n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers\n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps\n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations\n\n*(*[What are Smart Citations?](https://www.scite.ai/))# Code, Data and Media Associated with this Article\n\nalphaXiv\n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers\n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub\n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub\n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face\n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast\n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower\n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender\n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.\n\nHave an idea for a project that will add value for arXiv's community? [ Learn more about arXivLabs](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/distilling-proprietary-model-reasoning-into-open-source-search-agents", "canonical_source": "https://arxiv.org/abs/2607.24280", "published_at": "2026-07-28 17:37:07+00:00", "updated_at": "2026-07-28 17:52:15.486249+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-agents", "ai-research"], "entities": ["Multi-Agent Protocol Distillation", "Qwen3-1.7B", "Qwen3-4B"], "alternates": {"html": "https://wpnews.pro/news/distilling-proprietary-model-reasoning-into-open-source-search-agents", "markdown": "https://wpnews.pro/news/distilling-proprietary-model-reasoning-into-open-source-search-agents.md", "text": "https://wpnews.pro/news/distilling-proprietary-model-reasoning-into-open-source-search-agents.txt", "jsonld": "https://wpnews.pro/news/distilling-proprietary-model-reasoning-into-open-source-search-agents.jsonld"}}