{"slug": "cost-aware-optimization-for-agentic-query-execution", "title": "Cost-Aware Optimization for Agentic Query Execution", "summary": "A new optimizer called EnumGRPO, developed by researchers, achieves 35.4% execution accuracy at $0.011 per query in LLM-operator cost on the SWAN benchmark, a ~317x cost reduction over the hybrid query baseline with an 18% relative improvement in answer accuracy. The work formalizes agentic query execution, where agent-based planning is interleaved with execution, and uses in-context reinforcement learning to distill quality-cost feedback into reusable planning heuristics.", "body_md": "# Computer Science > Databases\n\n[Submitted on 2 Jun 2026]\n\n# Title:Cost-Aware Optimization for Agentic Query Execution\n\n[View PDF](/pdf/2606.03152)\n\n[HTML (experimental)](https://arxiv.org/html/2606.03152v1)\n\nAbstract:Classical query optimization searches over algebraically equivalent plans that differ only in cost. This assumption breaks once LLM-backed operators enter the picture: their placement, ordering, and granularity jointly determine both dollar cost and answer quality, and the right choice among the alternatives is often revealed only at runtime. We formalize this setting as agentic query execution, a query execution paradigm in which agent-based planning is interleaved with execution, and agent workflow optimization becomes the analogue of classical query optimization. We then present EnumGRPO, a self-improving optimizer for this setting. During a learning stage, EnumGRPO enumerates query plans over decisions such as execution paradigm, operator type, operator placement, selectivity scope, and projection width, then distills quality-cost feedback into reusable planning heuristics via in-context reinforcement learning. Across four databases in SWAN, EnumGRPO achieves 35.4% execution accuracy at $0.011 per query in LLM-operator cost, a ~317x cost reduction over the hybrid query baseline with an 18% relative improvement in answer accuracy.\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/cost-aware-optimization-for-agentic-query-execution", "canonical_source": "https://arxiv.org/abs/2606.03152", "published_at": "2026-08-20 04:03:37+00:00", "updated_at": "2026-08-20 04:17:14.217950+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "ai-research", "ai-infrastructure"], "entities": ["EnumGRPO", "SWAN"], "alternates": {"html": "https://wpnews.pro/news/cost-aware-optimization-for-agentic-query-execution", "markdown": "https://wpnews.pro/news/cost-aware-optimization-for-agentic-query-execution.md", "text": "https://wpnews.pro/news/cost-aware-optimization-for-agentic-query-execution.txt", "jsonld": "https://wpnews.pro/news/cost-aware-optimization-for-agentic-query-execution.jsonld"}}