{"ID":2858451,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.08803","arxiv_id":"2510.08803","title":"Man-Made Heuristics Are Dead. Long Live Code Generators!","abstract":"Policy design for various systems controllers has conventionally been a manual process, with domain experts carefully tailoring heuristics for the specific instance in which the policy will be deployed. In this paper, we re-imagine policy design via a novel automated search technique fueled by recent advances in generative models, specifically Large Language Model (LLM)-driven code generation. We outline the design and implementation of PolicySmith, a framework that applies LLMs to synthesize instance-optimal heuristics. We apply PolicySmith to two long-standing systems policies - web caching and congestion control, highlighting the opportunities unraveled by this LLM-driven heuristic search. For caching, PolicySmith discovers heuristics that outperform established baselines on standard open-source traces. For congestion control, we show that PolicySmith can generate safe policies that integrate directly into the Linux kernel.","short_abstract":"Policy design for various systems controllers has conventionally been a manual process, with domain experts carefully tailoring heuristics for the specific instance in which the policy will be deployed. In this paper, we re-imagine policy design via a novel automated search technique fueled by recent advances in genera...","url_abs":"https://arxiv.org/abs/2510.08803","url_pdf":"https://arxiv.org/pdf/2510.08803v1","authors":"[\"Rohit Dwivedula\",\"Divyanshu Saxena\",\"Aditya Akella\",\"Swarat Chaudhuri\",\"Daehyeok Kim\"]","published":"2025-10-09T20:35:00Z","proceeding":"cs.OS","tasks":"[\"cs.OS\",\"cs.DC\",\"cs.LG\",\"cs.NE\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}