Man-Made Heuristics Are Dead. Long Live Code Generators!

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Dwivedula, Rohit, Saxena, Divyanshu, Akella, Aditya, Chaudhuri, Swarat, Kim, Daehyeok
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917001327280128
author Dwivedula, Rohit
Saxena, Divyanshu
Akella, Aditya
Chaudhuri, Swarat
Kim, Daehyeok
author_facet Dwivedula, Rohit
Saxena, Divyanshu
Akella, Aditya
Chaudhuri, Swarat
Kim, Daehyeok
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_08803
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Man-Made Heuristics Are Dead. Long Live Code Generators!
Dwivedula, Rohit
Saxena, Divyanshu
Akella, Aditya
Chaudhuri, Swarat
Kim, Daehyeok
Operating Systems
Distributed, Parallel, and Cluster Computing
Machine Learning
Neural and Evolutionary Computing
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.
title Man-Made Heuristics Are Dead. Long Live Code Generators!
topic Operating Systems
Distributed, Parallel, and Cluster Computing
Machine Learning
Neural and Evolutionary Computing
url https://arxiv.org/abs/2510.08803