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

arXiv: https://arxiv.org/abs/2510.08803 · HTML: https://mlsanity.com/paper/2510.08803/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 72 references that are in the map.
- First posted on arXiv 9 Oct 2025.

## Builds on (most cited first, 8 of 8)

- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [Symbolic Regression with a Learned Concept Library](https://mlsanity.com/paper/2409.09359/) (2024)
- [Shaking the foundations: delusions in sequence models for interaction and control](https://mlsanity.com/paper/2110.10819/) (2021)
- [On the Effectiveness of Large Language Models in Domain-Specific Code Generation](https://mlsanity.com/paper/2312.01639/) (2023)
- [What do LLMs need to Synthesize Correct Router Configurations?](https://mlsanity.com/paper/2307.04945/) (2023)
- [Designing Network Algorithms via Large Language Models](https://mlsanity.com/paper/2404.01617/) (2024)
- [ROBUS: Fair Cache Allocation for Multi-tenant Data-parallel Workloads](https://mlsanity.com/paper/1504.06736/) (2015)
- [Universal Packet Scheduling](https://mlsanity.com/paper/1510.03551/) (2015)

## Built on by (most cited first, 6 of 6)

- [Glia: A Human-Inspired AI for Automated Systems Design and Optimization](https://mlsanity.com/paper/2510.27176/) (2025)
- [Improving Coherence and Persistence in Agentic AI for System Optimization](https://mlsanity.com/paper/2603.21321/) (2026)
- [Computer Architecture's AlphaZero Moment: Automated Discovery in an Encircled World](https://mlsanity.com/paper/2604.03312/) (2026)
- [Let the Barbarians In: How AI Can Accelerate Systems Performance Research](https://mlsanity.com/paper/2512.14806/) (2025)
- [Vulcan: Instance-specialized, Verifiable Systems Heuristics Through LLM-driven Search](https://mlsanity.com/paper/2512.25065/) (2025)
- [Can You Check That? The Checkability Boundary for Local LLM Network Automation](https://mlsanity.com/paper/2609.31540/) (2026)

## Abstract (arXiv)

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.