# Vulcan: Instance-specialized, Verifiable Systems Heuristics Through LLM-driven Search

arXiv: https://arxiv.org/abs/2512.25065 · HTML: https://mlsanity.com/paper/2512.25065/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 114 references that are in the map.
- First posted on arXiv 31 Dec 2025.

## Builds on (most cited first, 29 of 29)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [Measuring Coding Challenge Competence With APPS](https://mlsanity.com/paper/2105.09938/) (2021)
- [AlphaEvolve: A coding agent for scientific and algorithmic discovery](https://mlsanity.com/paper/2506.13131/) (2025)
- [Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models](https://mlsanity.com/paper/2310.04406/) (2023)
- [Executable Code Actions Elicit Better LLM Agents](https://mlsanity.com/paper/2402.01030/) (2024)
- [BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions](https://mlsanity.com/paper/2406.15877/) (2024)
- [ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution](https://mlsanity.com/paper/2509.19349/) (2025)
- [Learning Scheduling Algorithms for Data Processing Clusters](https://mlsanity.com/paper/1810.01963/) (2018)
- [DynamoLLM: Designing LLM Inference Clusters for Performance and Energy Efficiency](https://mlsanity.com/paper/2408.00741/) (2024)
- [SWE-PolyBench: A multi-language benchmark for repository level evaluation of coding agents](https://mlsanity.com/paper/2504.08703/) (2025)
- [Serverless in the Wild: Characterizing and Optimizing the Serverless Workload at a Large Cloud Provider](https://mlsanity.com/paper/2003.03423/) (2020)
- [Heterogeneity-Aware Cluster Scheduling Policies for Deep Learning Workloads](https://mlsanity.com/paper/2008.09213/) (2020)
- [TAPAS: Thermal- and Power-Aware Scheduling for LLM Inference in Cloud Platforms](https://mlsanity.com/paper/2501.02600/) (2025)
- [Code Researcher: Deep Research Agent for Large Systems Code and Commit History](https://mlsanity.com/paper/2506.11060/) (2025)
- [Security and Quality in LLM-Generated Code: A Multi-Language, Multi-Model Analysis](https://mlsanity.com/paper/2502.01853/) (2025)
- [TokenCake: A KV-Cache-centric Serving Framework for LLM-based Multi-Agent Applications](https://mlsanity.com/paper/2510.18586/) (2025)
- [Glia: A Human-Inspired AI for Automated Systems Design and Optimization](https://mlsanity.com/paper/2510.27176/) (2025)
- [The GAP Benchmark Suite](https://mlsanity.com/paper/1508.03619/) (2015)
- [TPP: Transparent Page Placement for CXL-Enabled Tiered-Memory](https://mlsanity.com/paper/2206.02878/) (2022)
- [Man-Made Heuristics Are Dead. Long Live Code Generators!](https://mlsanity.com/paper/2510.08803/) (2025)
- [Congestion Control System Optimization with Large Language Models](https://mlsanity.com/paper/2508.16074/) (2025)
- [LAVA: Lifetime-Aware VM Allocation with Learned Distributions and Adaptation to Mispredictions](https://mlsanity.com/paper/2412.09840/) (2024)
- [The eBPF Runtime in the Linux Kernel](https://mlsanity.com/paper/2410.00026/) (2024)
- [Robust Heuristic Algorithm Design with LLMs](https://mlsanity.com/paper/2510.08755/) (2025)
- [ROBUS: Fair Cache Allocation for Multi-tenant Data-parallel Workloads](https://mlsanity.com/paper/1504.06736/) (2015)
- [C2TCP: A Flexible Cellular TCP to Meet Stringent Delay Requirements](https://mlsanity.com/paper/1810.13241/) (2018)

## Built on by (most cited first, 1 of 1)

- [LLM-Driven Heuristic Synthesis for Industrial Process Control: Lessons from Hot Steel Rolling](https://mlsanity.com/paper/2603.20537/) (2026)

## Abstract (arXiv)

Systems resource management tasks rely primarily on hand-designed heuristics. However, growing hardware heterogeneity and workload diversity require heuristics specialized to particular deployment instances, making manual design expensive and difficult to scale. In this paper, we explore how to synthesize systems heuristics using LLMs. The main challenge is ensuring that generated heuristics execute safely, integrate correctly with the surrounding system, and still achieve strong performance. We propose Vulcan, a framework that identifies LLM-friendly interfaces that isolate core decision logic from the rest of the implementation. With Vulcan, LLM-generated code is restricted to simple stateless decision functions, while trusted runtime abstractions provide rich derived statistics for meaningful policy exploration without system-integration bugs. To ensure execution safety, LLMs synthesize heuristics in a restricted language, Anvil, that guarantees important properties by construction. We evaluate Vulcan across three well-studied domains and demonstrate up to 4.9× higher savings for spot-VM scheduling, up to 2× lower miss ratios for cache eviction, and up to 14% higher application performance for tiered-memory systems, while ensuring execution safety throughout.