Vulcan: Instance-Optimal Systems Heuristics Through LLM-Driven Search
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917178543964160 |
|---|---|
| author | Dwivedula, Rohit Saxena, Divyanshu Yadalam, Sujay Kim, Daehyeok Akella, Aditya |
| author_facet | Dwivedula, Rohit Saxena, Divyanshu Yadalam, Sujay Kim, Daehyeok Akella, Aditya |
| contents | Resource-management tasks in modern operating and distributed systems continue to rely primarily on hand-designed heuristics for tasks such as scheduling, caching, or active queue management. Designing performant heuristics is an expensive, time-consuming process that we are forced to continuously go through due to the constant flux of hardware, workloads and environments.
We propose a new alternative: synthesizing instance-optimal heuristics -- specialized for the exact workloads and hardware where they will be deployed -- using code-generating large language models (LLMs). To make this synthesis tractable, Vulcan separates policy and mechanism through LLM-friendly, task-agnostic interfaces. With these interfaces, users specify the inputs and objectives of their desired policy, while Vulcan searches for performant policies via evolutionary search over LLM-generated code. This interface is expressive enough to capture a wide range of system policies, yet sufficiently constrained to allow even small, inexpensive LLMs to generate correct and executable code.
We use Vulcan to synthesize performant heuristics for cache eviction and memory tiering, and find that these heuristics outperform all human-designed state-of-the-art algorithms by upto 69% and 7.9% in performance for each of these tasks respectively. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_25065 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Vulcan: Instance-Optimal Systems Heuristics Through LLM-Driven Search Dwivedula, Rohit Saxena, Divyanshu Yadalam, Sujay Kim, Daehyeok Akella, Aditya Operating Systems Artificial Intelligence Distributed, Parallel, and Cluster Computing Resource-management tasks in modern operating and distributed systems continue to rely primarily on hand-designed heuristics for tasks such as scheduling, caching, or active queue management. Designing performant heuristics is an expensive, time-consuming process that we are forced to continuously go through due to the constant flux of hardware, workloads and environments. We propose a new alternative: synthesizing instance-optimal heuristics -- specialized for the exact workloads and hardware where they will be deployed -- using code-generating large language models (LLMs). To make this synthesis tractable, Vulcan separates policy and mechanism through LLM-friendly, task-agnostic interfaces. With these interfaces, users specify the inputs and objectives of their desired policy, while Vulcan searches for performant policies via evolutionary search over LLM-generated code. This interface is expressive enough to capture a wide range of system policies, yet sufficiently constrained to allow even small, inexpensive LLMs to generate correct and executable code. We use Vulcan to synthesize performant heuristics for cache eviction and memory tiering, and find that these heuristics outperform all human-designed state-of-the-art algorithms by upto 69% and 7.9% in performance for each of these tasks respectively. |
| title | Vulcan: Instance-Optimal Systems Heuristics Through LLM-Driven Search |
| topic | Operating Systems Artificial Intelligence Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2512.25065 |