This work investigates whether LLM-based agents can autonomously achieve substantial performance improvements in scientific software, including mature implementations that have already been extensively optimized by human developers.
Abstract
Scientific software is increasingly required to process larger datasets while maintaining acceptable execution times. Software optimization traditionally requires substantial expertise in programming, algorithms, and numerical methods. Recent advances in large language models (LLMs) offer the possibility of automating much of this process. We investigate whether LLM-based agents can autonomously achieve substantial performance improvements in scientific software, including mature implementations that have already been extensively optimized by human developers. We tasked an LLM-based agent with optimizing software for three computational problems: t-SNE, single-sample gene set enrichment analysis (ssGSEA), and graphlet counting. Humans defined the scope, correctness criteria, and a verification mechanism, after which the agent worked autonomously, in some cases for several hours. Code maintainers reviewed each resulting implementation and verified its correctness. The optimized implementations were faster in all tested configurations, by up to two orders of magnitude over the fastest existing tools. The improvements included low-level code optimizations, mathematical reformulations, and an entirely new algorithm for graphlet counting. Software optimization can increasingly be delegated to autonomous agents, with the human role shifting from implementing optimizations to deciding which software to optimize, defining objectives, providing verification mechanisms, and ensuring the correctness of the final software. For well-scoped, verifiable problems, we argue that manual software optimization may be a thing of the past.
This study empirically evaluates whether cost-efficient Large Language Models (LLMs) can be trusted to generate enterprise code to a written specification. Three models (Gemini Flash 3, GPT-5.4 mini and Claude Haiku 4.5) were asked to solve 992 algorithmic problems as Java Spring Boot service methods conforming to a ma...
Chandimal Adikari, N. Herath· International Conference on...· 0 citations
This paper presents a systematic refactoring approach using Claude agentic AI on real-world project-scheduling workloads in a high-performance computing (HPC) environment, where the agent identifies bottlenecks, implements targeted optimizations, and evaluates their effects, while the researcher retains final control.
ASAD is introduced, an adaptive agentic system for debugging that configures its team according to the nature and complexity of each bug, and dynamically adjusts the number and roles of agents.
Yacine Majdoub, Eya Ben Charrada, Haifa Touati· IEEE Transactions on Softwar...· 0 citations
The proposed hybrid approach demonstrates practical potential, but its implementation in real-world development will require improving the semantics of automatically generated contracts, expanding training sets, and creating automated error correction procedures integrated into the generation cycle.
P. Mel'nikov, Andrey Tyugashev, V. N. Novikova· Reliability and Quality of C...· 0 citations
Can coding agents restore software that no longer runs while preserving its underlying methods, and reconstruct industrial software engines from open specifications? Here we introduce ReviveBench, a benchmark with two task families evaluated by hidden verifiers calibrated against native execution environments, establis...
Tian-Yu Liu, Ding-Yuan Dai, Yu-Fan Du et al.· arXiv.org· 0 citations
This work introduces online LLM-based AAD, a novel optimization paradigm that treats the algorithm itself as a state-dependent decision variable and proposes OnDesign, a multi-agent framework that reconciles competing design perspectives to synthesize executable algorithms and uses execution feedback to refine how runt...
Zhi-Yao Zhang, Yi-Chen Li, Xing-Yu Wu et al.· 0 citations