Evaluating Agentic Optimization on Large Codebases
This addresses the need for better benchmarks to assess LLM agents in code optimization for developers and researchers, though it is incremental as it builds on existing evaluation methods.
The authors tackled the problem of evaluating LLM coding agents' ability to optimize entire codebases under realistic constraints by introducing FormulaCode, a benchmark with 957 performance bottlenecks from real-world repositories, and found that repository-scale, multi-objective optimization remains a major challenge for frontier agents.
Large language model (LLM) coding agents increasingly operate at the repository level, motivating benchmarks that evaluate their ability to optimize entire codebases under realistic constraints. Existing code benchmarks largely rely on synthetic tasks, binary correctness signals, or single-objective evaluation, limiting their ability to assess holistic optimization behavior. We introduce FormulaCode, a benchmark for evaluating agentic optimization on large, real-world codebases with fine-grained, multi-objective performance metrics. FormulaCode comprises 957 performance bottlenecks mined from scientific Python repositories on GitHub, each paired with expert-authored patches and, on average, 264.6 community-maintained performance workloads per task, enabling the holistic ability of LLM agents to optimize codebases under realistic correctness and performance constraints. Our evaluations reveal that repository-scale, multi-objective optimization remains a major challenge for frontier LLM agents. Project website at: https://formula-code.github.io