FormulaCode is a new benchmark for repository-level LLM agent optimization using 957 mined bottlenecks, expert patches, and multi-objective metrics from real scientific Python repositories.
We also showcase the number of tasks, the date of creation of the latest task, and additional information about the functionality and popularity of the repository
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.SE 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
FormulaCode: Evaluating Agentic Optimization on Large Codebases
FormulaCode is a new benchmark for repository-level LLM agent optimization using 957 mined bottlenecks, expert patches, and multi-objective metrics from real scientific Python repositories.