Spotlights finds software improvement areas to boost engineering goals
Spotlights: Discovering Improvement Opportunities in Software Repositories
Software Engineering
Summary
Finding ways to make software better can be hard because you first need to know what parts of the code are worth changing. The authors created Spotlights, a system that helps identify sections of code in a software project where improvements could meet a high-level goal like faster speed or better reliability. Spotlights looks at the whole project and some runtime data, then suggests where to focus changes without needing a specific problem reported. Tests show it successfully points out useful code spots, some of which led to faster processing without losing quality.
What this means in practice
- •For software engineering teams: Identify key code areas in large projects to guide performance or reliability improvements aligned with high-level goals.
- •For system reliability engineers: Use in diagnosing which parts of software can be altered to enhance system stability without prior knowledge of defects.
Authors
Udi Barzelay, Ophir Azulai, Idan Friedman, Inbar Shapira, Foad Abo Dahood, Yevgeny Burshtein, Orit Prince, Michael Soloveitchik, Oshri Naparstek, Roi Pony, Tal Drory, Michael Factor
Abstract
Coding agents and evolutionary code-search systems can improve implementations once a target and evaluation criterion have been specified. Applying these methods to an existing software repository raises an earlier question: which implementation choices are worth investigating for a high-level engineering objective? We introduce \emph{optimization-opportunity discovery}, the repository-level task of identifying candidate source regions, explaining how they relate to the objective, and proposing possible changes. The task takes as input a repository, an engineering objective, and optional runtime evidence such as offline telemetry observations or profiles. It does not require the user to specify a defect, bottleneck, or code location. We present \emph{Spotlights}, a system that performs this task through logical repository mapping, successive agent reviews, and optional research linking candidates to relevant techniques. We evaluate Spotlights across model serving, document retrieval, blockchain ordering, and document processing. Across three cases, it recovers seven of nine expert-selected targets. In the reliability study, 70\% of the top ten candidates meet the stated correctness and severity thresholds. Across five repeated retrieval runs, 73.6\% of candidate occurrences have a matching source region in all five runs. Spotlights also rediscovers the target of a withheld retrieval optimization and connects it to a relevant tiling technique. In an implementation study, a discovered change reduces end-to-end page-processing runtime by 10.6\% while preserving measured output quality. These results establish optimization-opportunity discovery as a distinct and empirically evaluable step between a broad engineering objective and subsequent implementation and validation.