From Overload to Insight: Bridging Code Search and Code Review with LLMs
Bibliographic record
Abstract
The software engineering (SE) research community has developed numerous tools to search and extract actionable insights from software artifacts, ranging from static analysis tools to testing frameworks and continuous integration pipelines (hereafter just "search tools"). Despite their potential, many of these search tools remain underutilized during code review, a critical process for ensuring software quality. Key challenges include the overwhelming volume of information generated by automated tools, high false-positive rates, and the need for manual configuration or interpretation, which disrupts the flow of review. In this paper, we propose a vision for an LLM-powered conversational agent designed to assist code reviewers by bridging the gap between human reviewers and search tools. This agent would summarize relevant insights, tailor them to the specific code change under review, and facilitate context-aware interactions. By enhancing the human-in-the-loop nature of code review, such a tool has the potential to amplify reviewer effectiveness, streamline the review process, and ultimately improve software quality.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.093 | 0.320 |
| Meta-epidemiology (narrow) | 0.002 | 0.002 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.011 | 0.004 |
| Science and technology studies | 0.006 | 0.009 |
| Scholarly communication | 0.016 | 0.023 |
| Open science | 0.005 | 0.028 |
| Research integrity | 0.006 | 0.005 |
| Insufficient payload (model declined to judge) | 0.008 | 0.005 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".