Pith. sign in

REVIEW 7 cited by

RAPGen: An Approach for Fixing Code Inefficiencies in Zero-Shot

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2306.17077 v4 pith:SUMW5FNP submitted 2023-06-29 cs.SE cs.AI

classification cs.SEcs.AI
keywords performancepromptrapgenapproachbugsfixingcodegenerate
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Performance bugs are non-functional bugs that can even manifest in well-tested commercial products. Fixing these performance bugs is an important yet challenging problem. In this work, we address this challenge and present a new approach called Retrieval-Augmented Prompt Generation (RAPGen). Given a code snippet with a performance issue, RAPGen first retrieves a prompt instruction from a pre-constructed knowledge-base of previous performance bug fixes and then generates a prompt using the retrieved instruction. It then uses this prompt on a Large Language Model (such as Codex) in zero-shot to generate a fix. We compare our approach with the various prompt variations and state of the art methods in the task of performance bug fixing. Our evaluation shows that RAPGen can generate performance improvement suggestions equivalent or better than a developer in ~60% of the cases, getting ~42% of them verbatim, in an expert-verified dataset of past performance changes made by C# developers.

Discussion (0). Sign in to comment.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Multi-Source and Cross-Scenario Strategy-Guided Code Optimization

    cs.SE 2026-07 conditional novelty 7.0 of 10

    MoST improves LLM-guided code optimization by clustering optimization strategies from heterogeneous knowledge sources and transferring them across programming languages.

  2. Can Coding Agents Implement Missed Compiler Optimizations? Evaluating LLM Agents on LLVM Peephole Optimizations

    cs.SE 2026-07 accept novelty 6.5 of 10

    No evaluated coding agent simultaneously matches human experts on behavioral validity and profitability when implementing real missed InstCombine optimizations from LLVM issues.

  3. Multi-level Code Optimization via Mixture of Prompts

    cs.SE 2026-07 conditional novelty 6.0 of 10

    Multi-level Mixture-of-Prompts optimization with differential profiling yields up to 57.48% opt% and multi-x speedups over prior LLM code optimizers on COFFE and EffiBench.

  4. SemOpt: LLM-Driven Code Optimization via Rule-Based Analysis

    cs.SE 2025-10 conditional novelty 6.0 of 10

    SemOpt generates Semgrep static-analysis rules from LLM-summarized optimization commits and uses them to locate and apply optimization strategies, outperforming retrieval-based baselines on C/C++ code.

  5. Bridging the Gap in Ophthalmic AI: MM-Retinal-Reason Dataset and OphthaReason Model toward Dynamic Multimodal Reasoning

    cs.AI 2025-08 unverdicted novelty 6.0 of 10

    A new retinal-imaging multimodal dataset and an ophthalmology-specific reasoning model claim state-of-the-art gains of 15 to 25 percent over existing medical and general multimodal LLMs.

  6. PSearch: Search-based Patch Generation in the Era of LLM-based Automated Program Repair

    cs.SE 2025-07 conditional novelty 6.0 of 10

    PSearch applies Monte Carlo Tree Search to LLM patch generation with LLM and test-based rewards, fixing 201 Defects4J bugs and resolving 164 SWE-Bench-Lite issues.

  7. GrowthHacker: Automated Off-Policy Evaluation Optimization Using Code-Modifying LLM Agents

    cs.SE 2025-11 conditional novelty 5.0 of 10

    A benchmark and small-scale evaluation suggesting LLM agents can modify off-policy evaluation code and sometimes improve the measured metrics, with the authors' two-agent framework the most reliable of those tested.

Pith tools