CORTEXA
← Browse
arxivcs.SEcs.AI2026-07-02

Understanding Agent-Based Patching of Compiler Missed Optimizations

Batu Guan, Zirui Wang, Shaohua Li

Compiler missed optimizations refer to cases in which compilers failed to optimize certain code. It takes many compiler developers' efforts to implement or patch such missed optimizations. In this paper, we present a systematic study of how well agents patch compiler missed optimizations. We identify a significant challenge that patching a missed optimization requires more than just fixing the reported case, and instead requires generalizing to similar cases. We construct a benchmark of real-world LLVM missed optimization issues and compare agent-generated patches with patches from developers in terms of optimization scope. Our results show that coding agents often optimize the given examples, but many generated patches either cover only part of the developer-intended scope or partially overlap with it; in some cases, they further generalize beyond the reference patch. We further introduce historical-knowledge augmentation techniques that leverage prior LLVM optimization pull requests through retrieval and distillation, showing that they improve developer-aligned generalization and yield practical benefits when applied to real-world IR.

View free PDFSource page

Related papers

arxivcs.AIcs.SE2026-07-21

Graph-Based Agentic AI with LangGraph: Workflow Pathways for Long-Running Stateful Business Processes

Daniel Pearson, Sidney Shapiro, Emiliano Sebastian Gonzalez Venegas, Sanad Al-Khatib, Aurora Pinzón Arzola

This paper is a practitioner guide to graph-based workflow pathways for long-running, stateful, multi-step generative AI systems in business processes. Rather than treating LangGraph, a low-level orchestration framework for stateful agents, as a model-quality benchmark target, we…

View free PDFSource page
arxivcs.SEcs.AI2026-07-01

Are Performance-Optimization Benchmarks Reliably Measuring Coding Agents?

Zhi Chen, Zhensu Sun, Yuling Shi, David Lo, Lingxiao Jiang

Repository-level performance-optimization benchmarks such as GSO, SWE-Perf and SWE-fficiency evaluate coding agents by applying patches to real repositories and comparing runtime against unoptimized baselines and official reference patches. Their leaderboard scores are increasing…

View free PDFSource page
arxivcs.SEcs.AIcs.CR2026-07-13

AutoTrace: From Patches to Triggers via Agentic Interprocedural Exploration

Arastoo Zibaeirad, Marco Vieira, Thomas Zimmermann

Given a vulnerability-fixing commit, trigger localization asks which specific statement turns the vulnerable program state into a concrete unsafe operation. This question is harder than binary vulnerability detection because the answer demands interprocedural, causal reasoning: i…

View free PDFSource page
arxivcs.SEcs.AI2026-07-22

PerfAgent: Profiler-Guided Iterative Refinement for Repository-Level Code Optimization

Ryan Deng, Yuanzhe Liu, Bastian Lipka, Yao Ma, Xuhao Chen, Tim Kaler, et al.

Large language model (LLM) agents now perform well on correctness-oriented repository-level tasks, including SWE-Bench issue resolution and feature implementation in real codebases. However, they still struggle with repository-level code optimization, which requires preserving be…

View free PDFSource page
arxivcs.SEcs.AI2026-07-18

Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits

Haifeng Li, Mo Hai

Large language models now translate natural-language descriptions of decision problems into solver-ready optimization models, but they fail silently. A generated model often runs and still formulates the wrong problem. This paper develops a theory of falsification-based verificat…

View free PDFSource page
arxivcs.SEcs.AI2026-07-01

SWE-Doctor: Guiding Software Engineering Agents with Runtime Diagnosis from Multi-Faceted Bug Reproduction Tests

Yaoqi Guo, Yang Liu, Jie M. Zhang, Yun Ma, Yiling Lou, Zhenpeng Chen

Large language model (LLM)-based software engineering agents are increasingly developed to resolve software issues by generating patches from issue reports and code repositories. Bug reproduction tests (BRTs) are an important building block for such agents and have been shown use…

View free PDFSource page