一句话：提出 Rust-SWE-bench 基准与 RustForger 智能体，通过自动测试环境和动态追踪提升 Rust 仓库级问题修复。
Rust 学习曲线陡峭、编码挑战大，自动化问题修复对其推广至关重要。然而，LLM 驱动的代码智能体在 Rust 上的应用受限于缺乏大规模仓库级基准。本文提出 Rust-SWE-bench，包含来自 34 个流行 Rust 仓库的 500 个真实仓库级任务，并用 4 个代表性智能体和 4 个先进 LLM 开展系统研究。研究发现，ReAct 类智能体最多解决 21.2% 的问题，主要受限于仓库级代码结构理解与 Rust 严格的类型和 trait 语义，且问题复现非常关键。受此启发，作者提出 RustForger，结合自动测试环境搭建与 Rust 元编程驱动的动态追踪，支持可靠的问题复现和动态分析。评估表明，RustForger 使用 Claude-Sonnet-3.7 解决 28.6% 的任务，较最强基线提升 34.9%，并额外解决 46 个其他智能体无法解决的任务。
The Rust programming language presents a steep learning curve and significant coding challenges, making the automation of issue resolution essential for its broader adoption. Recently, LLM-powered code agents have shown remarkable success in resolving complex software engineering tasks, yet their application to Rust has been limited by the absence of a large-scale, repository-level benchmark. To bridge this gap, we introduce Rust-SWE-bench, a benchmark comprising 500 real-world, repository-level software engineering tasks from 34 diverse and popular Rust repositories. We then perform a comprehensive study on Rust-SWE-bench with four representative agents and four state-of-the-art LLMs to establish a foundational understanding of their capabilities and limitations in the Rust ecosystem. Our extensive study reveals that while ReAct-style agents are promising, i.e., resolving up to 21.2% of issues, they are limited by two primary challenges: comprehending repository-wide code structure and complying with Rust’s strict type and trait semantics. We also find that issue reproduction is rather critical for task resolution. Inspired by these findings, we propose RustForger, a novel agentic approach that integrates an automated test environment setup with a Rust metaprogramming-driven dynamic tracing strategy to facilitate reliable issue reproduction and dynamic analysis. The evaluation shows that RustForger using Claude-Sonnet-3.7 significantly outperforms all baselines, resolving 28.6% of tasks on Rust-SWE-bench, i.e., a 34.9% improvement over the strongest baseline, and, in aggregate, uniquely solves 46 tasks that no other agent could solve across all adopted advanced LLMs.
@inproceedings{abs-2602-22764,
title = {Evaluating and Improving Automated Repository-Level Rust Issue Resolution with LLM-based Agents},
author = {Jiahong Xiang and Wenxiao He and Xihua Wang and Hongliang Tian and Yuqun Zhang},
booktitle = {ICSE},
year = {2026},
doi = {10.1145/3744916.3773108}
}