arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.21681cs.SE
收藏

AkiraRust:重新思考利用反馈引导的思考开关的LLM辅助Rust修复

AkiraRust: Re-thinking LLM-aided Rust Repair Using a Feedback-guided Thinking Switch

National University of Defense Technology(国防科技大学);Southeast University(东南大学)

Renshuang Jiang, Yichong Wang, Pan Dong, Xiaoxiang Fang, Zhenling Duan, Tinglue Wang, Yuchen Hu, Jie Yu, Zhe Jiang

AI总结:

AkiraRust通过反馈引导的思考开关机制,实现Rust修复的语义正确性和效率提升。

摘要:

消除Rust程序中的未定义行为需要深入的语义理解以实现准确可靠的修复。尽管现有研究已展示了LLM在支持Rust代码分析和修复方面的潜力,但大多数框架仍受制于僵化的模板或缺乏可执行语义的基础,导致上下文意识有限和语义错误。本文提出了AkiraRust,一个基于LLM的修复和验证框架,其结合了有限状态机以动态适应运行时语义条件下的检测和修复流程。AkiraRust引入了一种双模式推理策略,协调多个代理之间的快速和慢速思考。每个代理映射到一个FSM状态,波形驱动的转换控制器管理状态切换、回滚决策和语义检查点,实现上下文感知和运行时自适应的修复。实验结果表明,AkiraRust实现了约92%的语义正确性,并相比SOTA平均提速2.2倍。

英文摘要:

Eliminating undefined behaviors (UBs) in Rust programs requires a deep semantic understanding to enable accurate and reliable repair. While existing studies have demonstrated the potential of LLMs to support Rust code analysis and repair, most frameworks remain constrained by inflexible templates or lack grounding in executable semantics, resulting in limited contextual awareness and semantic incorrectness. Here, we present AkiraRust, an LLM-driven repair and verification framework that incorporates a finite-state machine to dynamically adapt its detection and repair flow to runtime semantic conditions. AkiraRust introduces a dual-mode reasoning strategy that coordinates fast and slow thinking across multiple agents. Each agent is mapped to an FSM state, and a waveform-driven transition controller manages state switching, rollback decisions, and semantic check pointing, enabling context-aware and runtime-adaptive repair. Experimental results show that AkiraRust achieves about 92% semantic correctness and delivers a 2.2x average speedup compared to SOTA.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑