Paper
AkiraRust: Re-thinking LLM-aided Rust Repair Using a Feedback-guided Thinking Switch
Authors
Renshuang Jiang, Yichong Wang, Pan Dong, Xiaoxiang Fang, Zhenling Duan, Tinglue Wang, Yuchen Hu, Jie Yu, Zhe Jiang
Abstract
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.
Metadata
Related papers
Vibe Coding XR: Accelerating AI + XR Prototyping with XR Blocks and Gemini
Ruofei Du, Benjamin Hersh, David Li, Nels Numan, Xun Qian, Yanhe Chen, Zhongy... • 2026-03-25
Comparing Developer and LLM Biases in Code Evaluation
Aditya Mittal, Ryan Shar, Zichu Wu, Shyam Agarwal, Tongshuang Wu, Chris Donah... • 2026-03-25
The Stochastic Gap: A Markovian Framework for Pre-Deployment Reliability and Oversight-Cost Auditing in Agentic Artificial Intelligence
Biplab Pal, Santanu Bhattacharya • 2026-03-25
Retrieval Improvements Do Not Guarantee Better Answers: A Study of RAG for AI Policy QA
Saahil Mathur, Ryan David Rittner, Vedant Ajit Thakur, Daniel Stuart Schiff, ... • 2026-03-25
MARCH: Multi-Agent Reinforced Self-Check for LLM Hallucination
Zhuo Li, Yupeng Zhang, Pengyu Cheng, Jiajun Song, Mengyu Zhou, Hao Li, Shujie... • 2026-03-25
Raw Data (Debug)
{
"raw_xml": "<entry>\n <id>http://arxiv.org/abs/2602.21681v1</id>\n <title>AkiraRust: Re-thinking LLM-aided Rust Repair Using a Feedback-guided Thinking Switch</title>\n <updated>2026-02-25T08:34:27Z</updated>\n <link href='https://arxiv.org/abs/2602.21681v1' rel='alternate' type='text/html'/>\n <link href='https://arxiv.org/pdf/2602.21681v1' rel='related' title='pdf' type='application/pdf'/>\n <summary>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.</summary>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.SE'/>\n <published>2026-02-25T08:34:27Z</published>\n <arxiv:comment>7 pages, 11 figures, accepted to DAC</arxiv:comment>\n <arxiv:primary_category term='cs.SE'/>\n <author>\n <name>Renshuang Jiang</name>\n </author>\n <author>\n <name>Yichong Wang</name>\n </author>\n <author>\n <name>Pan Dong</name>\n </author>\n <author>\n <name>Xiaoxiang Fang</name>\n </author>\n <author>\n <name>Zhenling Duan</name>\n </author>\n <author>\n <name>Tinglue Wang</name>\n </author>\n <author>\n <name>Yuchen Hu</name>\n </author>\n <author>\n <name>Jie Yu</name>\n </author>\n <author>\n <name>Zhe Jiang</name>\n </author>\n </entry>"
}