Skip to content
Book Open access

StarVerus: LLM-Powered Multi-Agent Collaboration for Industrial Rust Code Verification Automation

Aug 2026 · Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2 · pp. 7444-7455 · 0 citations · 37 references

TL;DR

A multi-agent collaborative framework, StarVerus, to automate the verification of industrial Rust code and introduces a planner-repairer-actor-rewriter multi-agent paradigm to further enhance the proof repair capabilities.

Abstract

Creating code specifications is a crucial measure to improve the trustworthiness of many industrial systems implemented in Rust with high security requirements. Because writing specifications requires highly specialized professionals and is time-consuming, the automatic generation of specifications, enabled by large language models (LLMs), has received increasing attention and shown promising results. However, these methods typically focus on partial specification generation (generating proofs after the contract is known) and on extracting dependencies between code modules using predefined relations. This is not suitable for real-world industrial systems where the goal is to generate complete specifications from scratch and where the complex dependencies between code modules are variable. To address this, we propose a multi-agent collaborative framework, StarVerus, to automate the verification of industrial Rust code. Specifically, StarVerus addresses the aforementioned limitations in two ways: 1) In the generation phase, it instructs the LLM to generate all specifications for a given code, and in the repair phase, it uses a cascaded two-stage process of contract alignment and proof repair to correct them; 2) In both the generation and repair phases, it utilizes a function call graph to adaptively obtain bidirectional contextual information (i.e., what it calls and what calls it) for each code module as an additional information source for the LLM. Furthermore, StarVerus introduces a planner-repairer-actor-rewriter multi-agent paradigm to further enhance the proof repair capabilities. Finally, the effectiveness of StarVerus is validated through experiments on benchmark datasets and deployment in a real operating system.

Read PDF

Similar papers

#artificial intelligence Conference Open access Sep 2026

LLM-Driven Multi-Agent Control for Skill-Based Smart Manufacturing

Factories are shifting toward smaller lot sizes with high product customization, requiring frequent re-programming of flexible and reconfigurable automation systems. LLM-based agents can be deployed in two complementary roles: offline, they generate deterministic production sequences, reducing programming effort; onlin...

Kay Köhle, Darko Anicic, T. Runkler et al. · 0 citations
Preprint Aug 2026

SemaPLC: A Project-Grounded, Verification-Gated Agent Harness for PLC Code Generation

This work presents \textsc{SemaPLC}, a project-grounded and verification-gated agent harness assembled from conventional tools but governed by a strict completion rule, which raises the mean at every layer and most sharply at runtime.

Yan-Lun Tu, Hua-Can Wang, Zi-Yue Zhou et al. · 1 citation · ⚡1
#artificial intelligence Review Sep 2026

MAGS: Multi-agent Auto-formalization Guarantees Safety for Agentic Outputs

This work introduces a unified multi-agent framework, MAGS, that generates executable programs with formal safety guarantees, using Dafny as a verification-aware intermediate representation where safety properties can be mechanically checked.

Albert Wu, N. Roberts, Tzu-Heng Huang et al. · 0 citations

MTAC-IFBench: Benchmarking Instruction-Following in Multi-Turn Agentic Coding

Recently, the rapid development of large language models (LLMs) has reshaped software engineering by enabling autonomous code agents that plan, execute, and utilize external tools iteratively to tackle complex tasks. Beyond achieving functional correctness, these agents must faithfully follow process instructions and c...

Bo-Si Wen, Cun-Xiang Wang, Jia-Yi Gui et al. · 1 citation
Book Open access Oct 2026

Smart Contract Synthesis via Multi-modal Specifications

This paper proposes SmartSpec, a synthesizer that generates smart-contract implementations from functional and safety specifications and validates them with integrated verification, and employs maximally permissive synthesis, ensuring contracts preserve all safety requirements while remaining as permissive as possible.

Tang-Lin Chen, Hao-Xian Chen, Hui-Lin Xiang et al. · 0 citations
Book Open access Oct 2026

Extender: A Multi-agent System for Code Extensibility Review

Software systems must evolve as requirements and environments change, which makes extensibility a central quality goal. The SOLID principles, five object-oriented design principles, are widely endorsed in software engineering practice to evaluate software quality. However, automatically detecting violations of SOLID pr...

Jia-He Chen, Jia-Cheng Shen · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.