Saved in:
Bibliographic Details
Main Authors: Liu, Xiang, Song, Sa, Zhang, Zhaowei, Lan, Huiying, Zeng, Jason, Wu, Ming, Heinrich, Michael, Sun, Yong, Zhang, Ceyao
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.29910
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910270171906048
author Liu, Xiang
Song, Sa
Zhang, Zhaowei
Lan, Huiying
Zeng, Jason
Wu, Ming
Heinrich, Michael
Sun, Yong
Zhang, Ceyao
author_facet Liu, Xiang
Song, Sa
Zhang, Zhaowei
Lan, Huiying
Zeng, Jason
Wu, Ming
Heinrich, Michael
Sun, Yong
Zhang, Ceyao
contents Consensus protocols form the backbone of distributed systems and blockchains, where implementation bugs can cause data corruption and financial losses. While LLM-based approaches show promise in code analysis, they struggle with deep protocol-level logic bugs involving complex state-dependent behaviors across multiple execution stages. We present Agora, a domain-aware multi-agent framework that integrates hypothesis-driven testing with LLM capabilities for systematic protocol verification. Agora employs specialized agents that collaboratively explore protocol state spaces, synthesize attack scenarios using domain-specific constraints, and validate findings through iterative refinement. This explicit role separation enables reasoning about global protocol invariants beyond single-function code analysis. We evaluate Agora on four consensus implementations (Raft, EPaxos, HotStuff, BullShark) using four state-of-the-art LLMs. Agora discovers 15 previously unknown protocol-level logic bugs that violate safety properties, while existing LLM-based agents fail to detect any such protocol-level logic bugs. Our results demonstrate that domain-aware multi-agent collaboration is essential for detecting deep logic bugs in complex protocols.
format Preprint
id arxiv_https___arxiv_org_abs_2605_29910
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Agora: Toward Autonomous Bug Detection in Production-Level Consensus Protocols with LLM Agents
Liu, Xiang
Song, Sa
Zhang, Zhaowei
Lan, Huiying
Zeng, Jason
Wu, Ming
Heinrich, Michael
Sun, Yong
Zhang, Ceyao
Software Engineering
Artificial Intelligence
Consensus protocols form the backbone of distributed systems and blockchains, where implementation bugs can cause data corruption and financial losses. While LLM-based approaches show promise in code analysis, they struggle with deep protocol-level logic bugs involving complex state-dependent behaviors across multiple execution stages. We present Agora, a domain-aware multi-agent framework that integrates hypothesis-driven testing with LLM capabilities for systematic protocol verification. Agora employs specialized agents that collaboratively explore protocol state spaces, synthesize attack scenarios using domain-specific constraints, and validate findings through iterative refinement. This explicit role separation enables reasoning about global protocol invariants beyond single-function code analysis. We evaluate Agora on four consensus implementations (Raft, EPaxos, HotStuff, BullShark) using four state-of-the-art LLMs. Agora discovers 15 previously unknown protocol-level logic bugs that violate safety properties, while existing LLM-based agents fail to detect any such protocol-level logic bugs. Our results demonstrate that domain-aware multi-agent collaboration is essential for detecting deep logic bugs in complex protocols.
title Agora: Toward Autonomous Bug Detection in Production-Level Consensus Protocols with LLM Agents
topic Software Engineering
Artificial Intelligence
url https://arxiv.org/abs/2605.29910