Agora: Toward Autonomous Bug Detection in Production-Level Consensus Protocols with LLM Agents
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _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 |