LLMs as Firmware Experts: A Runtime-Grown Tree-of-Agents Framework

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Xiangrui, Chen, Zeyu, Wang, Haining, Li, Qiang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908670891130880
author Zhang, Xiangrui
Chen, Zeyu
Wang, Haining
Li, Qiang
author_facet Zhang, Xiangrui
Chen, Zeyu
Wang, Haining
Li, Qiang
contents Large Language Models (LLMs) and their agent systems have recently demonstrated strong potential in automating code reasoning and vulnerability detection. However, when applied to large-scale firmware, their performance degrades due to the binary nature of firmware, complex dependency structures, and heterogeneous components. To address this challenge, this paper presents FIRMHIVE, a recursive agent hive that enables LLMs to act as autonomous firmware security analysts. FIRMHIVE introduces two key mechanisms: (1) transforming delegation into a per-agent, executable primitive and (2) constructing a runtime Tree of Agents (ToA) for decentralized coordination. We evaluate FIRMHIVE using real-world firmware images obtained from publicly available datasets, covering five representative security analysis tasks. Compared with existing LLM-agent baselines, FIRMHIVE performs deeper (about 16x more reasoning steps) and broader (about 2.3x more files inspected) cross-file exploration, resulting in about 5.6x more alerts per firmware. Compared to state-of-the-art (SOTA) security tools, FIRMHIVE identifies about 1.5x more vulnerabilities (1,802 total) and achieves 71% precision, representing significant improvements in both yield and fidelity.
format Preprint
id arxiv_https___arxiv_org_abs_2511_18438
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LLMs as Firmware Experts: A Runtime-Grown Tree-of-Agents Framework
Zhang, Xiangrui
Chen, Zeyu
Wang, Haining
Li, Qiang
Cryptography and Security
Software Engineering
Large Language Models (LLMs) and their agent systems have recently demonstrated strong potential in automating code reasoning and vulnerability detection. However, when applied to large-scale firmware, their performance degrades due to the binary nature of firmware, complex dependency structures, and heterogeneous components. To address this challenge, this paper presents FIRMHIVE, a recursive agent hive that enables LLMs to act as autonomous firmware security analysts. FIRMHIVE introduces two key mechanisms: (1) transforming delegation into a per-agent, executable primitive and (2) constructing a runtime Tree of Agents (ToA) for decentralized coordination. We evaluate FIRMHIVE using real-world firmware images obtained from publicly available datasets, covering five representative security analysis tasks. Compared with existing LLM-agent baselines, FIRMHIVE performs deeper (about 16x more reasoning steps) and broader (about 2.3x more files inspected) cross-file exploration, resulting in about 5.6x more alerts per firmware. Compared to state-of-the-art (SOTA) security tools, FIRMHIVE identifies about 1.5x more vulnerabilities (1,802 total) and achieves 71% precision, representing significant improvements in both yield and fidelity.
title LLMs as Firmware Experts: A Runtime-Grown Tree-of-Agents Framework
topic Cryptography and Security
Software Engineering
url https://arxiv.org/abs/2511.18438