FirmPilot: Evidence-Guided Multi-Agent Environment Recovery for IoT Firmware Rehosting
On the map: LLM agents and tool use → Software engineering coding agents
Abstract (arXiv)
Firmware rehosting executes firmware images in emulated environments such as QEMU to enable scalable dynamic analysis of Internet of Things (IoT) devices. In practice, rehosting pipelines remain fragile across diverse real-world firmware images, as reaching an externally observable execution state depends on tightly coupled artifacts spanning boot scripts, persistent configuration (e.g., NVRAM-like key-value state), and network setup. Template-driven frameworks often fail to accommodate long-tail vendor conventions, while unconstrained use of large language models (LLMs) risks unsupported modifications and irreproducible executions. We introduce FirmPilot, an evidence-guided multi-agent framework for environment recovery in firmware rehosting. FirmPilot reformulates rehosting as iterative environment reconstruction in which a search agent grounds decisions through similarity-based retrieval, a planner coordinates execution-accepted transitions, and specialized agents recover filesystem/init artifacts, persistent state, and network exposure. Through repeated execution and evidence-grounded artifact deltas, the system resolves cross-layer dependencies across boot, state, and networking that otherwise prevent firmware executions from reaching a stable, externally reachable state in emulation. Evaluated on the large-scale, real-world LFwC firmware corpus, FirmPilot improves web-service reachability over FirmAE from 25.49% to 52.39% and network reachability from 39.30% to 71.93%. The resulting rehosts raise the average number of detected services per firmware from 0.86 to 1.62 and support downstream analysis workflows, including RouterSploit interaction and protocol-aware fuzzing over recovered service surfaces. The evaluation shows that evidence- and feedback-grounded agent coordination improves rehosting success, service recovery, and downstream utility in automated firmware rehosting.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. Builds on 10 of its 40 references that are in the map. First posted on arXiv 16 Jul 2026.
Builds on
10 of 40 references.
Closest ancestors · 1
Same direction, newest first
- 2025PatchPilot: A Cost-Efficient Software Engineering Agent with Early Attempts on Formal Verification4 Feb
Other references · 9
- 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
- 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
- 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,348
- 2023The Hitchhiker's Guide to Program Analysis: A Journey with Large Language Modelscited by 18
- 2019P2IM: Scalable and Hardware-independent Firmware Testing via Automatic Peripheral Interface Modeling (extended version)cited by 5
- 2025AutoPatch: Multi-Agent Framework for Patching Real-World CVE Vulnerabilitiescited by 4
- 2021Automatic Firmware Emulation through Invalidity-guided Knowledge Inference (Extended Version)cited by 2
- 2024Mens Sana In Corpore Sano: Sound Firmware Corpora for Vulnerability Researchcited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025LLMs as Firmware Experts: A Runtime-Grown Tree-of-Agents Framework
- 2026Octopus Protocol: One-Shot Hardware Discovery and Control for AI Agents via Infrastructure-as-Prompts
- 2026Crab: A Semantics-Aware Checkpoint/Restore Runtime for Agent Sandboxes
- 2026Towards LLM-Assisted Architecture Recovery for Real-World ROS~2 Systems: An Agent-Based Multi-Level Approach to Hierarchical Structural Architecture Reconstruction
- 2026Rethinking MCP Security: A Large-Scale Study of Runtime MCP Servers and Security Scanner Reliability
- 2026When Tools Fail: Benchmarking Dynamic Replanning and Anomaly Recovery in LLM Agents
- 2026AegisFlow: A Multi-Agent Agentic AI Framework for Autonomous Remediation and Self-Healing in Fragile Data Ecosystems
- 2026OrchestraBench: Evaluating Multi-Agent Orchestration Failure Modes, Recovery, and Decomposition Quality