# A Simulation Platform for AUV Fault Recovery: Exploring LLM-Based Diagnostic Strategies

arXiv: https://arxiv.org/abs/2609.20620 · HTML: https://mlsanity.com/paper/2609.20620/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 23 references that are in the map.
- First posted on arXiv 17 Sep 2026.

## Builds on (most cited first, 9 of 9)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [PIQA: Reasoning about Physical Commonsense in Natural Language](https://mlsanity.com/paper/1911.11641/) (2019)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [Retrieval Augmentation Reduces Hallucination in Conversation](https://mlsanity.com/paper/2104.07567/) (2021)
- [ChatGPT for Robotics: Design Principles and Model Abilities](https://mlsanity.com/paper/2306.17582/) (2023)
- [DAVE Aquatic Virtual Environment: Toward a General Underwater Robotics Simulator](https://mlsanity.com/paper/2209.02862/) (2022)
- [A Collaborative Reasoning Framework for Anomaly Diagnostics in Underwater Robotics](https://mlsanity.com/paper/2511.03075/) (2025)
- [Affordably Fine-tuned LLMs Provide Better Answers to Course-specific MCQs](https://mlsanity.com/paper/2501.05891/) (2025)

## Abstract (arXiv)

Autonomous underwater vehicles (AUVs) operating beyond reliable communications must recover from failures without human intervention. We investigate an architecture in which conventional deterministic layered control autonomy manages normal operations, while an invokable large language model (LLM) serves as a diagnostic and recovery planner when onboard anomaly detection identifies performance outside expected limits. Because language models are stochastic, rigorous evaluation requires ensemble testing rather than individual demonstrations. We present a closed-loop simulation architecture that couples real-time C vehicle software with a higher-level orchestration layer for physics-based fault injection, structured prompting, language-model interaction, mission file generation, validation, execution, and LLM-judge scoring. The framework, which we call SPAR (Simulation Platform for AUV Recovery), supports evaluation across fault realizations, prompt structures, reasoning models, and mission conditions. We vary these for a mass-shift fault over 480 SPAR trials, evaluating a frontier model and three off-the-shelf locally deployable LLMs. Model choice dominates diagnosis: the frontier model places the CG-shift mechanism in its top three hypotheses in 85-90% of trials, versus 60-78% for the best local model. Reasoning analysis indicates that local-model success is associated with following the complete diagnostic procedure, whereas weaker models often commit prematurely to elevator failure even though the actuator tracks its command. Diagnosis and operational decision performance do not appear to be coupled in this dataset. The contributions are an architecture extending unanticipated-fault recovery from detection to mitigation and an ensemble methodology for evaluating LLM-assisted mission management on low-power AUVs.