# A Collaborative Reasoning Framework for Anomaly Diagnostics in Underwater Robotics

arXiv: https://arxiv.org/abs/2511.03075 · HTML: https://mlsanity.com/paper/2511.03075/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 4 of its 21 references that are in the map.
- First posted on arXiv 4 Nov 2025.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)

## Builds on (most cited first, 4 of 4)

- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [Distributed AI Agents for Cognitive Underwater Robot Autonomy](https://mlsanity.com/paper/2507.23735/) (2025)
- [Digital Twin-based Out-of-Distribution Detection in Autonomous Vessels](https://mlsanity.com/paper/2504.19816/) (2025)
- [Tethered Multi-Robot Systems in Marine Environments](https://mlsanity.com/paper/2508.02264/) (2025)

## Built on by (most cited first, 2 of 2)

- [World-Model-Grounded LLM Planning for AUV and ASV Navigation Near Offshore Wind Farms](https://mlsanity.com/paper/2608.19661/) (2026)
- [A Simulation Platform for AUV Fault Recovery: Exploring LLM-Based Diagnostic Strategies](https://mlsanity.com/paper/2609.20620/) (2026)

## Abstract (arXiv)

The safe deployment of autonomous systems in safety-critical settings requires a paradigm that combines human expertise with AI-driven analysis, especially when anomalies are unforeseen. We introduce AURA (Autonomous Resilience Agent), a collaborative framework for anomaly and fault diagnostics in robotics. AURA integrates large language models (LLMs), a high-fidelity digital twin (DT), and human-in-the-loop interaction to detect and respond to anomalous behavior in real time. The architecture uses two agents with clear roles: (i) a low-level State Anomaly Characterization Agent that monitors telemetry and converts signals into a structured natural-language problem description, and (ii) a high-level Diagnostic Reasoning Agent that conducts a knowledge-grounded dialogue with an operator to identify root causes, drawing on external sources. Human-validated diagnoses are then converted into new training examples that refine the low-level perceptual model. This feedback loop progressively distills expert knowledge into the AI, transforming it from a static tool into an adaptive partner. We describe the framework's operating principles and provide a concrete implementation, establishing a pattern for trustworthy, continually improving human-robot teams.