mlsanityData to 7 Oct 2026

Real-Time Anomaly Detection and Reactive Planning with Large Language Models

arXiv 2407.08735 ↗First posted 11 Jul 2024cs.RO cs.AI cs.SYcited by 67

Not on the map. Why?

Abstract (arXiv)

Foundation models, e.g., large language models (LLMs), trained on internet-scale data possess zero-shot generalization capabilities that make them a promising technology towards detecting and mitigating out-of-distribution failure modes of robotic systems. Fully realizing this promise, however, poses two challenges: (i) mitigating the considerable computational expense of these models such that they may be applied online, and (ii) incorporating their judgement regarding potential anomalies into a safe control framework. In this work, we present a two-stage reasoning framework: First is a fast binary anomaly classifier that analyzes observations in an LLM embedding space, which may then trigger a slower fallback selection stage that utilizes the reasoning capabilities of generative LLMs. These stages correspond to branch points in a model predictive control strategy that maintains the joint feasibility of continuing along various fallback plans to account for the slow reasoner's latency as soon as an anomaly is detected, thus ensuring safety. We show that our fast anomaly classifier outperforms autoregressive reasoning with state-of-the-art GPT models, even when instantiated with relatively small language models. This enables our runtime monitor to improve the trustworthiness of dynamic robotic systems, such as quadrotors or autonomous vehicles, under resource and time constraints. Videos illustrating our approach in both simulation and real-world experiments are available on this project page: https://sites.google.com/view/aesop-llm.

Key facts. Cited by 67 papers in the map (data through 7 Oct 2026). Builds on 54 of its 60 references that are in the map. First posted on arXiv 11 Jul 2024.

Builds on

54 of 60 references.

References · 54

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2023GPT-4 Technical Reportcited by 18,132
  5. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  6. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  7. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  8. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  9. 2020End-to-End Object Detection with Transformerscited by 7,384
  10. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  11. 2023Mistral 7Bcited by 3,065
  12. 2017CARLA: An Open Urban Driving Simulatorcited by 2,431
38 more
  1. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
  2. 2020Shortcut Learning in Deep Neural Networkscited by 1,928
  3. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,548
  4. 2019Do ImageNet Classifiers Generalize to ImageNet?cited by 1,507
  5. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  6. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,371
  7. 2022SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Modelscited by 1,338
  8. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  9. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,274
  10. 2022Code as Policies: Language Model Programs for Embodied Controlcited by 1,172
  11. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,079
  12. 2022Inner Monologue: Embodied Reasoning through Planning with Language Modelscited by 1,057
  13. 2020MPNet: Masked and Permuted Pre-training for Language Understandingcited by 973
  14. 2021Robust fine-tuning of zero-shot modelscited by 785
  15. 2021A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantificationcited by 777
  16. 2023A Simple and Effective Pruning Approach for Large Language Modelscited by 776
  17. 2023VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Modelscited by 733
  18. 2022Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distributioncited by 722
  19. 2023Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizescited by 710
  20. 2022LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Actioncited by 435
  21. 2020A Unifying Review of Deep and Shallow Anomaly Detectioncited by 423
  22. 2023Language to Rewards for Robotic Skill Synthesiscited by 307
  23. 2022Simple Open-Vocabulary Object Detection with Vision Transformerscited by 303
  24. 2023Improving Text Embeddings with Large Language Modelscited by 295
  25. 2021Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalizationcited by 248
  26. 2023Text2Motion: From Natural Language Instructions to Feasible Planscited by 223
  27. 2023Scaling Robot Learning with Semantically Imagined Experiencecited by 175
  28. 2023Language-Driven Representation Learning for Roboticscited by 163
  29. 2017OSQP: An Operator Splitting Solver for Quadratic Programscited by 156
  30. 2021A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challengescited by 154
  31. 2020Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts?cited by 139
  32. 2023Task-Specific Skill Localization in Fine-tuned Language Modelscited by 104
  33. 2024AutoRT: Embodied Foundation Models for Large Scale Orchestration of Robotic Agentscited by 83
  34. 2022Robotic Skill Acquisition via Instruction Augmentation with Vision-Language Modelscited by 58
  35. 2023Semantic Anomaly Detection with Large Language Modelscited by 53
  36. 2021Sample-Efficient Safety Assurances using Conformal Predictioncited by 41
  37. 2022A System-Level View on Out-of-Distribution Data in Roboticscited by 33
  38. 2021Sketching Curvature for Efficient Out-of-Distribution Detection for Deep Neural Networkscited by 32

50 most cited of 54 All 54 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 14; 2025: 33; 2026: 20.

67 papers.

Sort:

By area:

  1. 2025SAFE: Multitask Failure Detection for Vision-Language-Action Modelscited by 74
  2. 2024Unpacking Failure Modes of Generative Policies: Runtime Monitoring of Consistency and Progresscited by 63
  3. 2025RoboMonkey: Scaling Test-Time Sampling and Verification for Vision-Language-Action Modelscited by 56
  4. 2025From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignmentcited by 51
  5. 2025Can We Detect Failures Without Failure Data? Uncertainty-Aware Runtime Failure Detection for Imitation Learning Policiescited by 49
  6. 2026A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agentscited by 47
  7. 2024Robot Utility Models: General Policies for Zero-Shot Deployment in New Environmentscited by 43
  8. 2025RoboFAC: A Comprehensive Framework for Robotic Failure Analysis and Correctioncited by 37
  9. 2025Failure Prediction at Runtime for Generative Robot Policiescited by 36
  10. 2025Adversarial Attacks on Robotic Vision Language Action Modelscited by 31
  11. 2025Safety Guardrails for LLM-Enabled Robotscited by 30
  12. 2025Uncertainty-aware Latent Safety Filters for Avoiding Out-of-Distribution Failurescited by 30
38 more
  1. 2025Generating Robot Constitutions & Benchmarks for Semantic Safetycited by 28
  2. 2024AD-LLM: Benchmarking Large Language Models for Anomaly Detectioncited by 25
  3. 2024Large Language Models for Anomaly and Out-of-Distribution Detection: A Surveycited by 24
  4. 2024Out-of-Distribution Detection: A Task-Oriented Survey of Recent Advancescited by 24
  5. 2025CUPID: Curating Data your Robot Loves with Influence Functionscited by 21
  6. 2024SPINE: Online Semantic Planning for Missions with Incomplete Natural Language Specifications in Unstructured Environmentscited by 16
  7. 2025Chameleon: Fast-slow Neuro-symbolic Lane Topology Extractioncited by 16
  8. 2024doScenes: An Autonomous Driving Dataset with Natural Language Instruction for Human Interaction and Vision-Language Navigationcited by 14
  9. 2025UncAD: Towards Safe End-to-end Autonomous Driving via Online Map Uncertaintycited by 14
  10. 2026CycleVLA: Proactive Self-Correcting Vision-Language-Action Models via Subtask Backtracking and Minimum Bayes Risk Decodingcited by 13
  11. 2025Air-Ground Collaboration for Language-Specified Missions in Unknown Environmentscited by 11
  12. 2024Generating Out-Of-Distribution Scenarios Using Language Modelscited by 10
  13. 2024SafeDrive: Knowledge- and Data-Driven Risk-Sensitive Decision-Making for Autonomous Vehicles with Large Language Modelscited by 10
  14. 2025Real-Time Out-of-Distribution Failure Prevention via Multi-Modal Reasoningcited by 10
  15. 2025Distilling On-device Language Models for Robot Planning with Minimal Human Interventioncited by 10
  16. 2025Next-Generation LLM for UAV: From Natural Language to Autonomous Flightcited by 10
  17. 2026Hide-and-Seek in Trajectories: Discovering Failure Signals for VLA Runtime Monitoringcited by 6
  18. 2024RAD: A Dataset and Benchmark for Real-Life Anomaly Detection with Robotic Observationscited by 5
  19. 2025LLMAP: LLM-Assisted Multi-Objective Route Planning with User Preferencescited by 5
  20. 2024SayComply: Grounding Field Robotic Tasks in Operational Compliance through Retrieval-Based Language Modelscited by 3
  21. 2025Foundation Models for Anomaly Detection: Vision and Challengescited by 3
  22. 2025Compositional Coordination for Multi-Robot Teams with Large Language Modelscited by 3
  23. 2025Designing Latent Safety Filters using Pre-Trained Vision Modelscited by 3
  24. 2025EmboMatrix: A Scalable Training-Ground for Embodied Decision-Makingcited by 3
  25. 2026Decoding Task Progress from VLA Representationscited by 3
  26. 2024GRAM: Generalization in Deep RL with a Robust Adaptation Modulecited by 2
  27. 2025Bounding Distributional Shifts in World Modeling through Novelty Detectioncited by 2
  28. 2025Out-of-Distribution Detection for Safety Assurance of AI and Autonomous Systemscited by 2
  29. 2025PIP-LLM: Integrating PDDL-Integer Programming with LLMs for Coordinating Multi-Robot Teams Using Natural Languagecited by 2
  30. 2025Run, Ruminate, and Regulate: A Dual-process Thinking System for Vision-and-Language Navigationcited by 2
  31. 2026ActProbe: Action-Space Probe for Early Failure Detection of Generative Robot Policiescited by 2
  32. 2026SAFECAST: Robust Failure Detection for VLA Policies with Contrast-Set Training and Calibrationcited by 2
  33. 2024ILeSiA: Interactive Learning of Robot Situational Awareness from Camera Inputcited by 1
  34. 2024Pre-Trained Vision Models as Perception Backbones for Safety Filters in Autonomous Drivingcited by 1
  35. 2025Drones that Think on their Feet: Sudden Landing Decisions with Embodied AIcited by 1
  36. 2025Robot-Powered Data Flywheels: Deploying Robots in the Wild for Continual Data Collection and Foundation Model Adaptationcited by 1
  37. 2026An LLM-Agnostic, MAVLink-Based Drone Command and Control Interface and Agentic Harness Using the Model Context Protocolcited by 1
  38. 2026Describe-Then-Act: Proactive Agent Steering via Distilled Language-Action World Modelscited by 1

50 most cited of 67 All 67 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Evaluating Uncertainty-based Failure Detection for Closed-Loop LLM Planners
  2. 2025AD-FM: Multimodal LLMs for Anomaly Detection via Multi-Stage Reasoning and Fine-Grained Reward Optimization
  3. 2026RAPT: Model-Predictive Out-of-Distribution Detection and Failure Diagnosis for Sim-to-Real Humanoid Deployment
  4. 2025World Models for Anomaly Detection during Model-Based Reinforcement Learning Inference
  5. 2025Embodied Hazard Mitigation using Vision-Language Models for Autonomous Mobile Robots
  6. 2026AnomalyAgent: Training-Free Agentic Models for Zero-/Few-Shot Anomaly Detection
  7. 2025AuDeRe: Automated Strategy Decision and Realization in Robot Planning and Control via LLMs
  8. 2025Detecting Silent Failures in Multi-Agentic AI Trajectories