Cover Image

Characterizing the Robustness of Black-Box LLM Planners Under Perturbed Observations with Adaptive Stress Testing

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chakraborty, Neeloy, Pohovey, John, Ornik, Melkior, Driggs-Campbell, Katherine
Format:	Preprint
Published:	2025
Subjects:	Robotics Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Hallucination Detection in Foundation Models for Decision-Making: A Flexible Definition and Review of the State of the Art
by: Chakraborty, Neeloy, et al.
Published: (2024)

Structured Graph Network for Constrained Robot Crowd Navigation with Low Fidelity Simulation
by: Liu, Shuijing, et al.
Published: (2024)

An Expert Ensemble for Detecting Anomalous Scenes, Interactions, and Behaviors in Autonomous Driving
by: Ji, Tianchen, et al.
Published: (2025)

Decentralized Structural-RNN for Robot Crowd Navigation with Deep Reinforcement Learning
by: Liu, Shuijing, et al.
Published: (2020)

HEIGHT: Heterogeneous Interaction Graph Transformer for Robot Navigation in Crowded and Constrained Environments
by: Liu, Shuijing, et al.
Published: (2024)

Neural Informed RRT*: Learning-based Path Planning with Point Cloud State Representations under Admissible Ellipsoidal Constraints
by: Huang, Zhe, et al.
Published: (2023)

ComTraQ-MPC: Meta-Trained DQN-MPC Integration for Trajectory Tracking with Limited Active Localization Updates
by: Puthumanaillam, Gokul, et al.
Published: (2024)

A Brief Survey on Leveraging Large Scale Vision Models for Enhanced Robot Grasping
by: Kamboj, Abhi, et al.
Published: (2024)

COMMET: A System for Human-Induced Conflicts in Mobile Manipulation of Everyday Tasks
by: Li, Dongping, et al.
Published: (2025)

LIT: Large Language Model Driven Intention Tracking for Proactive Human-Robot Collaboration -- A Robot Sous-Chef Application
by: Huang, Zhe, et al.
Published: (2024)

Weathering Ongoing Uncertainty: Learning and Planning in a Time-Varying Partially Observable Environment
by: Puthumanaillam, Gokul, et al.
Published: (2023)

Lessons in Cooperation: A Qualitative Analysis of Driver Sentiments towards Real-Time Advisory Systems from a Driving Simulator User Study
by: Hasan, Aamir, et al.
Published: (2024)

Enhancing Robot Navigation Policies with Task-Specific Uncertainty Managements
by: Puthumanaillam, Gokul, et al.
Published: (2025)

Few-shot Scooping Under Domain Shift via Simulated Maximal Deployment Gaps
by: Zhu, Yifan, et al.
Published: (2024)

Tool-Planner: Task Planning with Clusters across Multiple Tools
by: Liu, Yanming, et al.
Published: (2024)

Manipulating Neural Path Planners via Slight Perturbations
by: Xiong, Zikang, et al.
Published: (2024)

GUIDEd Agents: Enhancing Navigation Policies through Task-Specific Uncertainty Abstraction in Localization-Limited Environments
by: Puthumanaillam, Gokul, et al.
Published: (2024)

Tool-as-Interface: Learning Robot Policies from Observing Human Tool Use
by: Chen, Haonan, et al.
Published: (2025)

EMMOE: A Comprehensive Benchmark for Embodied Mobile Manipulation in Open Environments
by: Li, Dongping, et al.
Published: (2025)

Cooperative Advisory Residual Policies for Congestion Mitigation
by: Hasan, Aamir, et al.
Published: (2024)

Learning Coordinated Bimanual Manipulation Policies using State Diffusion and Inverse Dynamics Models
by: Chen, Haonan, et al.
Published: (2025)

Language Models can Infer Action Semantics for Symbolic Planners from Environment Feedback
by: Zhu, Wang, et al.
Published: (2024)

Code-as-Symbolic-Planner: Foundation Model-Based Robot Planning via Symbolic Code Generation
by: Chen, Yongchao, et al.
Published: (2025)

Navigating in Uncertain Environments with Heterogeneous Visibility
by: Lee, Jongann, et al.
Published: (2026)

TAB-Fields: A Maximum Entropy Framework for Mission-Aware Adversarial Planning
by: Puthumanaillam, Gokul, et al.
Published: (2024)

A Moral Imperative: The Need for Continual Superalignment of Large Language Models
by: Puthumanaillam, Gokul, et al.
Published: (2024)

Robo-Troj: Attacking LLM-based Task Planners
by: Nahian, Mohaiminul Al, et al.
Published: (2025)

Tree-Planner: Efficient Close-loop Task Planning with Large Language Models
by: Hu, Mengkang, et al.
Published: (2023)

OmniEVA: Embodied Versatile Planner via Task-Adaptive 3D-Grounded and Embodiment-aware Reasoning
by: Liu, Yuecheng, et al.
Published: (2025)

DRAGON: A Dialogue-Based Robot for Assistive Navigation with Visual Language Grounding
by: Liu, Shuijing, et al.
Published: (2023)

Latent Adaptive Planner for Dynamic Manipulation
by: Noh, Donghun, et al.
Published: (2025)

TwoStep: Multi-agent Task Planning using Classical Planners and Large Language Models
by: Bai, David, et al.
Published: (2024)

Amortizing Trajectory Diffusion with Keyed Drift Fields
by: Puthumanaillam, Gokul, et al.
Published: (2026)

Hierarchical Motion Planning and Control under Unknown Nonlinear Dynamics via Predicted Reachability
by: Zhang, Zhiquan, et al.
Published: (2026)

Evaluating Uncertainty-based Failure Detection for Closed-Loop LLM Planners
by: Zheng, Zhi, et al.
Published: (2024)

Collision- and Reachability-Aware Multi-Robot Control with Grounded LLM Planners
by: Ji, Jiabao, et al.
Published: (2025)

Generating Traffic Scenarios via In-Context Learning to Learn Better Motion Planner
by: Aiersilan, Aizierjiang
Published: (2024)

CorrectionPlanner: Self-Correction Planner with Reinforcement Learning in Autonomous Driving
by: Guo, Yihong, et al.
Published: (2026)

LLM-Personalize: Aligning LLM Planners with Human Preferences via Reinforced Self-Training for Housekeeping Robots
by: Han, Dongge, et al.
Published: (2024)

The RL/LLM Taxonomy Tree: Reviewing Synergies Between Reinforcement Learning and Large Language Models
by: Pternea, Moschoula, et al.
Published: (2024)