Cover Image

SafeMind: Benchmarking and Mitigating Safety Risks in Embodied LLM Agents

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chen, Ruolin, Sun, Yinqian, Wang, Jihang, Lv, Mingyang, Zhang, Qian, Zeng, Yi
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

SafeMind: A Risk-Aware Differentiable Control Framework for Adaptive and Safe Quadruped Locomotion
by: Zhang, Zukun, et al.
Published: (2026)

CogToM: A Comprehensive Theory of Mind Benchmark inspired by Human Cognition for Large Language Models
by: Tong, Haibo, et al.
Published: (2026)

Towards Reliable Evaluation of Adversarial Robustness for Spiking Neural Networks
by: Wang, Jihang, et al.
Published: (2025)

SafeAgentBench: A Benchmark for Safe Task Planning of Embodied LLM Agents
by: Yin, Sheng, et al.
Published: (2024)

ForesightSafety Bench: A Frontier Risk Evaluation and Governance Framework towards Safe AI
by: Tong, Haibo, et al.
Published: (2026)

A Framework for Benchmarking and Aligning Task-Planning Safety in LLM-Based Embodied Agents
by: Huang, Yuting, et al.
Published: (2025)

Autonomous Alignment with Human Value on Altruism through Considerate Self-imagination and Theory of Mind
by: Tong, Haibo, et al.
Published: (2024)

Advancing Embodied Agent Security: From Safety Benchmarks to Input Moderation
by: Wang, Ning, et al.
Published: (2025)

EnactToM: An Evolving Benchmark for Functional Theory of Mind in Embodied Agents
by: Juneja, Gurusha, et al.
Published: (2026)

R-Judge: Benchmarking Safety Risk Awareness for LLM Agents
by: Yuan, Tongxin, et al.
Published: (2024)

BeSafe-Bench: Unveiling Behavioral Safety Risks of Situated Agents in Functional Environments
by: Li, Yuxuan, et al.
Published: (2026)

MedSentry: Understanding and Mitigating Safety Risks in Medical LLM Multi-Agent Systems
by: Chen, Kai, et al.
Published: (2025)

MindPower: Enabling Theory-of-Mind Reasoning in VLM-based Embodied Agents
by: Zhang, Ruoxuan, et al.
Published: (2025)

RoboSafe: Safeguarding Embodied Agents via Executable Safety Logic
by: Wang, Le, et al.
Published: (2025)

Multi-compartment Neuron and Population Encoding Powered Spiking Neural Network for Deep Distributional Reinforcement Learning
by: Sun, Yinqian, et al.
Published: (2023)

Continual Learning of Multiple Cognitive Functions with Brain-inspired Temporal Development Mechanism
by: Han, Bing, et al.
Published: (2025)

Adaptive Theory of Mind for LLM-based Multi-Agent Coordination
by: Mu, Chunjiang, et al.
Published: (2026)

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator
by: Zhou, Xueyang, et al.
Published: (2025)

Building Altruistic and Moral AI Agent with Brain-inspired Emotional Empathy Mechanisms
by: Zhao, Feifei, et al.
Published: (2024)

ClawSafety: "Safe" LLMs, Unsafe Agents
by: Wei, Bowen, et al.
Published: (2026)

SafeScientist: Toward Risk-Aware Scientific Discoveries by LLM Agents
by: Zhu, Kunlun, et al.
Published: (2025)

EmbodiedCity: A Benchmark Platform for Embodied Agent in Real-world City Environment
by: Gao, Chen, et al.
Published: (2024)

CityEQA: A Hierarchical LLM Agent on Embodied Question Answering Benchmark in City Space
by: Zhao, Yong, et al.
Published: (2025)

MADRA: Multi-Agent Debate for Risk-Aware Embodied Planning
by: Wang, Junjian, et al.
Published: (2025)

MindForge: Empowering Embodied Agents with Theory of Mind for Lifelong Cultural Learning
by: Lică, Mircea, et al.
Published: (2024)

TowerMind: A Tower Defence Game Learning Environment and Benchmark for LLM as Agents
by: Wang, Dawei, et al.
Published: (2026)

Light Alignment Improves LLM Safety via Model Self-Reflection with a Single Neuron
by: Shen, Sicheng, et al.
Published: (2026)

SafeHarbor: Hierarchical Memory-Augmented Guardrail for LLM Agent Safety
by: Liu, Zhe, et al.
Published: (2026)

Mitigating the Safety-utility Trade-off in LLM Alignment via Adaptive Safe Context Learning
by: Wang, Yanbo, et al.
Published: (2026)

Stay in Character, Stay Safe: Dual-Cycle Adversarial Self-Evolution for Safety Role-Playing Agents
by: Liao, Mingyang, et al.
Published: (2026)

AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agents
by: Wang, Haoyu, et al.
Published: (2025)

BeliefNest: A Joint Action Simulator for Embodied Agents with Theory of Mind
by: Sagara, Rikunari, et al.
Published: (2025)

IndicSafe: A Benchmark for Evaluating Multilingual LLM Safety in South Asia
by: Pattnayak, Priyaranjan, et al.
Published: (2026)

EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents
by: Yang, Rui, et al.
Published: (2025)

EmboCoach-Bench: Benchmarking AI Agents on Developing Embodied Robots
by: Lei, Zixing, et al.
Published: (2026)

CrimeMind: Simulating Urban Crime with Multi-Modal LLM Agents
by: Zeng, Qingbin, et al.
Published: (2025)

SafePro: Evaluating the Safety of Professional-Level AI Agents
by: Zhou, Kaiwen, et al.
Published: (2026)

DriveSafe: A Hierarchical Risk Taxonomy for Safety-Critical LLM-Based Driving Assistants
by: Kumar, Abhishek, et al.
Published: (2026)

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses
by: Li, Xiao, et al.
Published: (2026)

Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark
by: Ji, Jiaming, et al.
Published: (2023)