LLM planners for robots often produce dangerous plans even when planning succeeds, with safety awareness staying flat as model scale improves planning ability.
A framework for benchmarking and aligning task-planning safety in llm-based embodied agents.arXiv preprint
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
years
2026 4roles
background 3polarities
background 3representative citing papers
SafetyALFRED shows multimodal LLMs recognize kitchen hazards accurately in QA tests but achieve low success rates when required to mitigate those hazards through embodied planning.
A survey that maps safety risks in personalized LLMs, introduces a unified taxonomy, and highlights three structural inadequacies in existing research on user-invariant safety, isolated techniques, and short-term evaluations.
citing papers explorer
-
Using large language models for embodied planning introduces systematic safety risks
LLM planners for robots often produce dangerous plans even when planning succeeds, with safety awareness staying flat as model scale improves planning ability.
-
SafetyALFRED: Evaluating Safety-Conscious Planning of Multimodal Large Language Models
SafetyALFRED shows multimodal LLMs recognize kitchen hazards accurately in QA tests but achieve low success rates when required to mitigate those hazards through embodied planning.
-
Personalization Meets Safety:Mechanisms,Risks,and Mitigations in Personalized LLMs
A survey that maps safety risks in personalized LLMs, introduces a unified taxonomy, and highlights three structural inadequacies in existing research on user-invariant safety, isolated techniques, and short-term evaluations.