SafeAgentBench
PulseAugur coverage of SafeAgentBench — every cluster mentioning SafeAgentBench across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
NEXUS framework enhances safety for embodied AI planning
Researchers have developed NEXUS, a novel neuro-symbolic framework designed to enhance the safety and robustness of embodied agents that plan using natural language instructions. This framework jointly maintains a PDDL …
-
Research paper highlights safety risks of voice-controlled embodied AI
A new research paper published on arXiv explores the safety implications of voice-controlled embodied AI systems. The study demonstrates that errors in automatic speech recognition (ASR) can lead to these AI models acce…
-
New PRISM method detects physical dangers in LLM actions beyond text safety
Researchers have developed a new method called PRISM to detect physical dangers posed by large language models (LLMs) when they are used to control embodied agents. Unlike traditional text-based safety checks, PRISM ana…