BeSafe-Bench: Unveiling Behavioral Safety Risks of Situated Agents in Functional Environments

arXiv 2603.25747d1f38c860da5a782b339b6fdfa3bfecd50936443794c64af53c73a6ec409a1c6
AI safetyCAD generationGUI agentsLLM securityagentic systemsbehavioral safetybenchmarkingembodied AIknowledge graphsmultimodal AIphotovoltaic safetyreinforcement learningsimulation automationspeech-language models

Paper metadata

arXiv ID
2603.25747
Version
Not specified by this published record
Category
Computer Science — Artificial Intelligence (cs.AI)

The PDF link points to arxiv.org. Baitaphish does not expose a private stored PDF.

Evidence and limitations

Source ID
arxiv_cs_ai
Record identifier
d1f38c860da5a782b339b6fdfa3bfecd50936443794c64af53c73a6ec409a1c6
Enrichment time
2026-08-16T13:04:32Z
AI-assisted enrichment
Yes

This record may overlap with other records. Its enrichment can be incomplete or wrong, and machine assistance was used. Validate consequential decisions against the linked source and your own environment.

BeSafe-Bench: Unveiling Behavioral Safety Risks of Situated Agents in Functional Environments · Baitaphish