RESEARCHInvestigateNEXT 12 MONTHS
AgentProv: Auditing Agentic LLM API Providers via Tool-use Policy Probes
arXiv cs.LG — Machine Learning
Factual evidence
What the source reports
AgentProv introduces tool-use policy probes to audit whether API providers silently substitute or quantize agentic LLM backbones.