Protocol Agent: What If Agents Could Use Cryptography In Everyday Life?
This work addresses the inability of current AI agents to effectively and securely employ cryptographic primitives in everyday interactions to resolve privacy and trust challenges. We propose the first framework enabling agents to autonomously identify, negotiate, and execute appropriate cryptographic protocols—such as those for anonymous credentials or fair payment splitting—to achieve privacy-preserving interactions. To evaluate this capability, we introduce a comprehensive benchmark encompassing protocol identification, multi-agent negotiation, execution, computational feasibility, and security assessment. We further develop data generation pipelines and supervised fine-tuning (SFT) strategies to enhance agent performance. Experimental results demonstrate that fine-tuned models significantly outperform baseline approaches on this benchmark, validating the efficacy of our proposed framework.