
Co-authored AgenticPay benchmark for evaluating multi-agent LLM negotiation systems.
How media typically covers Shangding Gu
Referenced in coverage
AgenticPay introduces a benchmark and simulation framework for evaluating multi-agent LLM-based negotiation systems in buyer-seller transactions, revealing substantial performance gaps in current LLMs for long-horizon strategic reasoning and language-mediated economic interaction.
“Co-authored AgenticPay benchmark for evaluating multi-agent LLM negotiation systems.”