AgenticPay: A Multi-Agent LLM Negotiation System for Buyer-Seller Transactions
This provides a foundation for studying agentic commerce and language-based market interaction, though it is incremental as it builds on existing multi-agent and LLM research.
The authors tackled the lack of principled benchmarks for evaluating LLM-based agents in economic negotiations by introducing AgenticPay, a simulation framework with over 110 tasks for multi-agent buyer-seller negotiation, which revealed substantial performance gaps in state-of-the-art LLMs.
Large language model (LLM)-based agents are increasingly expected to negotiate, coordinate, and transact autonomously, yet existing benchmarks lack principled settings for evaluating language-mediated economic interaction among multiple agents. We introduce AgenticPay, a benchmark and simulation framework for multi-agent buyer-seller negotiation driven by natural language. AgenticPay models markets in which buyers and sellers possess private constraints and product-dependent valuations, and must reach agreements through multi-round linguistic negotiation rather than numeric bidding alone. The framework supports a diverse suite of over 110 tasks ranging from bilateral bargaining to many-to-many markets, with structured action extraction and metrics for feasibility, efficiency, and welfare. Benchmarking state-of-the-art proprietary and open-weight LLMs reveals substantial gaps in negotiation performance and highlights challenges in long-horizon strategic reasoning, establishing AgenticPay as a foundation for studying agentic commerce and language-based market interaction. Code and dataset are available at the link: https://github.com/SafeRL-Lab/AgenticPay.