Saved in:
Bibliographic Details
Main Authors: Liu, Xianyang, Gu, Shangding, Song, Dawn
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.06008
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915778477948928
author Liu, Xianyang
Gu, Shangding
Song, Dawn
author_facet Liu, Xianyang
Gu, Shangding
Song, Dawn
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2602_06008
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle AgenticPay: A Multi-Agent LLM Negotiation System for Buyer-Seller Transactions
Liu, Xianyang
Gu, Shangding
Song, Dawn
Artificial Intelligence
Machine Learning
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.
title AgenticPay: A Multi-Agent LLM Negotiation System for Buyer-Seller Transactions
topic Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2602.06008