FishBargain: An LLM-Empowered Bargaining Agent for Online Fleamarket Platform Sellers

TL;DR

The paper tackles bargaining on online fleamarket platforms where individual sellers face time constraints and limited negotiation skills. It introduces FishBargain, a large-language-model-powered bargaining agent with three modules—price extractor, policy planner, and utterance generator—to automate and optimize seller negotiations. The policy planner decouples strategy into discrete actions and language skills and employs bi-directional thinking to anticipate adversary actions. Experiments on 11,130 real Xianyu dialogues show FishBargain improves automatic and human evaluation metrics over baselines, indicating significant potential to help individual sellers close more deals and extend to broader fleamarket settings.

Abstract

Different from traditional Business-to-Consumer e-commerce platforms~(e.g., Amazon), online fleamarket platforms~(e.g., Craigslist) mainly focus on individual sellers who are lack of time investment and business proficiency. Individual sellers often struggle with the bargaining process and thus the deal is unaccomplished. Recent advancements in Large Language Models(LLMs) demonstrate huge potential in various dialogue tasks, but those tasks are mainly in the form of passively following user's instruction. Bargaining, as a form of proactive dialogue task, represents a distinct art of dialogue considering the dynamism of environment and uncertainty of adversary strategies. In this paper, we propose an LLM-empowered bargaining agent designed for online fleamarket platform sellers, named as FishBargain. Specifically, FishBargain understands the chat context and product information, chooses both action and language skill considering possible adversary actions and generates utterances. FishBargain has been tested by thousands of individual sellers on one of the largest online fleamarket platforms~(Xianyu) in China. Both qualitative and quantitative experiments demonstrate that FishBargain can effectively help sellers make more deals.

Figures (3)

• Figure 1: Bargaining process on the Xianyu platform. The two on the left are human responses. Failure to respond in time and lack of bargaining skills lead to a failed sale. The one on the right is the FishBargain response, which responds in time and closes the deal.
• Figure 2: Overview of the FishBargain system architecture.
• Figure 3: Illustration of FishBargain responses.