FaMA: LLM-Empowered Agentic Assistant for Consumer-to-Consumer Marketplace
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909770444701696 |
|---|---|
| author | Yan, Yineng Wang, Xidong Cheng, Jin Seng Hu, Ran Guan, Wentao Farahmand, Nahid Lin, Hengte Li, Yue |
| author_facet | Yan, Yineng Wang, Xidong Cheng, Jin Seng Hu, Ran Guan, Wentao Farahmand, Nahid Lin, Hengte Li, Yue |
| contents | The emergence of agentic AI, powered by Large Language Models (LLMs), marks a paradigm shift from reactive generative systems to proactive, goal-oriented autonomous agents capable of sophisticated planning, memory, and tool use. This evolution presents a novel opportunity to address long-standing challenges in complex digital environments. Core tasks on Consumer-to-Consumer (C2C) e-commerce platforms often require users to navigate complex Graphical User Interfaces (GUIs), making the experience time-consuming for both buyers and sellers. This paper introduces a novel approach to simplify these interactions through an LLM-powered agentic assistant. This agent functions as a new, conversational entry point to the marketplace, shifting the primary interaction model from a complex GUI to an intuitive AI agent. By interpreting natural language commands, the agent automates key high-friction workflows. For sellers, this includes simplified updating and renewal of listings, and the ability to send bulk messages. For buyers, the agent facilitates a more efficient product discovery process through conversational search. We present the architecture for Facebook Marketplace Assistant (FaMA), arguing that this agentic, conversational paradigm provides a lightweight and more accessible alternative to traditional app interfaces, allowing users to manage their marketplace activities with greater efficiency. Experiments show FaMA achieves a 98% task success rate on solving complex tasks on the marketplace and enables up to a 2x speedup on interaction time. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_03890 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FaMA: LLM-Empowered Agentic Assistant for Consumer-to-Consumer Marketplace Yan, Yineng Wang, Xidong Cheng, Jin Seng Hu, Ran Guan, Wentao Farahmand, Nahid Lin, Hengte Li, Yue Artificial Intelligence The emergence of agentic AI, powered by Large Language Models (LLMs), marks a paradigm shift from reactive generative systems to proactive, goal-oriented autonomous agents capable of sophisticated planning, memory, and tool use. This evolution presents a novel opportunity to address long-standing challenges in complex digital environments. Core tasks on Consumer-to-Consumer (C2C) e-commerce platforms often require users to navigate complex Graphical User Interfaces (GUIs), making the experience time-consuming for both buyers and sellers. This paper introduces a novel approach to simplify these interactions through an LLM-powered agentic assistant. This agent functions as a new, conversational entry point to the marketplace, shifting the primary interaction model from a complex GUI to an intuitive AI agent. By interpreting natural language commands, the agent automates key high-friction workflows. For sellers, this includes simplified updating and renewal of listings, and the ability to send bulk messages. For buyers, the agent facilitates a more efficient product discovery process through conversational search. We present the architecture for Facebook Marketplace Assistant (FaMA), arguing that this agentic, conversational paradigm provides a lightweight and more accessible alternative to traditional app interfaces, allowing users to manage their marketplace activities with greater efficiency. Experiments show FaMA achieves a 98% task success rate on solving complex tasks on the marketplace and enables up to a 2x speedup on interaction time. |
| title | FaMA: LLM-Empowered Agentic Assistant for Consumer-to-Consumer Marketplace |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2509.03890 |