LLM4Rail: An LLM-Augmented Personalized Railway Services Platform
Organizations: School of Artificial Intelligence, Chongqing University of Posts and Telecommunications, China · Department of Intelligent Science, Xi’an Jiaotong-Liverpool University, China · Department of Research and Development, Shenzhen Fanxiang Industrial Co., Ltd, China
Abstract
Large language models (LLMs) have significantly reshaped different walks of business. To meet the increasing demands for individualized railway service, we develop LLM4Rail - a novel LLM-augmented personalized railway services platform. Empowered by the LLM, LLM4Rail provides dedicated modules for ticket and weather inquiries, food & drink recommendations, and casual conversation. In LLM4Rail, we propose the iterative "Experience-Retrieval Question-Thought-Action-Observation (ER-QTAO)" reasoning framework. It introduces two key mechanisms, Experience Storage and Retrieval (ESR) and Diagnostic Observation Generation (DOG), to enhance the LLM's ability to invoke appropriate external tools with complex arguments. To provide personalized onboard dining services, we first construct the Chinese Railway Food & Drink (CRFD) dataset, which covers a wide range of signature dishes categorized by city, cuisine, age group, and spiciness level, and then develop an LLM-based zero-shot conversational recommender system for railway catering. In addition, to address the unconstrained nature of generative recommendations, we design a feature-similarity-based alignment mechanism to ensure that all recommended items are aligned with entries in the CRFD dataset.
Figures & tables
| Module | Foundation LLM | LLM-Only | CoT [ 20 ] | ReAct [ 26 ] | Reflexion [ 17 ] | LLM4Rail | |||||
| Acc (%) | # | Acc (%) | # | Acc (%) | # | Acc (%) | # | Acc (%) | # | ||
| Ticket Inquiry | Qwen3-235B | 23.6% | 1.00 | 48.4% | 1.00 | 21.8% | 2.30 | 19.8% | 1.00 | 24.8% | 2.92 |
| DeepSeek-v3.1 | 45.8% | 1.00 | 64.2% | 1.00 | 52.0% | 3.45 | 28.6% | 1.00 | 60.4% | 3.50 | |
| ChatGPT-4o | 38.5% | 1.00 | 52.3% | 1.00 | 42.7% | 2.26 | 25.0% | 1.00 | 51.6% | 2.90 | |
| Weather Inquiry | Qwen3-235B | 36.0% | 1.00 | 52.3% | 1.00 | 60.2% | 2.64 | 45.8% | 1.00 | 63.1% | 2.98 |
| DeepSeek-v3.1 | 37.0% | 1.00 | 54.6% | 1.00 | 71.7% | 3.00 | 48.3% | 1.00 | 74.2% | 3.20 | |
Memory-Augmented Language Model Agents
Memory-augmented language model agents use persistent facts, interaction histories, and skills to support personalization and long-horizon tasks.
See all 478 papers