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
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
Figure 1: The overall architecture of the LLM4Rail platform.
Figure 2: An illustration of the Chinese Railway Food and Drink (CRFD) takeout dataset constructed by us.
Figure 3: An illustration of the LLM-based conversational food & drink recommendations using feature similarity-based item alignment.
Module
Foundation LLM
LLM-Only
CoT [ 20 ]
ReAct [ 26 ]
Reflexion [ 17 ]
LLM4Rail
Acc (%)
# Iter
Acc (%)
# Iter
Acc (%)
# Iter
Acc (%)
# Iter
Acc (%)
# Iter
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
Table 1: Performance comparison of various reasoning frameworks and foundation models on Ticket Inquiry and Weather Inquiry tasks in terms of information retrieval accuracy (Acc) and average number of reasoning iterations ( #\mboxIter ).
Table 5
Figure 4: The proportion of the top- k food and drink items Prop@k(k=1,5,10) recommended by different foundation models that are present in the CRFD dataset (left), and the performance of food and drink recommendation by different recommendation methods in terms of Recall@k(k=1,5,10) (right).
Figure 5: LLM4Rail system demonstration: Food & Drink Recommendation.
Although large language models (LLMs) have recently gained traction in recommender systems due to their strong reasoning capabilities and extensive world knowledge, previous LLM-based agents suffer from hallucination and context-length limitations, and thus are not suitable for full-ranking recommendation tasks. To circumvent these limitations through architectural design rather than modifying the LLM itself, we propose an agent-based recommendation framework, memory-based Personalized Recommendation Tool learning via autonomous language Agents (PRTA), in which an LLM acts as a central planner interacting with multiple recommendation models as tools. The LLM-based agent is responsible for high-level reasoning and personalized tool selection, while traditional recommendation models perform full-ranking scoring, leveraging their scalability in modeling behavioral patterns. To support personalized tool selection, we design reflection mechanisms that enable the agent to evaluate and compare tools for each user based on user profiles and candidate ranked lists. Extensive experiments across three public datasets demonstrate the superiority of \modelname over traditional recommendation and LLM-based baselines in improving full-ranking recommendation performance.
Mingdai Yang, Zhiwei Liu, Weizhi Zhang +3
Univ. of Illinois Chicago Chicago, IL, USA · Microsoft Mountain View, USA · Beihang University, & Hangzhou Innovation Institute of BUAA Beijing & Hangzhou, China
In recommender systems, large language models (LLMs) have gained popularity for generating descriptive summarization to improve recommendation robustness, along with Graph Convolution Networks. However, existing LLM-enhanced recommendation studies mainly rely on the internal knowledge of LLMs about item titles while neglecting the importance of various factors influencing users' decisions. Although information reflecting various decision factors of each user is abundant in reviews, few studies have actively exploited such insights for recommendation. To address these limitations, we propose a ReFORM: Review-aggregated Profile Generation via LLM with Multi-FactOr Attentive RecoMmendation framework. Specifically, we first generate factor-specific user and item profiles from reviews using LLM to capture a user's preference by items and an item's evaluation by users. Then, we propose a Multi-Factor Attention to highlight the most influential factors in each user's decision-making process. In this paper, we conduct experiments on two restaurant datasets of varying scales, demonstrating its robustness and superior performance over state-of-the-art baselines. Furthermore, in-depth analyses validate the effectiveness of the proposed modules and provide insights into the sources of personalization. Our source code and datasets are available at https://github.com/m0onsoo/ReFORM.
Moonsoo Park, Seulbeen Je, Donghyeon Park
University of Southern California, USA · Sejong University, South Korea
Context-aware recommender systems have long recognized that factors such as location, time, and weather shape where and what people choose to eat. Existing weather-aware food and point-of-interest recommenders, however, typically treat weather generically -- mapping conditions to preferences through hand-crafted rules or specially trained context models -- and do not capture that the culturally appropriate response to weather is itself region-specific: a rainy evening calls for hot tea and fried snacks in one culinary culture and for very different comfort food in another. Encoding such weather-by-region-by-cuisine interactions as explicit rules or training data is brittle and does not scale. We present a weather- and location-aware agentic dining-recommendation system that takes a different approach: a large language model (LLM) orchestrates tools for location and weather retrieval and then reasons in natural language over the combined context, drawing on the cultural and culinary world knowledge already latent in the model to produce region-sensitive, weather-appropriate recommendations without per-region rule tables or specialized training. We describe the agent architecture, the tool-orchestration flow (Google location services and a weather service feeding an OpenAI LLM), and the reasoning mechanism, and we report on a working prototype that was implemented and briefly deployed end-to-end. We discuss design trade-offs -- cost, latency, ambiguity handling, and fallbacks -- and we are explicit about limitations, including the absence of a formal user study and the risk of cultural stereotyping in locality-based inference. The contribution is architectural: a simple, extensible pattern for incorporating environmental and cultural context into agentic recommendation through LLM reasoning rather than engineered rules.