# DiMA: An LLM-Powered Ride-Hailing Assistant at DiDi

arXiv: https://arxiv.org/abs/2503.04768 · HTML: https://mlsanity.com/paper/2503.04768/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 49 references that are in the map.
- First posted on arXiv 12 Feb 2025.

## Builds on (most cited first, 20 of 20)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration](https://mlsanity.com/paper/2306.00978/) (2023)
- [Mind2Web: Towards a Generalist Agent for the Web](https://mlsanity.com/paper/2306.06070/) (2023)
- [Yi: Open Foundation Models by 01.AI](https://mlsanity.com/paper/2403.04652/) (2024)
- [Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models](https://mlsanity.com/paper/2401.01335/) (2024)
- [TravelPlanner: A Benchmark for Real-World Planning with Language Agents](https://mlsanity.com/paper/2402.01622/) (2024)
- [A Simple Language Model for Task-Oriented Dialogue](https://mlsanity.com/paper/2005.00796/) (2020)
- [UBAR: Towards Fully End-to-End Task-Oriented Dialog Systems with GPT-2](https://mlsanity.com/paper/2012.03539/) (2020)
- [GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-Supervised Learning and Explicit Policy Injection](https://mlsanity.com/paper/2111.14592/) (2021)
- [Smaller, Weaker, Yet Better: Training LLM Reasoners via Compute-Optimal Sampling](https://mlsanity.com/paper/2408.16737/) (2024)
- [Are LLMs All You Need for Task-Oriented Dialogue?](https://mlsanity.com/paper/2304.06556/) (2023)
- [Large Language Models as Zero-shot Dialogue State Tracker through Function Calling](https://mlsanity.com/paper/2402.10466/) (2024)
- [Intelligent Virtual Assistants with LLM-based Process Automation](https://mlsanity.com/paper/2312.06677/) (2023)
- [Timo: Towards Better Temporal Reasoning for Language Models](https://mlsanity.com/paper/2406.14192/) (2024)
- [End-to-end Task-oriented Dialogue: A Survey of Tasks, Methods, and Future Directions](https://mlsanity.com/paper/2311.09008/) (2023)
- [AutoSTF: Decoupled Neural Architecture Search for Cost-Effective Automated Spatio-Temporal Forecasting](https://mlsanity.com/paper/2409.16586/) (2024)
- [GRILLBot In Practice: Lessons and Tradeoffs Deploying Large Language Models for Adaptable Conversational Task Assistants](https://mlsanity.com/paper/2402.07647/) (2024)

## Built on by (most cited first, 7 of 7)

- [DeepTravel: An End-to-End Agentic Reinforcement Learning Framework for Autonomous Travel Planning Agents](https://mlsanity.com/paper/2509.21842/) (2025)
- [USTBench: Benchmarking and Dissecting Spatiotemporal Reasoning of LLMs as Urban Agents](https://mlsanity.com/paper/2505.17572/) (2025)
- [Agent-Omit: Adaptive Context Omission for Efficient LLM Agents](https://mlsanity.com/paper/2602.04284/) (2026)
- [Large Language Model Powered Intelligent Urban Agents: Concepts, Capabilities, and Applications](https://mlsanity.com/paper/2507.00914/) (2025)
- [AgentBalance: Backbone-then-Topology Design for Cost-Effective Multi-Agent Systems under Budget Constraints](https://mlsanity.com/paper/2512.11426/) (2025)
- [Understanding Structured Financial Data with LLMs: A Case Study on Fraud Detection](https://mlsanity.com/paper/2512.13040/) (2025)
- [ProfiLLM: Utility-Aligned Agentic User Profiling for Industrial Ride-Hailing Dispatch](https://mlsanity.com/paper/2606.18803/) (2026)

## Abstract (arXiv)

On-demand ride-hailing services like DiDi, Uber, and Lyft have transformed urban transportation, offering unmatched convenience and flexibility. In this paper, we introduce DiMA, an LLM-powered ride-hailing assistant deployed in DiDi Chuxing. Its goal is to provide seamless ride-hailing services and beyond through a natural and efficient conversational interface under dynamic and complex spatiotemporal urban contexts. To achieve this, we propose a spatiotemporal-aware order planning module that leverages external tools for precise spatiotemporal reasoning and progressive order planning. Additionally, we develop a cost-effective dialogue system that integrates multi-type dialog repliers with cost-aware LLM configurations to handle diverse conversation goals and trade-off response quality and latency. Furthermore, we introduce a continual fine-tuning scheme that utilizes real-world interactions and simulated dialogues to align the assistant's behavior with human preferred decision-making processes. Since its deployment in the DiDi application, DiMA has demonstrated exceptional performance, achieving 93% accuracy in order planning and 92% in response generation during real-world interactions. Offline experiments further validate DiMA capabilities, showing improvements of up to 70.23% in order planning and 321.27% in response generation compared to three state-of-the-art agent frameworks, while reducing latency by 0.72× to 5.47×. These results establish DiMA as an effective, efficient, and intelligent mobile assistant for ride-hailing services. Our project is released at https://github.com/usail-hkust/DiMA and we also release the MCP service (https://mcp.didichuxing.com/api) to foster the ride-hailing research community.