# TransitLM: A Large-Scale Dataset and Benchmark for Map-Free Transit Route Generation

arXiv: https://arxiv.org/abs/2605.22355 · HTML: https://mlsanity.com/paper/2605.22355/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 45 references that are in the map.
- First posted on arXiv 21 May 2026.

## Builds on (most cited first, 28 of 28)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Training Compute-Optimal Large Language Models](https://mlsanity.com/paper/2203.15556/) (2022)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [Don't Stop Pretraining: Adapt Language Models to Domains and Tasks](https://mlsanity.com/paper/2004.10964/) (2020)
- [ZeRO: Memory Optimizations Toward Training Trillion Parameter Models](https://mlsanity.com/paper/1910.02054/) (2019)
- [TravelPlanner: A Benchmark for Real-World Planning with Language Agents](https://mlsanity.com/paper/2402.01622/) (2024)
- [On the Planning Abilities of Large Language Models : A Critical Investigation](https://mlsanity.com/paper/2305.15771/) (2023)
- [NATURAL PLAN: Benchmarking LLMs on Natural Language Planning](https://mlsanity.com/paper/2406.04520/) (2024)
- [LLM-A*: Large Language Model Enhanced Incremental Heuristic Search on Path Planning](https://mlsanity.com/paper/2407.02511/) (2024)
- [GeoLM: Empowering Language Models for Geospatially Grounded Language Understanding](https://mlsanity.com/paper/2310.14478/) (2023)
- [Can Large Vision Language Models Read Maps Like a Human?](https://mlsanity.com/paper/2503.14607/) (2025)
- [CityBench: Evaluating the Capabilities of Large Language Models for Urban Tasks](https://mlsanity.com/paper/2406.13945/) (2024)
- [Route Planning in Transportation Networks](https://mlsanity.com/paper/1504.05140/) (2015)
- [TripTailor: A Real-World Benchmark for Personalized Travel Planning](https://mlsanity.com/paper/2508.01432/) (2025)
- [TripCraft: A Benchmark for Spatio-Temporally Fine Grained Travel Planning](https://mlsanity.com/paper/2502.20508/) (2025)
- [TP-RAG: Benchmarking Retrieval-Augmented Large Language Model Agents for Spatiotemporal-Aware Travel Planning](https://mlsanity.com/paper/2504.08694/) (2025)
- [TRIP-Bench: A Benchmark for Long-Horizon Interactive Agents in Real-World Scenarios](https://mlsanity.com/paper/2602.01675/) (2026)
- [MobilityBench: A Benchmark for Evaluating Route-Planning Agents in Real-World Mobility Scenarios](https://mlsanity.com/paper/2602.22638/) (2026)
- [Connection Scan Algorithm](https://mlsanity.com/paper/1703.05997/) (2017)
- [TraveLLM: Could you plan my new public transit route in face of a network disruption?](https://mlsanity.com/paper/2407.14926/) (2024)
- [USTBench: Benchmarking and Dissecting Spatiotemporal Reasoning of LLMs as Urban Agents](https://mlsanity.com/paper/2505.17572/) (2025)
- [GridRoute: A Benchmark for LLM-Based Route Planning with Cardinal Movement in Grid Environments](https://mlsanity.com/paper/2505.24306/) (2025)
- [MapTrace: Scalable Data Generation for Route Tracing on Maps](https://mlsanity.com/paper/2512.19609/) (2025)

## Abstract (arXiv)

Public transit route planning traditionally depends on structured map infrastructure and complex routing engines, and no existing dataset supports training models to bypass this dependency. We present TransitLM, a large-scale dataset of over 13 million transit route planning records from four Chinese cities covering 120,845 stations and 13,666 lines, released as a continual pre-training corpus and benchmark data for three evaluation tasks with complementary metrics. Experiments show that an LLM trained on TransitLM produces structurally valid routes at high accuracy and implicitly grounds arbitrary GPS coordinates to appropriate stations without any explicit mapping. These results demonstrate that transit route planning can be learned entirely from data, enabling end-to-end, map-free route generation directly from origin-destination information. The dataset and benchmark are available at https://huggingface.co/datasets/GD-ML/TransitLM, with evaluation code at https://github.com/HotTricker/TransitLM.