# LawFlow: Collecting and Simulating Lawyers' Thought Processes on Business Formation Case Studies

arXiv: https://arxiv.org/abs/2504.18942 · HTML: https://mlsanity.com/paper/2504.18942/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 17 of its 34 references that are in the map.
- First posted on arXiv 26 Apr 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 17 of 17)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [TravelPlanner: A Benchmark for Real-World Planning with Language Agents](https://mlsanity.com/paper/2402.01622/) (2024)
- [HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs](https://mlsanity.com/paper/2412.18925/) (2024)
- [The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-Tuning](https://mlsanity.com/paper/2305.14045/) (2023)
- [OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models](https://mlsanity.com/paper/2410.09671/) (2024)
- [DriveCoT: Integrating Chain-of-Thought Reasoning with End-to-End Driving](https://mlsanity.com/paper/2403.16996/) (2024)
- [LexEval: A Comprehensive Chinese Legal Benchmark for Evaluating Large Language Models](https://mlsanity.com/paper/2409.20288/) (2024)
- [WorkflowLLM: Enhancing Workflow Orchestration Capability of Large Language Models](https://mlsanity.com/paper/2411.05451/) (2024)
- [ProAgent: From Robotic Process Automation to Agentic Process Automation](https://mlsanity.com/paper/2311.10751/) (2023)
- [Robotic Process Automation -- A Systematic Literature Review and Assessment Framework](https://mlsanity.com/paper/2012.11951/) (2020)
- [LexGPT 0.1: pre-trained GPT-J models with Pile of Law](https://mlsanity.com/paper/2306.05431/) (2023)
- [ScholaWrite: A Dataset of End-to-End Scholarly Writing Process](https://mlsanity.com/paper/2502.02904/) (2025)
- [On the Evaluation of Intelligent Process Automation](https://mlsanity.com/paper/2001.02639/) (2020)
- [Decoding the End-to-end Writing Trajectory in Scholarly Manuscripts](https://mlsanity.com/paper/2304.00121/) (2023)
- [AnnoCaseLaw: A Richly-Annotated Dataset For Benchmarking Explainable Legal Judgment Prediction](https://mlsanity.com/paper/2503.00128/) (2025)

## Built on by (most cited first, 2 of 2)

- [Flipping the Dialogue: Training and Evaluating User Language Models](https://mlsanity.com/paper/2510.06552/) (2025)
- [How Do AI Agents Do Human Work? Comparing AI and Human Workflows Across Diverse Occupations](https://mlsanity.com/paper/2510.22780/) (2025)

## Abstract (arXiv)

Legal practitioners, particularly those early in their careers, face complex, high-stakes tasks that require adaptive, context-sensitive reasoning. While AI holds promise in supporting legal work, current datasets and models are narrowly focused on isolated subtasks and fail to capture the end-to-end decision-making required in real-world practice. To address this gap, we introduce LawFlow, a dataset of complete end-to-end legal workflows collected from trained law students, grounded in real-world business entity formation scenarios. Unlike prior datasets focused on input-output pairs or linear chains of thought, LawFlow captures dynamic, modular, and iterative reasoning processes that reflect the ambiguity, revision, and client-adaptive strategies of legal practice. Using LawFlow, we compare human and LLM-generated workflows, revealing systematic differences in structure, reasoning flexibility, and plan execution. Human workflows tend to be modular and adaptive, while LLM workflows are more sequential, exhaustive, and less sensitive to downstream implications. Our findings also suggest that legal professionals prefer AI to carry out supportive roles, such as brainstorming, identifying blind spots, and surfacing alternatives, rather than executing complex workflows end-to-end. Our results highlight both the current limitations of LLMs in supporting complex legal workflows and opportunities for developing more collaborative, reasoning-aware legal AI systems. All data and code are available on our project page (https://minnesotanlp.github.io/LawFlow-website/).