AutoScrum: Automating Project Planning Using Large Language Models
This work addresses the problem of manual and time-consuming project planning for project managers and teams, offering an automated solution that could streamline workflows, though it appears incremental in applying existing LLM capabilities to a specific domain.
The paper tackles automating project planning by using large language models to design complex project plans from current and desired states, demonstrating two approaches: a scrum-based method for detailed planning and a shortcut method for quick task generation, with all automation implemented through novel 'Language Programs' in natural language.
Recent advancements in the field of large language models have made it possible to use language models for advanced reasoning. In this paper we leverage this ability for designing complex project plans based only on knowing the current state and the desired state. Two approaches are demonstrated - a scrum based approach and a shortcut plan approach. The scrum based approach executes an automated process of requirements gathering, user story mapping, feature identification, task decomposition and finally generates questions and search terms for seeking out domain specific information to assist with task completion. The shortcut approach looks at most recent snapshot of the current and desired state and generates the next most reasonable task to do in order to get to the desired state as quickly as possible. In this paper we automate everything using a novel concept of "Language Programs". These are programs written in natural language designed to process input data through the language model. Guidance language is used for all LLM programs. All demo source code for this paper is available at https://github.com/autoscrum/autoscrum