Conversational Planning for Personal Plans

TL;DR

This paper introduces a novel LLM-based architecture for long-term conversational planning, enabling personalized, adaptive assistance across various real-life tasks by integrating macro-actions and tool use.

Contribution

It proposes a new framework where LLMs serve as meta-controllers for long-term planning, combining macro-actions and tool use for personalized task management.

Findings

Effective long-term planning through macro-actions

Adaptive conversational coaching demonstrated

Framework applicable to diverse real-life scenarios

Abstract

The language generation and reasoning capabilities of large language models (LLMs) have enabled conversational systems with impressive performance in a variety of tasks, from code generation, to composing essays, to passing STEM and legal exams, to a new paradigm for knowledge search. Besides those short-term use applications, LLMs are increasingly used to help with real-life goals or tasks that take a long time to complete, involving multiple sessions across days, weeks, months, or even years. Thus to enable conversational systems for long term interactions and tasks, we need language-based agents that can plan for long horizons. Traditionally, such capabilities were addressed by reinforcement learning agents with hierarchical planning capabilities. In this work, we explore a novel architecture where the LLM acts as the meta-controller deciding the agent's next macro-action, and tool use augmented LLM-based option policies execute the selected macro-action. We instantiate this framework for a specific set of macro-actions enabling adaptive planning for users' personal plans through conversation and follow-up questions collecting user feedback. We show how this paradigm can be applicable in scenarios ranging from tutoring for academic and non-academic tasks to conversational coaching for personal health plans.