Conversational Planning for Personal Plans
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913709827293184 |
|---|---|
| author | Christakopoulou, Konstantina Qu, Iris Canny, John Goodridge, Andrew Adams, Cj Chen, Minmin Matarić, Maja |
| author_facet | Christakopoulou, Konstantina Qu, Iris Canny, John Goodridge, Andrew Adams, Cj Chen, Minmin Matarić, Maja |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_19500 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Conversational Planning for Personal Plans Christakopoulou, Konstantina Qu, Iris Canny, John Goodridge, Andrew Adams, Cj Chen, Minmin Matarić, Maja Artificial Intelligence Computation and Language Human-Computer Interaction Machine Learning 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. |
| title | Conversational Planning for Personal Plans |
| topic | Artificial Intelligence Computation and Language Human-Computer Interaction Machine Learning |
| url | https://arxiv.org/abs/2502.19500 |