PRINCIPLES: Synthetic Strategy Memory for Proactive Dialogue Agents
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915942598967296 |
|---|---|
| author | Kim, Namyoung Ong, Kai Tzu-iunn Hwang, Yeonjun Kang, Minseok Jihn, Iiseo Kim, Gayoung Kim, Minju Yeo, Jinyoung |
| author_facet | Kim, Namyoung Ong, Kai Tzu-iunn Hwang, Yeonjun Kang, Minseok Jihn, Iiseo Kim, Gayoung Kim, Minju Yeo, Jinyoung |
| contents | Dialogue agents based on large language models (LLMs) have shown promising performance in proactive dialogue, which requires effective strategy planning. However, existing approaches to strategy planning for proactive dialogue face several limitations: limited strategy coverage, preference bias in planning, and reliance on costly additional training. To address these, we propose PRINCIPLES: a synthetic strategy memory for proactive dialogue agents. PRINCIPLES is derived through offline self-play simulations and serves as reusable knowledge that guides strategy planning during inference, eliminating the need for additional training and data annotation. We evaluate PRINCIPLES in both emotional support and persuasion domains, demonstrating consistent improvements over strong baselines. Furthermore, PRINCIPLES maintains its robustness across extended and more diverse evaluation settings. See our project page at https://huggingface.co/spaces/kimnamssya/Principles. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_17459 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PRINCIPLES: Synthetic Strategy Memory for Proactive Dialogue Agents Kim, Namyoung Ong, Kai Tzu-iunn Hwang, Yeonjun Kang, Minseok Jihn, Iiseo Kim, Gayoung Kim, Minju Yeo, Jinyoung Computation and Language Dialogue agents based on large language models (LLMs) have shown promising performance in proactive dialogue, which requires effective strategy planning. However, existing approaches to strategy planning for proactive dialogue face several limitations: limited strategy coverage, preference bias in planning, and reliance on costly additional training. To address these, we propose PRINCIPLES: a synthetic strategy memory for proactive dialogue agents. PRINCIPLES is derived through offline self-play simulations and serves as reusable knowledge that guides strategy planning during inference, eliminating the need for additional training and data annotation. We evaluate PRINCIPLES in both emotional support and persuasion domains, demonstrating consistent improvements over strong baselines. Furthermore, PRINCIPLES maintains its robustness across extended and more diverse evaluation settings. See our project page at https://huggingface.co/spaces/kimnamssya/Principles. |
| title | PRINCIPLES: Synthetic Strategy Memory for Proactive Dialogue Agents |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2509.17459 |