DarwinTOD: LLM-driven Lifelong Self-evolution for Task-oriented Dialog Systems
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910127108390912 |
|---|---|
| author | Zhang, Shuyu Liu, Yujie Wang, Xinru Zhang, Cheng Zhu, Yanmin Li, Bin |
| author_facet | Zhang, Shuyu Liu, Yujie Wang, Xinru Zhang, Cheng Zhu, Yanmin Li, Bin |
| contents | Traditional task-oriented dialog systems are unable to evolve from ongoing interactions or adapt to new domains after deployment, that is a critical limitation in real-world dynamic environments. Continual learning approaches depend on episodic retraining with human curated data, failing to achieve autonomy lifelong improvement. While evolutionary computation and LLM driven self improvement offer promising mechanisms for dialog optimization, they lack a unified framework for holistic, iterative strategy refinement. To bridge this gap, we propose DarwinTOD, a lifelong self evolving dialog framework that systematically integrates these two paradigms, enabling continuous strategy optimization from a zero-shot base without task specific fine-tuning. DarwinTOD maintains an Evolvable Strategy Bank and operates through a dual-loop process: online multi-agent dialog execution with peer critique, and offline structured evolutionary operations that refine the strategy bank using accumulated feedback. This closed-loop design enables autonomous continuous improvement without human intervention. Extensive experiments show that DarwinTOD surpasses previous state-of-the-art methods and exhibits continuous performance gains throughout evolution. Our work provides a novel framework for building dialog systems with lifelong self evolution capabilities. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_07248 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DarwinTOD: LLM-driven Lifelong Self-evolution for Task-oriented Dialog Systems Zhang, Shuyu Liu, Yujie Wang, Xinru Zhang, Cheng Zhu, Yanmin Li, Bin Multiagent Systems Human-Computer Interaction Traditional task-oriented dialog systems are unable to evolve from ongoing interactions or adapt to new domains after deployment, that is a critical limitation in real-world dynamic environments. Continual learning approaches depend on episodic retraining with human curated data, failing to achieve autonomy lifelong improvement. While evolutionary computation and LLM driven self improvement offer promising mechanisms for dialog optimization, they lack a unified framework for holistic, iterative strategy refinement. To bridge this gap, we propose DarwinTOD, a lifelong self evolving dialog framework that systematically integrates these two paradigms, enabling continuous strategy optimization from a zero-shot base without task specific fine-tuning. DarwinTOD maintains an Evolvable Strategy Bank and operates through a dual-loop process: online multi-agent dialog execution with peer critique, and offline structured evolutionary operations that refine the strategy bank using accumulated feedback. This closed-loop design enables autonomous continuous improvement without human intervention. Extensive experiments show that DarwinTOD surpasses previous state-of-the-art methods and exhibits continuous performance gains throughout evolution. Our work provides a novel framework for building dialog systems with lifelong self evolution capabilities. |
| title | DarwinTOD: LLM-driven Lifelong Self-evolution for Task-oriented Dialog Systems |
| topic | Multiagent Systems Human-Computer Interaction |
| url | https://arxiv.org/abs/2601.07248 |