DarwinTOD: LLM-driven Lifelong Self-evolution for Task-oriented Dialog Systems
This addresses the limitation of static dialog systems in dynamic real-world environments, offering a novel approach for autonomous lifelong improvement without human intervention.
The paper tackles the problem of task-oriented dialog systems being unable to evolve or adapt after deployment by proposing DarwinTOD, a framework that integrates evolutionary computation and LLM-driven self-improvement for continuous optimization, achieving performance gains that surpass previous state-of-the-art methods.
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.