DarwinTOD proposes a dual-loop LLM-driven framework with an Evolvable Strategy Bank that enables lifelong autonomous improvement in task-oriented dialog systems through online multi-agent critique and offline evolutionary refinement.
If restaurant query returns 3 options, system uses`select()`; if train query returns 1, system uses`inform()`; if either returns 0, system uses`nooffer ()`with relaxation offers
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.MA 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
DarwinTOD: LLM-driven Lifelong Self-evolution for Task-oriented Dialog Systems
DarwinTOD proposes a dual-loop LLM-driven framework with an Evolvable Strategy Bank that enables lifelong autonomous improvement in task-oriented dialog systems through online multi-agent critique and offline evolutionary refinement.