DIVERT uses snapshot-based branching and diversity-guided user simulation to discover more agent failures per token while expanding coverage of interaction tasks.
B.3 Divergent User Generation For each selected junction, we generate multiple candidate user responses using the same prompt and decoding configuration
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Efficient Agent Evaluation via Diversity-Guided User Simulation
DIVERT uses snapshot-based branching and diversity-guided user simulation to discover more agent failures per token while expanding coverage of interaction tasks.