Equal reward weighting outperforms targeted weighting in RL-based BPMN generation across 48 configurations, with design choices producing effects as large as applying RL itself.
Permutation, Parametric, and Bootstrap Tests of Hypotheses
1 Pith paper cite this work, alongside 699 external citations. Polarity classification is still indexing.
1
Pith paper citing it
699
external citations · OpenAlex
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Improving LLM-Generated Process Model Quality Through Reinforcement Learning: The Role of Reward Function Design
Equal reward weighting outperforms targeted weighting in RL-based BPMN generation across 48 configurations, with design choices producing effects as large as applying RL itself.