List your company

Role Consistency on SWE dev full set (test)

8.4Total Overstepping Rate (<INFO>)ChatDev (Joint FT)
6.8817.1427.437.66Apr 3, 2026

Evaluation results

MethodLinks
ChatDev (Joint FT)CEO agent training=FT, CPO agent training=FT, Backbone=Qwen, Role clarity regularization=true2026.048.49-38-58
ChatDev (Base CEO, FT CPO)CEO agent training=Base, CPO agent training=FT, Backbone=Qwen, Role clarity regularization=true2026.041832.4-28.4-34.6
ChatDev (FT CEO, Base CPO)CEO agent training=FT, CPO agent training=Base, Backbone=Qwen, Role clarity regularization=true2026.0440.640.8-5.8-26.2
ChatDev (Base-Base)CEO agent training=Base, CPO agent training=Base, Backbone=Qwen, Role clarity regularization=true2026.0446.467——