CRPO modifies GRPO with three mechanisms—decoupling task and style rewards, adapting constraints to character complexity, and using generic responses as negative baselines—to improve character fidelity in role-playing agents.
Sgpo: Self-generated preference optimization based on self-improver.arXiv preprint arXiv:2507.20181,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
CRPO: Character-centric Group Relative Policy Optimization for Role-aware Reasoning in Role-playing Agents
CRPO modifies GRPO with three mechanisms—decoupling task and style rewards, adapting constraints to character complexity, and using generic responses as negative baselines—to improve character fidelity in role-playing agents.