Adversarial Closed-Loop Curriculum for Evolving Role-Playing Agents

arXiv:2609.28609 · cs.AI · Submitted 2026-09-23 · Read on arXiv

cs.AI

Submitted: 2026-09-23

Updated: 2026-09-23

Code: https://github.com/verl-project/verl

Terminology

• Actor — 64× in this paper · explained in 3 episodes
• Benchmark — 24× in this paper · explained in 2 episodes
• Consistency — 14× in this paper · explained in 3 episodes
• GRPO — 11× in this paper · explained in 6 episodes
• Reinforcement Learning — 10× in this paper · explained in 4 episodes
• Character Consistency — 6× in this paper
• Ablation — 4× in this paper · explained in 1 episode
• Fidelity — 4× in this paper · explained in 2 episodes
• Fine-Tuning — 4× in this paper · explained in 5 episodes
• LLM judge — 4× in this paper · explained in 2 episodes
• Verifier — 3× in this paper · explained in 2 episodes
• Interaction Proactivity — 2× in this paper
• Linguistic Quality — 2× in this paper
• Reinforcement Learning (RL) — 2× in this paper · explained in 25 episodes
• Verification — 2× in this paper · explained in 2 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Ablation study — 1× in this paper · explained in 1 episode
• Adversarial Context — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Contrastive Learning — 1× in this paper · explained in 5 episodes
• Conversation Memory — 1× in this paper
• Core — 1× in this paper · explained in 2 episodes
• Generalizability — 1× in this paper · explained in 6 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Intra-Pool Distance — 1× in this paper
• LLM-as-a-Judge — 1× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Multimodal Reasoning — 1× in this paper · explained in 5 episodes
• New Clusters — 1× in this paper
• Personalization — 1× in this paper · explained in 2 episodes
• Role-Cognition Boundary — 1× in this paper
• Script-Based Knowledge — 1× in this paper
• Script-Contradictory Knowledge — 1× in this paper
• Self-consistency — 1× in this paper · explained in 2 episodes
• Situational Coherence — 1× in this paper
• Topic Advancement — 1× in this paper

Sources

• Confidence Is All You Need: Few-Shot RL Fine-Tuning of Language Models
• Maximizing Confidence Alone Improves Reasoning
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• RAIDEN-R1: Improving Role-awareness of LLMs via GRPO with Verifiable Reward

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection