5 papers
MemPO: Self-Memory Policy Optimization for Long-Horizon Agents
Ruoran Li, Xinghua Zhang, Haiyang Yu +7
Long-horizon agents face the challenge of growing context size during interaction with environment, which degrades the performance and stability. Existing methods typically introdu…
TemplateRL: Structured Template-Guided Reinforcement Learning for LLM Reasoning
Jinyang Wu, Chonghua Liao, Mingkuan Feng +6
Reinforcement learning (RL) has emerged as an effective paradigm for enhancing model reasoning. However, existing RL methods like GRPO typically rely on unstructured self-sampling…
MOA: Multi-Objective Alignment for Role-Playing Agents
Chonghua Liao, Ke Wang, Yuchuan Wu +3
Role-playing agents (RPAs) require balancing multiple objectives, such as instruction following, persona consistency, and stylistic fidelity, which are not always perfectly aligned…
SSL: Sweet Spot Learning for Differentiated Guidance in Agentic Optimization
Jinyang Wu, Changpeng Yang, Yuhao Shen +9
Reinforcement learning with verifiable rewards has emerged as a powerful paradigm for training intelligent agents. However, existing methods typically employ binary rewards that fa…
Entropy Regularizing Activation: Boosting Continuous Control, Large Language Models, and Image Classification with Activation as Entropy Constraints
Zilin Kang, Chonghua Liao, Tingqiang Xu +1
We propose ERA, a new paradigm that constrains the sampling entropy above given thresholds by applying specially designed activations to the outputs of models. Our approach demonst…