3 papers
cs.AI2026
Interactive Memory Learning for Long-Term Conversations
Cai Ke, Jiangyue Yan, Han Zhang +5
Recent advancements in large language models have significantly enhanced the capabilities of agents in modeling long-term conversations. Despite these successes, existing approache…
cs.AI2026
ThinkFlow: Self-Evolving Probabilistic Latent Memory for Lifelong Conversational Agents
Cai Ke, Xin Liu, Han Zhang +6
Lifelong conversational agents rely on memory systems to maintain deep, context-aware interactions with users. However, existing explicit textual memory pipelines suffer from a sev…
cs.LG2025
GEPO: Group Expectation Policy Optimization for Stable Heterogeneous Reinforcement Learning
Han Zhang, Ruibin Zheng, Zexuan Yi +16
As single-center computing approaches power constraints, decentralized training becomes essential. However, traditional Reinforcement Learning (RL) methods, crucial for enhancing l…