5 papers
Mind2Dialogue: Training Human-Aware Language Models by Simulating User Mental States
Zixuan Wang, Yufan Zhou, Jinzhou Tang +16
As language models become more capable, long-term collaboration in learning, reasoning, and decision-making calls for a deeper understanding of the people they serve. Yet training…
TokenPilot: Cache-Efficient Context Management for LLM Agents
Buqiang Xu, Zirui Xue, Dianmou Chen +12
As LLM agents are deployed in long-horizon sessions, context accumulation drives up inference costs. Existing approaches utilize text pruning or dynamic memory eviction to minimize…
Tuning LLMs by RAG Principles: Towards LLM-native Memory
Jiale Wei, Shuchi Wu, Ruochen Liu +3
Memory, additional information beyond the training of large language models (LLMs), is crucial to various real-world applications, such as personal assistant. The two mainstream so…
AI-native Memory 2.0: Second Me
Jiale Wei, Xiang Ying, Tao Gao +3
Human interaction with the external world fundamentally involves the exchange of personal memory, whether with other individuals, websites, applications, or, in the future, AI agen…
AI-native Memory: A Pathway from LLMs Towards AGI
Jingbo Shang, Zai Zheng, Jiale Wei +3
Large language models (LLMs) have demonstrated the world with the sparks of artificial general intelligence (AGI). One opinion, especially from some startups working on LLMs, argue…