From the 2 of 5 linked papers with an AI index.
5 papers
Metis: Memory Foundation Model
Zeyu Zhang, Ziliang Guo, Yihang Sun +14
The paper presents Metis, a memory foundation model that embeds a persistent, dynamically updated memory state within the model backbone, allowing it to store and retrieve informat…
MemOps: Benchmarking Lifecycle Memory Operations in Long-Horizon Conversations
Xixuan Hao, Zeyu Zhang, Zehao Lin +6
The paper introduces MemOps, a benchmark that evaluates long‑term conversational memory by tracking explicit lifecycle operations (remember, forget, update, etc.) rather than only…
-Bench: Evaluating Persona-Sensitive Influencing in Persuasive Dialogues
Peixuan Han, Hongyi Du, Jiayu Liu +3
Personalization is a crucial capability of modern language agents. However, current research primarily positions personalized agents as passive responders to user preferences, limi…
GMTRouter: Personalized LLM Router over Multi-turn User Interactions
Encheng Xie, Yihang Sun, Tao Feng +1
Large Language Model (LLM) routing has demonstrated strong capability in balancing response quality with computational cost. As users exhibit diverse preferences, personalization h…
GraphEval: A Lightweight Graph-Based LLM Framework for Idea Evaluation
Tao Feng, Yihang Sun, Jiaxuan You
The powerful capabilities of Large Language Models (LLMs) have led to their growing use in evaluating human-generated content, particularly in evaluating research ideas within acad…