4 papers
LiveMem: Maintaining Memory State Continuity in Long-Running LLM Inference
Zhichen Liu, Ruihan Sun, Hengjie Yang +4
Long-running assistants and agents consume interaction streams that eventually outgrow the context. Existing context retention, summarization, and retrieval preserve access to sele…
MICA: Multi-granularity Intertemporal Credit Assignment for Long-Horizon Emotional Support Dialogue
Naifan Zhang, Ruihan Sun, Jinwei Su +4
Reinforcement learning (RL) for large language models (LLMs) has shown strong performance in single-turn tasks, but extending it to multi-turn interaction remains challenging due t…
EMPA: Evaluating Persona-Aligned Empathy as a Process
Shiya Zhang, Yuhan Zhan, Ruixi Su +4
Evaluating persona-aligned empathy in LLM-based dialogue agents remains challenging. User states are latent, feedback is sparse and difficult to verify in situ, and seemingly suppo…
Echo-N1: Affective RL Frontier
Naifan Zhang, Ruihan Sun, Ruixi Su +9
The LLM field has spent a year perfecting RL for tasks machines already excel at, math, code, and deterministic reasoning, while completely sidestepping the domain that actually de…