2 papers
cs.AI2026
What Deserves Memory: Adaptive Memory Distillation for LLM Agents
Wenquan Ma, Jiayan Nan, Wenlong Wu +1
Memory systems for LLM agents struggle to determine what information deserves retention. Existing approaches rely on predefined heuristics such as importance scores, emotional tags…
cs.CL2025
Omne-R1: Learning to Reason with Memory for Multi-hop Question Answering
Boyuan Liu, Feng Ji, Jiayan Nan +4
This paper introduces Omne-R1, a novel approach designed to enhance multi-hop question answering capabilities on schema-free knowledge graphs by integrating advanced reasoning mode…