Showing cs.AIShow all
3 papers · 1 filter
cs.AI2026
ConvMem: Convolutional Memory for Long-Context Reasoning
Hongming Zhang, Zhaozhen Gu, Fengshuo Bai +6
While Large Language Models (LLMs) have demonstrated impressive capabilities, they often struggle with extremely long contexts due to fixed context limits. To address this, sequent…
cs.AI2026
HyMem: Hierarchical Context Management for Long-Horizon Agents via Information Isolation
XinQi Wang, Jinwei Xiao, Sijia Cui +4
Large language model (LLM) agents often perform poorly on complex, long-horizon tasks because their context becomes increasingly cluttered over time. As interactions accumulate, de…
cs.AI2025
Coarse-to-Fine Grounded Memory for LLM Agent Planning
Wei Yang, Jinwei Xiao, Hongming Zhang +3
Recent advancements in Large Language Models (LLMs) have driven growing interest in LLM-based agents for complex planning tasks. To avoid costly agent training, many studies adopte…