Observation record / arXiv · 人工智能

MemComposer: Learning to Assemble Memories for LLM Agents via Reinforcement Learning

First seen 10/17, 04:20 · Last observed 10/18, 10:21 · Source data is current

Title-based outlineMemComposer: Learning to Assemble Memories for LLM Agents via Reinforcement Learning

Why it mattersResearch metadata links to papers and authors. Read the original for conclusions; publication order is not impact.

Published 10/17, 12:00

30 minutesRank movement—

Building history

1 hourRank movement—

Building history

24 hoursRank movement—

Building history

Publication position history

6 observations

Publication feed in source order. Position changes do not count as heat or momentum.

arXiv metadata CC0; papers retain individual licenses· Author Yixuan Xie, Xueqiang Xu, Xinyi Fan, Xinxi Lyu, Tao Feng, Xing Fan, Chenlei Guo, Jie Hao, Shaowen Wan

View original observation times and ranks

Observation time (Beijing)	Source position
10/18, 10:21	35
10/18, 04:21	35
10/17, 22:21	35
10/17, 16:21	35
10/17, 10:20	35
10/17, 04:20	35

Daily aggregate history

日期	Best daily position	Last daily position	Observations
2026-10-17	35	35	4
2026-10-18	35	35	2