Author

Cheng Yang

h-index 7 View on Semantic Scholar

We have 1 of 32 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Jan 2026

Beyond Static Summarization: Proactive Memory Extraction for LLM Agents

ProMem is proposed, a proactive memory extraction framework that separates details, events, and relations, and uses different extraction strategies for each type, and improves memory completeness and QA accuracy, while keeping a good balance between quality and token cost.

Cheng Yang, Zequn Sun, Wei Wei et al. · arXiv.org · 16 citations