Research map / Large language models / Retrieval and knowledge
RGMem: Renormalization Group–inspired Memory Evolution for Language Agents
Ao Tian, Yunfeng Lu, Xinxin Fan, Changhao Wang, Lanzhi Zhou, Yeyao Zhang, Yanfang Liu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use RGMem multi-scale memory instead of best baseline (Memory OS) | GPT-4.1 backbone · PersonaMem (128k) | average accuracy (%): 65.03 -> 74.01 | Improved |
| Use RGMem instead of best baseline (Memory OS) | GPT-4o-mini backbone · PersonaMem (128k) | average accuracy (%): 56.79 -> 63.87 | Improved |
| Use RGMem instead of Zep | gpt-4o-mini · LOCOMO | average accuracy (%): 75.14 -> 78.92 | Improved |
| Use RGMem instead of Full-Context | gpt-4.1-mini · LOCOMO | average accuracy (%): 87.52 vs 86.17 | No clear effect |
| Use RGMem instead of Full-Context | gpt-4o-mini · LOCOMO | average accuracy (%): 71.41 -> 78.92 | Improved |
| Increase retrieved context from about 3k to beyond 3.8k tokens (ablation) | RGMem · LOCOMO | accuracy | Mixed |
| Move evolution threshold away from 3 (both lower and higher) (ablation) | RGMem · LOCOMO | accuracy | Hurt |
| Move evolution threshold away from 3 (ablation) | RGMem · PersonaMem Latest Preference | accuracy | Hurt |
| Use RGMem instead of Memory OS on open-domain questions | gpt-4o-mini · LOCOMO Open | accuracy (%): 67.71 vs 67.71 | No clear effect |
Closest papers by meaning
- AMemGym: Interactive Memory Benchmarking for Assistants in Long-Horizon Conversations (ICLR 2026 · similarity 0.90)
- MemEvolve: Meta-Evolution of Agent Memory Systems (ICML 2026 · similarity 0.89)
- Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions (ICLR 2026 · similarity 0.88)
- MemGen: Weaving Generative Latent Memory for Self-Evolving Agents (ICLR 2026 · similarity 0.88)
- AMA-Bench: Evaluating Long-Horizon Memory for Agentic Applications (ICML 2026 · similarity 0.88)
- AdaMEM: Test-Time Adaptive Memory for Language Agents (ICML 2026 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
