Research map / Large language models / AI and society
MemoryBench: A Benchmark for Memory and Continual Learning in LLM Systems
Qingyao Ai, Yichen Tang, Changyue Wang, Jianming Long, Weihang Su, Yiqun 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 |
|---|---|---|---|
| add memory systems (A-Mem, Mem0, MemoryOS) instead of RAG | memory-based LLMsys · MemoryBench off-policy | normalized score | No clear effect |
| add memory and feedback logs vs Vanilla | memory-based LLMsys · MemoryBench (most partitions) | normalized score | Improved |
| add memory systems on SiLo partition | memory-based LLMsys · MemoryBench SiLo | normalized score | Hurt |
| use memory systems on Locomo only | A-Mem, Mem0, MemoryOS · Locomo | original metric | Improved |
| add simulated user feedback to Vanilla | Vanilla Qwen3-8B · MemoryBench | task performance | Improved |
| use action feedback (like, copy) instead of verbal feedback | memory-based LLMsys · MemoryBench | normalized score | No clear effect |
Closest papers by meaning
- Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions (ICLR 2026 · similarity 0.89)
- Minerva: A Programmable Memory Test Benchmark for Language Models (ICML 2025 · similarity 0.89)
- Continual Learning Bench: Evaluating Frontier AI Systems in Real-World Stateful Environments (NeurIPS 2026 · similarity 0.89)
- From RAG to Memory: Non-Parametric Continual Learning for Large Language Models (ICML 2025 · similarity 0.88)
- CMT: A Memory Compression Method for Continual Knowledge Learning of Large Language Models (AAAI 2025 · similarity 0.88)
- CoIN: A Benchmark of Continual Instruction Tuning for Multimodel Large Language Models (NeurIPS 2024 · 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.
