AtomMem: Building Simple and Effective Memory System for LLM Agents via Atomic Facts
- Published
- Source
- arXiv
- Paper number
- 460
- Field
- LLMs / NLP
- arXiv ID
- 2606.19847
Key points
- Fact Executor: A lightweight SFT-tuned LLM extracts only the core information from raw conversations as atomic facts, using Qwen3-14B with LoRA rank 128.
- Hierarchical memory structure: It organizes atomic facts into event memory for context and temporal profiles for tracking user state.
- Association memory graph: Retrieval uses entity duplication, shared events, and conversation continuity to connect fragmented memories.
- On the LoCoMo benchmark's Multi-Hop J-score, it improves by 31.1% over LightMem and reduces tokens by 61.4% versus Mem0.
- Even the simple flat variant, AtomMem-Flat, improves Multi-Hop F1 from 20.97 to 37.03, a 76.6% gain over the baseline, showing that memory representation quality is the key.
- The retrieval parameter k_f = 10 is the best balance of accuracy, cost, and latency, while k > 20 hurts performance because of noise.
Paper links
External research summaries. These are not HDATF publications or measured product results.