Accurate and Efficient Long-Term Memory for LLM Agents

Researchers introduce MOSAIC (Memory-Organized Structured Agent for Information Collection), a structured, conflict-aware long-term memory framework for LLM agents that achieves 89.35% accuracy on the LoCoMo benchmark, 27.21 percentage points higher than the best baseline, while reducing search latency to 0.58 seconds per question through hash-accelerated retrieval. The framework also detects 66% of injected factual conflicts, 4.7 times more than the best baseline, by cross-referencing new information against existing graph neighbors at save time.

arXiv:2607.16211v1 Announce Type: new Abstract: LLM agents augmented with persistent memory can recall past interactions, but existing systems suffer from two limitations: flat, unstructured storage loses relational context needed for multi-hop and temporal reasoning, and reliance on expensive LLM-based classification makes them impractical for latency-sensitive deployment. Without mechanisms to validate new information against stored knowledge, these systems silently accumulate contradictions. We present MOSAIC Memory-Organized Structured Agent for Information Collection , a structured, conflict-aware long-term memory framework for LLM agents that is substantially more accurate and efficient. MOSAIC introduces three key capabilities: 1 entity-typed graph storage with semantic classification preserving relational structure across events, personas, and relationships, enabling multi-hop and temporal reasoning over conversation history; 2 hash-accelerated dual-path retrieval replacing LLM-based classification with locality-sensitive hashing, achieving near-instantaneous lookup with negligible accuracy loss; and 3 active conflict detection at save time that cross-references new information against existing graph neighbors, triggering updates or deletions for contradictory entries. Evaluated on LoCoMo long-conversation QA , HaluMem, and a novel clinical-guideline error compounding test, MOSAIC achieves 89.35% accuracy on LoCoMo +27.21 pp over the best baseline , best HaluMem-Medium extraction F1 86.77% and HaluMem-Long extraction F1 85.84% , best QA correctness on both Medium and Long 73.10%, 70.75% , and detects 66% of injected factual conflicts-4.7 times higher than the best baseline 14% -while hash-accelerated retrieval keeps average search latency at 0.58 s per question.