{"slug": "accurate-and-efficient-long-term-memory-for-llm-agents", "title": "Accurate and Efficient Long-Term Memory for LLM Agents", "summary": "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.", "body_md": "arXiv:2607.16211v1 Announce Type: new\nAbstract: 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.", "url": "https://wpnews.pro/news/accurate-and-efficient-long-term-memory-for-llm-agents", "canonical_source": "https://arxiv.org/abs/2607.16211", "published_at": "2026-07-21 04:00:00+00:00", "updated_at": "2026-07-21 04:07:26.153308+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-agents", "ai-research"], "entities": ["MOSAIC", "LoCoMo", "HaluMem"], "alternates": {"html": "https://wpnews.pro/news/accurate-and-efficient-long-term-memory-for-llm-agents", "markdown": "https://wpnews.pro/news/accurate-and-efficient-long-term-memory-for-llm-agents.md", "text": "https://wpnews.pro/news/accurate-and-efficient-long-term-memory-for-llm-agents.txt", "jsonld": "https://wpnews.pro/news/accurate-and-efficient-long-term-memory-for-llm-agents.jsonld"}}