{"ID":2840347,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.12960","arxiv_id":"2511.12960","title":"ENGRAM: Effective, Lightweight Memory Orchestration for Conversational Agents","abstract":"Large language models (LLMs) deployed in user-facing applications require long-horizon consistency: the ability to remember prior interactions, respect user preferences, and ground reasoning in past events. However, contemporary memory systems often adopt complex architectures such as knowledge graphs, multi-stage retrieval pipelines, and OS-style schedulers, which introduce engineering complexity and reproducibility challenges. We present ENGRAM, a lightweight memory system that organizes conversation into three canonical memory types (episodic, semantic, and procedural) through a single router and retriever. Each user turn is converted into typed memory records with normalized schemas and embeddings and stored in a database. At query time, the system retrieves top-k dense neighbors for each type, merges results with simple set operations, and provides the most relevant evidence as context to the model. ENGRAM attains state-of-the-art results on LoCoMo, a multi-session conversational QA benchmark for long-horizon memory, and exceeds the full-context baseline by 15 points on LongMemEval while using only about 1% of the tokens. These results show that careful memory typing and straightforward dense retrieval can enable effective long-term memory management in language models without requiring complex architectures.","short_abstract":"Large language models (LLMs) deployed in user-facing applications require long-horizon consistency: the ability to remember prior interactions, respect user preferences, and ground reasoning in past events. However, contemporary memory systems often adopt complex architectures such as knowledge graphs, multi-stage retr...","url_abs":"https://arxiv.org/abs/2511.12960","url_pdf":"https://arxiv.org/pdf/2511.12960v2","authors":"[\"Daivik Patel\",\"Shrenik Patel\"]","published":"2025-11-17T04:39:16Z","proceeding":"cs.MA","tasks":"[\"cs.MA\"]","methods":"[\"Large Language Model\",\"Language Model\",\"Generative Adversarial Network\"]","has_code":false}