# Amory: Building Coherent Narrative-Driven Agent Memory through Agentic Reasoning Source: [Amory: Building Coherent Narrative-Driven Agent Memory through Agentic Reasoning]() Collection index: [llms.txt]() Data updated: 2026-01-14T05:00:04.658Z Authors: Yue Zhou, Xiaobo Guo, Belhassen Bayar, Srinivasan H. Sengamedu Published: 2026-01-09T19:51:11.000Z ## Abstract Long-term conversational agents face a fundamental scalability challenge as interactions extend over time: repeatedly processing entire conversation histories becomes computationally prohibitive. Current approaches attempt to solve this through memory frameworks that predominantly fragment conversations into isolated embeddings or graph representations and retrieve relevant ones in a RAG style. While computationally efficient, these methods often treat memory formation minimally and fail to capture the subtlety and coherence of human memory. We introduce Amory, a working memory framework that actively constructs structured memory representations through enhancing agentic reasoning during offline time. Amory organizes conversational fragments into episodic narratives, consolidates memories with momentum, and semanticizes peripheral facts into semantic memory. At retrieval time, the system employs coherence-driven reasoning over narrative structures. Evaluated on the LOCOMO benchmark for long-term reasoning, Amory achieves considerable improvements over previous state-of-the-art, with performance comparable to full context reasoning while reducing response time by 50%. Analysis shows that momentum-aware consolidation significantly enhances response quality, while coherence-driven retrieval provides superior memory coverage compared to embedding-based approaches. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Constraint Recall on AGENTIF long-horizon agentic conversations](): Constraint Recall; AGENTIF long-horizon agentic conversations; Constraint Recall: 47.4. - [Long-context reasoning and retrieval on LoCoMo (test)](): Long-context reasoning and retrieval; LoCoMo (test); Single-Hop F1: 89. ## Original sources and implementation [Original paper]() [PDF]()