Memanto: Typed Semantic Memory with Information-Theoretic Retrieval for Long-Horizon Agents

2026-04-23

AI Summary

This work addresses the limitations of existing agent memory systems, which rely on complex semantic graphs and incur high computational overhead and latency, hindering long-term, multi-session deployment. To overcome these challenges, the authors propose Memanto, a universal memory layer that eschews traditional knowledge graph assumptions in favor of thirteen predefined memory types, automated conflict resolution, and temporal versioning. Coupled with an information-theoretic, index-free retrieval engine, Memanto achieves, for the first time, zero ingestion latency and high-fidelity memory recall within a single query. Evaluated on the LongMemEval and LoCoMo benchmarks, Memanto attains accuracies of 89.8% and 87.1%, respectively, substantially outperforming current hybrid graph- and vector-based systems while significantly reducing operational complexity.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Modeling other Agents
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Agentic search
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

The transition from stateless language model inference to persistent, multi session autonomous agents has revealed memory to be a primary architectural bottleneck in the deployment of production grade agentic systems. Existing methodologies largely depend on hybrid semantic graph architectures, which impose substantial computational overhead during both ingestion and retrieval. These systems typically require large language model mediated entity extraction, explicit graph schema maintenance, and multi query retrieval pipelines. This paper introduces Memanto, a universal memory layer for agentic artificial intelligence that challenges the prevailing assumption that knowledge graph complexity is necessary to achieve high fidelity agent memory. Memanto integrates a typed semantic memory schema comprising thirteen predefined memory categories, an automated conflict resolution mechanism, and temporal versioning. These components are enabled by Moorcheh's Information Theoretic Search engine, a no indexing semantic database that provides deterministic retrieval within sub ninety millisecond latency while eliminating ingestion delay. Through systematic benchmarking on the LongMemEval and LoCoMo evaluation suites, Memanto achieves state of the art accuracy scores of 89.8 percent and 87.1 percent respectively. These results surpass all evaluated hybrid graph and vector based systems while requiring only a single retrieval query, incurring no ingestion cost, and maintaining substantially lower operational complexity. A five stage progressive ablation study is presented to quantify the contribution of each architectural component, followed by a discussion of the implications for scalable deployment of agentic memory systems.

Problem

• agent memory
• semantic memory
• knowledge graph
• information retrieval
• long-horizon agents

Innovation

• typed semantic memory
• information-theoretic retrieval
• agent memory
• no-indexing semantic database
• temporal versioning