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

Papers with Code Trending Papers
semantic-memory agent-memory information-theoretic-retrieval vector-only long-horizon-agents retrieval llm

Summary

Memanto introduces a typed semantic memory system using a schema, conflict resolution, and Moorcheh's information-theoretic retrieval engine, achieving state-of-the-art results on LongMemEval and LoCoMo benchmarks with zero ingestion cost and sub-90ms latency.

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.
Original Article
View Cached Full Text

Cached at: 06/05/26, 02:06 PM

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

Source: https://huggingface.co/papers/2604.22085 Memanto challenges the assumption that knowledge graphs are necessary for high-quality agent memory. Using a typed semantic schema, built-in conflict resolution, and Moorcheh’s information-theoretic retrieval engine, we achieve 89.8% on LongMemEval and 87.1% on LoCoMo, SOTA among vector-only systems, with zero ingestion cost, single-query retrieval, and sub-90ms latency. The core finding: recall beats precision, and LLMs are better filters than pre-computed graph structures.

Try it: pip install memanto

memanto-gif

Similar Articles

T-Mem: Memory That Anticipates, Not Archives

arXiv cs.CL

T-Mem is a new long-term conversational memory architecture that enables both descriptive and associative recall, covering scenarios where query and memory share surface features and those where they are connected by latent semantic arcs. It reaches state-of-the-art on the LoCoMo and LoCoMo-Plus benchmarks.

AdMem: Advanced Memory for Task-solving Agents

arXiv cs.AI

This paper introduces AdMem, a unified memory framework for LLM-based agents that integrates semantic, episodic, and procedural memory with a bi-level short-term and long-term store, using a multi-agent architecture for automatic memory generation and adaptive retrieval. Experiments show improved robustness and success on long multi-turn tasks.

Accurate and Efficient Long-Term Memory for LLM Agents

arXiv cs.AI

MOSAIC is a structured, conflict-aware long-term memory framework for LLM agents that uses entity-typed graph storage, hash-accelerated retrieval, and active conflict detection to achieve high accuracy and efficiency on long-conversation QA and factual conflict detection tasks.