Banger report on building faster memory for AI Agents. If your agent’s memory layer is slow, this design is worth a look. Great weekend read. It proposes a new agentic memory architecture, Jev-Mem, inspired by System-One/System-Two cognition. This builds agent memory 6.6x faster and cuts query latency by 36.7% while scoring higher on LoCoMo. In this system, a lightweight controller makes the memory decisions. It assigns memory types and relations when storing, and handles routing, retrieval budget, graph traversal, scoring and stopping when reading. The LLM is called only for final reasoning and answer writing. On LoCoMo, it scores 0.777 overall with an LLM judge, an 11.0% relative improvement over the strongest baseline. Memory construction takes 158 seconds, and average query latency drops to 0.93 seconds. Paper: https://academy.dair.ai/papers/jev-mem-system-one-controlled-agentic-memory-for-efficient-ai-agents-2609.23986…

Jev-Mem: System-One-Controlled Agentic Memory for Efficient AI Agents

Source: https://academy.dair.ai/papers/jev-mem-system-one-controlled-agentic-memory-for-efficient-ai-agents-2609.23986 Agents · Memory · ReasoningChat with Paper

First page

The curator’s take

Dongming Jiang, Yi Li and Bingzhe Li (UT Dallas) build Jev-Mem, an agent memory system that hands memory organization and retrieval control to a lightweight System-One controller and calls an LLM only for final reasoning.

Ask this paper

Question about this paper Key points01

Three planes. A System-One control plane, a structured multi-relational memory plane and a System-Two reasoning plane split fast control from slow deliberation.

02

What the controller does. It assigns memory types and relations during construction and handles query routing, retrieval budget, graph traversal, candidate scoring and adaptive stopping during retrieval.

03

LLM off the critical path. System Two runs only for complex reasoning and answer synthesis, so memory operations no longer wait on autoregressive generation.

04

Accuracy. On LoCoMo it scores 0.777 overall with an LLM judge, an 11.0% relative improvement over the strongest baseline.

05

Speed. Memory construction takes 158 s, 6.6x faster than the fastest competing system, and average query latency drops 36.7% to 0.93 s.

AbstractAgentic memory is becoming essential for long-horizon AI agents, yet many existing systems rely on autoregressive LLMs to control how memories are organized, retrieved, and used, placing expensive generation on the critical path of memory operations. We introduce \textbf{\method}, a new agentic memory architecture inspired by System-One/System-Two cognition. System One captures fast, lightweight decision-making, whereas System Two performs slower, deliberative reasoning. Jev-Mem brings this division of labor to agentic memory through a dedicated System-One control plane, a structured multi-relational memory plane, and a System-Two reasoning plane. The System-One controller governs memory typing and relational organization during construction, and dynamically performs query routing, retrieval-budget allocation, graph traversal, candidate scoring, and adaptive stopping during retrieval. System Two is invoked only for complex reasoning and answer synthesis. This design improves both memory effectiveness and system efficiency: on LoCoMo Jev-Mem achieves an overall LLM-as-a-Judge score of 0.777, an 11.0\% relative improvement over the strongest baseline, while reducing memory construction time to 158\,s, a 6.6\\times speedup over the fastest competing memory system, and lowering average query latency to 0.93\,s, a 36.7\% reduction.