Jev-Mem: System-One-Controlled Agentic Memory for Efficient AI Agents
Jev-Mem uses a fast System-One controller for agent memory, beating baselines on LoCoMo while cutting latency.
Researchers introduce Jev-Mem, an agentic memory system that separates fast memory control from slower reasoning. A System-One controller manages memory typing, query routing, retrieval budgets, graph traversal, scoring, and stopping, while System Two is reserved for complex reasoning and answer synthesis. On LoCoMo it scores 0.777 under LLM-as-a-Judge, an 11 percent relative gain over the strongest baseline. Memory construction takes 158 seconds, 6.6 times faster than the fastest competitor, and average query latency is 0.93 seconds, down 36.7 percent.
- System-One plane controls construction and retrieval; System Two handles hard reasoning.
- LoCoMo LLM-as-a-Judge score is 0.777, up 11 percent versus the best baseline.
- Memory construction takes 158 seconds, a 6.6-times speedup over the fastest rival.
- Average query latency falls to 0.93 seconds, a 36.7 percent reduction.
Full article177 words · extracted from huggingface.co · click to collapse
Agentic 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 \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 6.6times speedup over the fastest competing memory system, and lowering average query latency to 0.93\,s, a 36.7\% reduction.
Text extracted automatically; images, tables and formatting may be missing. Original: https://huggingface.co/papers/2609.23986