CalibratedDecisions.

Post · Context & memory

Jev-Mem

A paper on System-One-controlled agentic memory.

Open x.com ↗
Artificial Intelligence Papers @SciFi

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

Dongming Jiang, Yi Li, Bingzhe Li
arxiv.org/abs/2609.23986 [𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙻𝙶] https:/

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 effectiv

The decision Jev makes

Keep or discard a tool result, or answer whether a stopping condition is met.

Where it fits

Agents drown in their own context. These projects use Jev to decide what to keep, what to drop and when a loop is actually finished. All 117 context & memory projects →

Related projects