Search papers, labs, and topics across Lattice.
This paper introduces MemCog, a novel memory system for conversational agents that integrates memory access directly into the reasoning process. MemCog uses a Navigable Memory Store with associative link graphs and a Cross-Dimensional Navigation Interface to enable multi-step, reasoning-driven memory traversal. The system proactively initiates memory exploration from conversational context, leading to state-of-the-art performance on both passive QA benchmarks and a newly introduced benchmark for proactive memory triggering.
Conversational agents can achieve superior memory recall and reasoning by treating memory as an active cognitive component rather than a passive tool.
Existing agent memory systems universally follow what we term a Memory-as-Tool paradigm where a single query triggers one-shot retrieval of flat passage lists, suffering from passive invocation, reasoning-retrieval decoupling, and structural mismatch between retrieved fragments and the agent's navigational needs. We propose MemCog, a Memory-as-Cognition system that makes memory access an integral part of the reasoning process. MemCog organizes user knowledge as Navigable Memory Store with associative link graphs, exposes Cross-Dimensional Navigation Interface for multi-step reasoning-driven traversal, and employs Proactive Reasoning Protocol that drives agents to spontaneously initiate memory exploration from conversational context. We additionally construct ProactiveMemBench, the first benchmark for evaluating proactive memory triggering. Experiments show that MemCog achieves state-of-the-art on passive QA benchmarks (92.98 on LoCoMo, 95.8 on LongMemEval) while substantially outperforming baselines on ProactiveMemBench, demonstrating the advantage of Memory-as-Cognition.
