CogMem: A Cognitive Memory Architecture for Sustained Multi-Turn Reasoning in Large Language Models
This addresses the issue of unreliable reasoning in LLMs for extended tasks, though it appears incremental as it builds on existing memory-augmented approaches.
The paper tackles the problem of large language models losing accuracy and coherence in multi-turn interactions by introducing CogMem, a memory-augmented architecture that mitigates reasoning failures and controls context growth, as shown in experiments on TurnBench.
Large language models (LLMs) excel at single-turn reasoning but often lose accuracy and coherence over extended, multi-turn interactions. Recent evaluations such as TurnBench highlight recurring failure modes-reasoning bias, task drift, hallucination, overconfidence, and memory decay. Current approaches typically append full conversational histories, causing unbounded context growth, higher computational costs, and degraded reasoning efficiency. We introduce CogMem, a cognitively inspired, memory-augmented LLM architecture that supports sustained iterative reasoning through structured, persistent memory. CogMem incorporates three layers: a Long-Term Memory (LTM) that consolidates cross-session reasoning strategies; a Direct Access (DA) memory that maintains session-level notes and retrieves relevant long-term memories; and a Focus of Attention (FoA) mechanism that dynamically reconstructs concise, task-relevant context at each turn. Experiments on TurnBench show that this layered design mitigates reasoning failures, controls context growth, and improves consistency across extended reasoning chains, moving toward more reliable, human-like reasoning in LLMs.