Large language models handle single-turn generation well, but multi-turn interactions still require the model to reconstruct user intent and task state from an expanding token history because internal representations do not persist across turns. This token-first paradigm leads to drift, inconsistent reasoning modes, and growing prompts as conversations deepen. We propose CORE, a concept-first interaction layer that improves multi-turn stability without modifying model weights. CORE combines a small library of universal cognitive operators with a persistent Local Concept - a compact semantic state capturing the task, constraints, preferences, and intermediate results. Each model call receives only this concept state, the user's latest instruction, and the selected operator, eliminating the need to replay full history. A preliminary prototype simulating CORE's behavior shows about 42% reduction in cumulative prompt tokens, though this number reflects prototype conditions and should not be interpreted as a real-world performance estimate. CORE offers a model-agnostic mechanism that separates conceptual reasoning from language generation, suggesting a scalable direction for more stable multi-turn systems.

翻译：大语言模型在单轮生成任务中表现良好，但在多轮交互中，由于内部表示无法跨轮次持续存在，模型仍需从不断增长的令牌历史中重构用户意图与任务状态。这种以令牌为先的范式会导致对话深入时出现意图漂移、推理模式不一致以及提示词膨胀等问题。本文提出CORE——一种不修改模型权重的概念优先交互层，旨在提升多轮对话的稳定性。CORE将小型通用认知算子库与持久化的局部概念相结合，后者作为紧凑的语义状态，捕获任务、约束条件、用户偏好及中间结果。每次模型调用仅接收该概念状态、用户最新指令及所选算子，无需回放完整历史记录。模拟CORE行为的初步原型显示累计提示令牌量减少约42%，但该数值仅反映原型测试条件，不应视为实际性能指标。CORE提供了一种与模型无关的机制，将概念推理与语言生成分离，为构建更稳定的多轮对话系统指明了可扩展的技术路径。