让大模型对话更稳定，用概念状态替代历史文本
CORE: A Conceptual Reasoning Layer for Large Language Models
- 用持久的概念状态取代反复输入历史，实现概念优先交互
- 原型测试显示累计提示词减少约42%
- 无需修改模型权重，适合各类大模型的多轮对话优化
大语言模型在单轮生成上表现良好，但在多轮交互中仍需从不断增长的令牌历史中重建用户意图和任务状态，因为内部表示无法跨轮次持续。这种以令牌为中心的范式导致意图漂移、推理模式不一致以及提示词持续膨胀。我们提出CORE——一种概念优先的交互层，可在不修改模型权重的情况下提升多轮稳定性。CORE结合一个小型通用认知操作符库与一个持久的局部概念（Local Concept），该概念以紧凑语义状态捕捉任务、约束、偏好及中间结果。每次模型调用仅接收此概念状态、用户的最新指令及所选操作符，无需重播完整历史。初步原型模拟显示累计提示词减少约42%，但该数据反映原型条件，不可作为真实性能估计。CORE提供了一种与模型无关的机制，将概念推理与语言生成解耦，为更稳定的多轮系统提供了可扩展方向。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。