Vibe Compiler：无需提示工程即可运行的研究逻辑综合工具——迈向生成式AI时代维持智能体的元认知
Vibe Compiler: A Research-Logic Synthesis Tool That Runs without Prompt Engineering -Toward Enhancing Metacognition for Sustaining Agency in the Age of Generative AI-
浏览论文内容
中文总结 AI 辅助
针对生成式AI可能侵蚀人类认知智能体的问题，提出基于综合-分析互惠模型的Vibe Compiler工具，通过16个学术参数的本体编译研究想法，以反思性问题引导研究人员，减少对复杂提示的依赖，提升AI辅助推理效果。
中文摘要 AI 辅助
将生成式AI用作得力助手极大加速了智力工作，但它也可能因鼓励不加批判地接受AI生成的推理而侵蚀人类认知智能体。这就需要在AI辅助智力工作中通过增强元认知来保留人类智能体的机制。为解决该问题，我们提出了综合-分析互惠模型，该模型将智力构建视为综合与分析之间的互惠互动：综合是将组件组合成人工制品，分析是根据客观指标对其进行批判性评估并约束后续综合。基于该模型，我们提出了Vibe Compiler，这是一种研究逻辑编译器，可帮助研究人员将模糊想法（Vibes）转化为连贯的研究逻辑。该系统使用包含16个学术参数的研究论文本体来编译这些想法。编译失败表明存在缺失的逻辑组件；系统不会自动填充这些组件，而是向研究人员提出反思性问题，鼓励他们完善缺失的推理。该框架从两个维度表征结构缺口：认知功能（综合vs.分析）和执行智能体（人类vs.AI），从而产生四种起源类型，用于识别故障发生的位置。我们的设计强调AI探查自身生成的输出以刺激人类元认知，鼓励研究人员作为管理者批判性地指导和验证AI生成的推理，而非被动接受者。基于NotebookLM和Gemini构建的原型经验表明，有效的AI辅助推理对复杂提示的依赖程度低于为AI提供的知识结构。本文正是使用所提出的Vibe Compiler开发的。
英文摘要
Used as a capable servant, generative AI has greatly accelerated intellectual work, yet it also risks eroding human epistemic agency by encouraging uncritical acceptance of AI-generated reasoning. Preserving that agency calls for mechanisms that augment human metacognition during AI-assisted work. We therefore propose the Synthesis-Analysis Reciprocity Model, which views intellectual construction as a reciprocal interaction between two cognitive functions. Synthesis selects and combines the components of the artifact; Analysis evaluates them critically against objective indicators and constrains the Synthesis that follows. Grounded in this model, we present the Vibe Compiler, a research-logic compiler that helps researchers turn vague intuitions (Vibes) into coherent research logic. The system attempts to compile those intuitions against a paper ontology of 16 academic parameters. It treats compilation failures as signs that logical components are missing. Rather than fill those gaps autonomously, it returns reflective questions that prompt researchers to develop the missing reasoning themselves. We further characterize the origins of structural gaps along two orthogonal dimensions: cognitive function (Synthesis versus Analysis) and executing agent (human versus AI). The four resulting types of origin give a principled way to identify where breakdowns in intellectual construction arise. Crucially, our design implements the type in which the AI probes its own synthesized output, itself driven by the user's Vibes, and thereby stimulates human metacognition. This choice raises researchers from passive "Makers" of the output into "Managers" who critically direct and validate what the AI produces. In a prototype on NotebookLM and Gemini, AI behavior depended less on prompting than on the structure of the knowledge supplied. The framework spans a learner layer and a researcher layer.
