用自动对抗协作框架在计算机中验证认知理论，无需预先设定模型和实验。
Automated Adversarial Collaboration for Advancing Theory Building in the Cognitive Sciences
- 通过大模型代理、程序合成与信息论实验设计闭环运行
- 在三类经典分类理论中成功识别出真实理论，噪声下仍有效
- 适合想用自动化方法推动理论竞争的认知科学学者
认知科学常通过狭窄范式和局部模型比较评估理论，限制了跨任务与实现方式的证据整合。我们提出一种自动对抗协作框架，可在候选模型与实验需在评判过程中发现时，对竞争性理论进行裁决。该系统结合大语言模型驱动的理论代理、程序合成与信息论实验设计，在闭环中运行。在涵盖三个经典分类理论的模拟研究中，该框架在不同噪声条件下均恢复出真实理论，仅在最困难设置下可靠性下降。研究结果为认知科学中的闭环、虚拟理论裁决提供了切实可行的概念验证。
原文摘要 · Abstract (English)
Cognitive science often evaluates theories through narrow paradigms and local model comparisons, limiting the integration of evidence across tasks and realizations. We introduce an automated adversarial collaboration framework for adjudicating among competing theories even when the candidate models and experiments must be discovered during the adjudication process. The system combines LLM-based theory agents, program synthesis, and information-theoretic experimental design in a closed loop. In a simulation study spanning three classic categorization theories, the framework recovered the ground-truth theory across noise settings with weaker reliability in the hardest settings. Together, the framework and findings provide a concrete proof of concept for closed-loop, in-silico theory adjudication in cognitive science.
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。