arXiv cs.AI· Solim LeGris, Philipp Mondorf, Jinran Jin, Akshay K. Jagadish, Brenden M. Lake, Todd M. Gureckis·· 4 小时前AI 评分46
BCSS 方法规模化合成人类与机器推理的符号模型
Synthesizing symbolic models of human and machine reasoning at scale
AI 导读
arXiv 论文提出行为条件符号合成（BCSS）方法，自动搜索可解释、确定性且可验证复现行为的符号程序，对人类与机器在数百道推理难题上的行为建模。分析显示两者都倾向于过度简化、采用仅部分解释观察的规则并错误推断问题特征间的依赖关系，推理投入量预测机器简化和解释观察的程度。这暗示人类与机器存在类似满意化的机制，BCSS 为比较人类与黑箱 AI 的规则推理提供了通用途径。
正文 · 原文
Abstract:Symbolic models offer a powerful account of cognition, but their scope has historically been limited by the need for hand-engineering and computational tractability. We show how advances in artificial intelligence (AI) can scale symbolic modeling and help overcome these engineering limitations. We introduce Behavior-Conditioned Symbolic Synthesis (BCSS)---an approach for automated search of interpretable, deterministic symbolic programs that verifiably reproduce behavior---and apply it to model both human and machine behavior across hundreds of challenging reasoning problems. Analyzing these programs reveals that both people and machines tend to oversimplify, adopt rules that are partial explanations for their observations, and misinfer dependencies between problem features. These shared signatures are modulated by available resources, with reasoning effort predicting the extent to which machines simplify and explain their observations. Together, these results point to underlying mechanisms reminiscent of satisficing in both people and machines, and illustrate how BCSS offers a general approach for interpreting and comparing rule-based reasoning of humans and black-box AI systems.
| Subjects: | Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2611.07088 [cs.AI] |
| (or arXiv:2611.07088v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.07088 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Solim LeGris [view email]
[v1]
Wed, 4 Nov 2026 19:51:02 UTC (3,269 KB)
来源：arXiv cs.AI · arxiv.org