Autonomous AI Agents Systematically Diverge From Human Preferences in Proof Formalization
中文摘要
研究显示自主AI在证明形式化中偏离人类偏好,揭示了两者在语法和语义关注点上的系统性差异。
English Summary
Autonomous AI agents systematically diverge from human preferences in proof formalization, exhibiting different priorities regarding syntax and underlying semantics during collaboration.
arXiv:2611.06995v1 Announce Type: new Abstract: Artificial intelligence (AI) systems have ushered in a new age of proof abundance, but helping humans understand these proofs requires new attention to the differences in how AI agents and humans pursue a proof-making task. We present "simulated collaboration", a methodology that allows us to examine two key questions: (1) the relative attention AI agents pay to surface syntax or, conversely, deeper underlying semantics, and (2) how and where AI agent preferences for what to do next diverge from human preferences. On a set of nine major human collaborations in Lean with 4.7M definitions across more than 6K commits, we find that, over the course of proof construction, AI agents (1) are far more strongly drawn than humans to explicitly marked gaps; (2) show a relative aversion to densely connected proof centers and to complex or surprising proof goals; and (3) are relatively attracted to surprising proof bodies, which they tend to regularize toward baseline. Our results highlight important blind spots and potential interventions for future human-AI collaboration in mathematics.