The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
The paper investigates how autonomous AI agents differ from humans in proof formalization tasks. Using a method called "simulated collaboration," the authors analyze nine major Lean collaborations involving 4.7 million definitions. They find that AI agents focus more on explicitly marked gaps, avoid densely connected proof centers and complex or surprising goals, yet are attracted to surprising proof bodies, which they tend to regularize toward a baseline.
arXiv:2608.28433v2 Announce Type: replace Abstract: Proof assistants such as Lean 4 promise the paradigm of formally verified mathematics, but large-scale formalization projects have faced major barr...
arXiv:2606. 04273v2 Announce Type: replace Abstract: For centuries, human mathematicians have written proofs to substantiate their mathematical arguments; yet, the ability to automatically verify the validity of proofs has long been a challenge.
arXiv:2603. 02668v2 Announce Type: replace Abstract: We present SorryDB, a dynamically-updating benchmark of open Lean tasks drawn from 78 real world formalization projects on GitHub.
arXiv:2606. 04273v1 Announce Type: new Abstract: For centuries, human mathematicians have written proofs to substantiate their mathematical arguments; yet, the ability to automatically verify the validity of proofs has long been a challenge.
arXiv:2607. 14582v1 Announce Type: new Abstract: Existing LLM-based theorem provers have achieved impressive results on formal mathematics benchmarks, yet they remain confined to acting as autonomous agents that prove a stated proposition.