An In-Context Learning Agent for Formal Theorem-Proving — mentioned by ekez

Wed, 30 Apr 2025 18:22:11 GMT

I wonder if the authors have tried incorporating error feedback from Lean into their models. Work from 2023 [1] showed general purpose models did better when they were able to incorporate error feedback, humans incorporate error feedback, but none of the SOTA models on minif2f seem to. [1]: https://arxiv.org/abs/2310.04353

Paper and discussion history. A mention is not an endorsement.

An In-Context Learning Agent for Formal Theorem-Proving — mentioned by aSanchezStern

Fri, 27 Oct 2023 18:52:58 GMT

Sounds like you've stumbled into the wonderful world of machine-learning guided proof synthesis! While I don't think the full system you're describing has been built yet, many similar systems and pieces have. In terms of the initial phase of supervised learning on existing proofs to prove new ones, there's TacticToe (https://arxiv.org/abs/1804.00596), Tactician (https://arxiv.org/pdf/2008.00120.pdf), CoqGym/ASTactic (https://arxiv.org/abs/1905.09381), Proverbot9001 (https://arxiv.org/abs/1907.07794), and Diva (https://dl.acm.org/doi/10.1145/3510003.3510138#sec-terms), among others. Most of…

Paper and discussion history. A mention is not an endorsement.

An In-Context Learning Agent for Formal Theorem-Proving · HackerPapers discussions

An In-Context Learning Agent for Formal Theorem-Proving — mentioned by ekez

An In-Context Learning Agent for Formal Theorem-Proving — mentioned by aSanchezStern