Fix, Not Just Resample: Bounded Compiler-Guided Repair in Lean 4
中文摘要
研究提出了一种针对 Lean 4 的有界在线修复模块,利用编译器错误信息修复失败策略而非单纯重新采样,提升了自动定理证明效率。
English Summary
A new bounded, online repair module for Lean 4 uses compiler error messages to fix failed tactics instead of just resampling, improving automated theorem proving.
arXiv:2610.26942v1 Announce Type: new Abstract: Automated theorem provers often rely on sampling language models, but proof assistants like Lean reject each failed step with a precise error message --- information that pure sampling discards. To overcome this, we introduce a bounded, online step-level repair module. Our search samples $K$ candidate tactics at each step and repairs a failed tactic at most $R$ times. Instead of discarding failed tactics, we feed the compiler's error message to a pretrained repair model to fix individual rejected steps in place. This approach improves the solve rate over a sampling-only baseline across all tested candidate budgets ($K \in \{1,3,5,8\}$), achieving up to a $32\%$ relative gain and solving $82$ additional theorems on a $1{,}990$-theorem subset of the LeanDojo benchmark. Repair is not free: it trades extra runtime for reachable proofs. But the trade is predictable: repair pays most when sampling is constrained; its return is front-loaded, with the first repair attempt capturing $84\text{--}96\%$ of the total gain; and the gain comes almost entirely from shallow tactic-execution failures rather than structural errors such as type mismatche…