The paper investigates how verifier feedback influences self‑repair in formal theorem proving. Using controlled one‑step experiments on Lean with frozen Qwen3.6‑27B and DeepSeek‑Prover‑V2‑7B, the authors find that showing a model its failed predecessor can hurt success and increase copying, while providing the corresponding compiler error can partially recover performance. In sequential trials, Qwen benefits from correct diagnostics within failed‑proof histories, but no feedback condition outperforms simple instruction‑only resampling, indicating that verifier feedback can aid repair yet cannot fully offset the cost of conditioning on a failed attempt.
By Jack Li, Sophia Li
arXiv:2606. 03743v1 Announce Type: new Abstract: While Large Language Models (LLMs) have shown strong performance in generating formal proofs, their outputs often remain less readable, modular, maintainable, and reusable than proofs in mature formal mathematics libraries.
By Yiming Fu, Peixuan Liu, Zichen Wang, Kun yuan
The paper introduces a reference‑free proxy‑judge framework for autoformalization, separating correctness into grounding, statement faithfulness, coverage, and inference. It presents three theoretical results linking proxy error rates to pass‑but‑wrong rates, the impact of false rejections on refinement, and a decomposition of final pass rates. The framework is instantiated with eight proxies and evaluated on ProofNet, miniF2F, e‑SNLI, and ProntoQA, showing that the predictions hold and identifying failure routes.
By Lei Xu, Xin Quan, Andr\'e Freitas
arXiv:2610.38174v1 Announce Type: cross
Abstract: We present EasyProver, a Lean proving system built from recursive agents with isolated contexts, asynchronous search, parallel tactic probing, and an...
By Debargha Ganguly, Divya Raghunathan, Dejan Jovanovi\'c, Vikash Singh, Soonho Kong, Aaron Tomb, Aman Goel, Ferhat Erata, Sam Bayless
arXiv:2608. 09277v1 Announce Type: new Abstract: Verified code generation asks a large language model (LLM) to generate both an executable program and a machine-checkable proof that the program meets a formal specification, promising software that is correct by construction.
By Zenan Li, Ziran Yang, Peiyang Song, Zhaoyu Li, Kaiyu Yang
arXiv:2607. 09366v1 Announce Type: cross Abstract: Program verification is crucial for software correctness, but producing fully verified programs remains difficult in practice.
By Shirley Yu, Ruben Martins
arXiv:2609.21190v1 Announce Type: cross
Abstract: Ensuring the correctness of LLM-generated code is a core challenge for modern software engineering. Benchmarks for agentic code generation check corr...
By George Ma, Benjamin Mikek, Haoyu Li, Ferhat Erata, Yuhao Zhang, Zeren Shui, Behrooz Omidvar Tehrani, Jun Huan, Murali Krishna Ramanathan, Somayeh Sojoudi, Hao Zhou, Anoop Deoras
arXiv:2607. 17352v1 Announce Type: new Abstract: Designing effective Lean proof agents is a central challenge in formal mathematical reasoning.
By Yuqing Li, Zeguan Wu, Yu Gan, Junyu Liu
The paper reports that all 1,325 theorems from the VeriContest benchmark—comprising 1,007 competitive‑programming problems in Rust with Verus specifications—were successfully proved using Rust‑Prover, a Lean 4‑based verifier. The authors translated each Verus specification and Rust program into Lean, then used Lean’s kernel to confirm the proofs, achieving a 70% first‑iteration success rate and completing 1,259 proofs in under 32 hours on Claude Opus 5.5. The translated Lean programs matched the original Rust outputs on 21,413 benchmark test cases, and the study also compared performance across multiple large‑language‑model settings, noting that higher reasoning effort increased cost without improving proof counts.
By Traian Serbanuta, Jun Xu, Andrei Stefanescu, Cosmin Radoi
arXiv:2607. 24604v1 Announce Type: cross Abstract: Generate--test--revise loops are common in coding agents, but repetition alone provides no reliability guarantee.
By Xueping Gao, Jianwei Yang, Qiang Yang
arXiv:2605. 20244v2 Announce Type: replace-cross Abstract: We present Lean Refactor, a plug-and-play retrieval-augmented agentic framework for multi-objective, controllable, and version-robust refactoring of Lean proofs.
By Jialin Lu, Soonho Kong, Rodrigo Stehling, Kaiyu Yang, Zhangyang Wang, Weiran Sun, Wuyang Chen
ClaimScope is a 72‑task benchmark that audits mathematical claims by requiring a verdict, scope, counterexample, and repair, covering areas such as optimizer‑state transport and exact $2 imes2$ linear algebra. The study evaluates Qwen3‑8B using a witness checker that only examines the model’s submitted state, showing that verifier feedback improves counterexample acceptance and safe completions compared to generic feedback. The results demonstrate that separating claim classification from executable evidence can yield gains in witness‑structure correction without necessarily improving broader reasoning.
By Mushir Akhtar