arXiv AI October 19, 2026 By Jack Li, Sophia Li

Repair, Retry, and the Cost of Hindsight: Verifier Feedback in Formal Theorem Proving

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

4d ago

Fix, Not Just Resample: Bounded Compiler-Guided Repair in Lean 4

The paper presents a bounded, online step-level repair module for Lean 4 that uses compiler error messages to fix rejected tactics instead of discarding them. By sampling up to $K$ candidate tactics and allowing at most $R$ repairs per step, the method improves solve rates over a sampling-only baseline, achieving up to a 32% relative gain and solving 82 additional theorems on a 1,990-theorem subset of the LeanDojo benchmark. The approach trades extra runtime for reachable proofs, with most benefit coming from early repair attempts and shallow tactic failures, and it successfully replicates on the Lean Workbook benchmark, nearly doubling its solve rate without regressions.

By Haotian Deng, Chris Farber, Sonal Narasimha, Samskrithi Sivakumar, Yexiang Xue

llms benchmarks

arXiv AI

Jul 15

Form, Not Content? A Preregistered, Placebo-Controlled Evaluation of Learned Error-Conditioned Self-Repair Through Prompts and Weights in Frozen Small Code Models

arXiv:2607. 12962v1 Announce Type: cross Abstract: Frozen small code LLMs are deployed locally, yet the information guiding a retry after a failed attempt is still measured without placebo controls in the self-repair literature.

By Mehmet Iscan

llms reinforcement-learning

arXiv Machine Learning

Jul 1

Falsification, Not Exposure: An Internally Preregistered Placebo-Controlled Decomposition of Self-Repair Feedback in Frozen Small Code Models

arXiv:2606. 31511v1 Announce Type: cross Abstract: In deployment settings where retraining is infeasible, small frozen code models are routinely asked to repair a failed program after seeing their own failing output, usually treated as a retry mechanism.

By Mehmet Iscan

benchmarks

arXiv AI

Jul 28

DualityCert: Verifier-Gated Language-Model Repair of Broken Duality Claims in Quantum Field Theory

arXiv:2607. 23614v1 Announce Type: cross Abstract: We present DualityCert, a symbolic verifier for candidate Seiberg-duality claims in four-dimensional N=1 quiver gauge theories.

By Xingyang Yu

agents benchmarks

arXiv AI

Oct 16

Don't Regenerate, Debug: A Domain-Specific Agent for Repairing Near-Miss Accelerator Kernels

The paper introduces a domain‑specific debugging agent for repairing near‑miss accelerator kernels, arguing that debugging is more efficient than regenerating kernels from scratch. It tackles knowledge scarcity, integrity, and cost control through pattern retrieval, anti‑cheat detection, and convergence safeguards. Empirical results show the debug agent achieves a 66.7% Pass@1 rate and uses 92.8% fewer tokens per success compared to traditional regeneration methods.

By Yansong Sun, Shenxiu Wu, Siyuan Chen, Runlin Hou, Junhao Qiu, Junming Cao, Shudi Shao, Zhichao Lu, Qingfu Zhang

llms rag agents reinforcement-learning benchmarks

arXiv AI

Jun 15

When Good Verifiers Go Bad: Self-Improving VLMs Can Regress on New Tasks

arXiv:2606. 14629v1 Announce Type: cross Abstract: Verifier-driven self-DPO is a common recipe for self-improving production visual-language models.

By Jianzhe Lin

llms reinforcement-learning

One email a morning, machine-written

Related stories

Fix, Not Just Resample: Bounded Compiler-Guided Repair in Lean 4

Form, Not Content? A Preregistered, Placebo-Controlled Evaluation of Learned Error-Conditioned Self-Repair Through Prompts and Weights in Frozen Small Code Models

Falsification, Not Exposure: An Internally Preregistered Placebo-Controlled Decomposition of Self-Repair Feedback in Frozen Small Code Models

DualityCert: Verifier-Gated Language-Model Repair of Broken Duality Claims in Quantum Field Theory

Don't Regenerate, Debug: A Domain-Specific Agent for Repairing Near-Miss Accelerator Kernels

When Good Verifiers Go Bad: Self-Improving VLMs Can Regress on New Tasks