paper-with-me

홈 › Papers

ImProver 2: Iteratively Self-Improving LMs for Neurosymbolic Proof Optimization

2026-05-21 · Riyaz Ahuja, Tate Rowney, Jeremy Avigad, Sean Welleck arxiv

Formal mathematics libraries are rapidly expanding, creating a growing need to refactor verified proofs for maintainability and to improve training data quality for neural provers. However, scalable proof optimization is hindered by heterogeneous and heuristically specified objectives, scarce data, and high training and inference costs. To overcome these challenges, we introduce ImProver 2, a neurosymbolic framework for automated proof optimization in Lean 4. ImProver 2 combines a data-efficient expert-iteration pipeline with a scaffold that exposes formal structure alongside lightweight informal abstractions. We further introduce a suite of metrics capturing structural proof properties. Using ImProver 2, we train a 7B-parameter model that outperforms orders-of-magnitude larger models within the same model family, and is competitive with mid-tier frontier models across metrics. We additionally demonstrate that our neurosymbolic scaffold significantly improves performance across both small and frontier models. We show that with proper scaffolding and training, small models can effectively restructure research-level proofs over complex and varied metrics, matching substantially larger systems and establishing proof optimization as a scalable, learnable task.

📄 PDF Abstract BibTeX arXiv:2605.22885

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

ImProver: Agent-Based Automated Proof Optimization

2024-10-07 · Riyaz Ahuja, Jeremy Avigad, Prasad Tetali, Sean Welleck

Large language models (LLMs) have been used to generate formal proofs of mathematical theorems in proofs assistants such as Lean. However, we often want to optimize a formal proof with respect to various criteria, depend…

Language ModellingLarge Language Model

SGPO: Self-Generated Preference Optimization based on Self-Improver

2025-07-27 · Hyeonji Lee, Daejin Jo, Seohwan Yun, Sungwoong Kim arxiv

Large language models (LLMs), despite their extensive pretraining on diverse datasets, require effective alignment to human preferences for practical and reliable deployment. Conventional alignment methods typically empl…

Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generation

2023-10-03 · Eric Zelikman, Eliana Lorch, Lester Mackey, Adam Tauman Kalai

Several recent advances in AI systems solve problems by providing a "scaffolding" program that structures multiple calls to language models (LMs) to generate better outputs. A scaffolding program is written in a programm…

Code GenerationLanguage ModelingLanguage Modelling

Self-Supervised Transformers as Iterative Solution Improvers for Constraint Satisfaction

2025-02-18 · Yudong W. Xu, Wenhao Li, Scott Sanner, Elias B. Khalil

We present a Transformer-based framework for Constraint Satisfaction Problems (CSPs). CSPs find use in many applications and thus accelerating their solution with machine learning is of wide interest. Most existing appro…

reinforcement-learningReinforcement Learning

DrugImproverGPT: A Large Language Model for Drug Optimization with Fine-Tuning via Structured Policy Optimization

2025-02-11 · Xuefeng Liu, Songhao Jiang, Siyu Chen, Zhuoran Yang 외

Finetuning a Large Language Model (LLM) is crucial for generating results towards specific objectives. This research delves into the realm of drug optimization and introduce a novel reinforcement learning algorithm to fi…

Language ModelingLanguage ModellingLarge Language Model