LeanAgent: Lifelong Learning for Formal Theorem Proving

• URL: http://arxiv.org/abs/2410.06209v7
• Date: Mon, 25 Nov 2024 02:39:03 GMT
• Title: LeanAgent: Lifelong Learning for Formal Theorem Proving
• Authors: Adarsh Kumarappan, Mo Tiwari, Peiyang Song, Robert Joseph George, Chaowei Xiao, Anima Anandkumar,
• Abstract summary: We present LeanAgent, a novel lifelong learning framework for formal theorem proving. LeanAgent continuously generalizes to and improves on ever-expanding mathematical knowledge. It successfully proves 155 theorems previously unproved formally by humans across 23 diverse Lean repositories.
• Score: 85.39415834798385
• License:
• Abstract: Large Language Models (LLMs) have been successful in mathematical reasoning tasks such as formal theorem proving when integrated with interactive proof assistants like Lean. Existing approaches involve training or fine-tuning an LLM on a specific dataset to perform well on particular domains, such as undergraduate-level mathematics. These methods struggle with generalizability to advanced mathematics. A fundamental limitation is that these approaches operate on static domains, failing to capture how mathematicians often work across multiple domains and projects simultaneously or cyclically. We present LeanAgent, a novel lifelong learning framework for formal theorem proving that continuously generalizes to and improves on ever-expanding mathematical knowledge without forgetting previously learned knowledge. LeanAgent introduces several key innovations, including a curriculum learning strategy that optimizes the learning trajectory in terms of mathematical difficulty, a dynamic database for efficient management of evolving mathematical knowledge, and progressive training to balance stability and plasticity. LeanAgent successfully proves 155 theorems previously unproved formally by humans across 23 diverse Lean repositories, many from advanced mathematics. It performs significantly better than the static LLM baseline, proving challenging theorems in domains like abstract algebra and algebraic topology while showcasing a clear progression of learning from basic concepts to advanced topics. In addition, we analyze LeanAgent's superior performance on key lifelong learning metrics. LeanAgent achieves exceptional scores in stability and backward transfer, where learning new tasks improves performance on previously learned tasks. This emphasizes LeanAgent's continuous generalizability and improvement, explaining its superior theorem-proving performance.

Related papers

• MathFimer: Enhancing Mathematical Reasoning by Expanding Reasoning Steps through Fill-in-the-Middle Task [49.355810887265925]
  We introduce MathFimer, a novel framework for mathematical reasoning step expansion. We develop a specialized model, MathFimer-7B, on our carefully curated NuminaMath-FIM dataset. We then apply these models to enhance existing mathematical reasoning datasets by inserting detailed intermediate steps into their solution chains.
  arXiv  Detail & Related papers  (2025-02-17T11:22:24Z)
• One Example Shown, Many Concepts Known! Counterexample-Driven Conceptual Reasoning in Mathematical LLMs [57.48325300739872]
  Leveraging mathematical Large Language Models for proof generation is a fundamental topic in LLMs research. We argue that the ability of current LLMs to prove statements largely depends on whether they have encountered the relevant proof process during training. Inspired by the pedagogical method of "proof by counterexamples" commonly used in human mathematics education, our work aims to enhance LLMs' ability to conduct mathematical reasoning and proof through counterexamples.
  arXiv  Detail & Related papers  (2025-02-12T02:01:10Z)
• LemmaHead: RAG Assisted Proof Generation Using Large Language Models [0.0]
  We develop LemmaHead, a knowledge base that supplements queries to the model with relevant mathematical context. To measure our model's performance in mathematical reasoning, our testing paradigm focuses on the task of automated theorem proving.
  arXiv  Detail & Related papers  (2025-01-27T05:46:06Z)
• Large Language Models for Mathematical Analysis [3.7325315394927023]
  This work addresses critical gaps in mathematical reasoning and contributes to advancing trustworthy AI. We developed the DEMI-MathAnalysis dataset, comprising proof-based problems from mathematical analysis topics. We also designed a guiding framework to rigorously enhance LLMs' ability to solve these problems.
  arXiv  Detail & Related papers  (2024-12-28T20:37:55Z)
• Formal Mathematical Reasoning: A New Frontier in AI [60.26950681543385]
  We advocate for formal mathematical reasoning and argue that it is indispensable for advancing AI4Math to the next level. We summarize existing progress, discuss open challenges, and envision critical milestones to measure future success.
  arXiv  Detail & Related papers  (2024-12-20T17:19:24Z)
• MathLearner: A Large Language Model Agent Framework for Learning to Solve Mathematical Problems [0.936726079405677]
  We propose an agent framework for learning to solve mathematical problems based on inductive reasoning. By emulating the human learning process of generalization of learned information, this framework has great performance in the mathematical reasoning process. Our model can be used as a personalised learning aid, thus reducing the inequality of educational resources.
  arXiv  Detail & Related papers  (2024-08-03T13:28:19Z)
• MathBench: Evaluating the Theory and Application Proficiency of LLMs with a Hierarchical Mathematics Benchmark [82.64129627675123]
  MathBench is a new benchmark that rigorously assesses the mathematical capabilities of large language models. MathBench spans a wide range of mathematical disciplines, offering a detailed evaluation of both theoretical understanding and practical problem-solving skills.
  arXiv  Detail & Related papers  (2024-05-20T17:52:29Z)
• InternLM-Math: Open Math Large Language Models Toward Verifiable Reasoning [98.53491178426492]
  We open-source our math reasoning LLMs InternLM-Math which is continue pre-trained from InternLM2. We unify chain-of-thought reasoning, reward modeling, formal reasoning, data augmentation, and code interpreter in a unified seq2seq format. Our pre-trained model achieves 30.3 on the MiniF2F test set without fine-tuning.
  arXiv  Detail & Related papers  (2024-02-09T11:22:08Z)
• math-PVS: A Large Language Model Framework to Map Scientific Publications to PVS Theories [10.416375584563728]
  This work investigates the applicability of large language models (LLMs) in formalizing advanced mathematical concepts. We envision an automated process, called emphmath-PVS, to extract and formalize mathematical theorems from research papers.
  arXiv  Detail & Related papers  (2023-10-25T23:54:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.