paper-with-me

홈 › Papers

MA-LoT: Multi-Agent Lean-based Long Chain-of-Thought Reasoning enhances Formal Theorem Proving

2025-03-05 · Ruida Wang, Rui Pan, Yuxin Li, Jipeng Zhang, Yizhen Jia, Shizhe Diao, Renjie Pi, Junjie Hu, Tong Zhang

Solving mathematical problems using computer-verifiable languages like Lean has significantly impacted mathematical and computer science communities. State-of-the-art methods utilize single Large Language Models (LLMs) as agents or provers to either generate complete proof or perform tree searches. However, single-agent methods inherently lack a structured way to combine high-level reasoning in Natural Language (NL) with Formal Language (FL) verification feedback. To solve these issues, we propose MA-LoT: Multi-Agent Lean-based Long Chain-of-Thought framework, (to the best of our knowledge), the first multi-agent framework for Lean4 theorem proving that balance high-level NL reasoning and FL verification in Long CoT. Using this structured interaction, our approach enables deeper insights and long-term coherence in proof generation, with which past methods struggle. We do this by leveraging emergent formal reasoning ability in Long CoT using our novel LoT-Transfer Learning training-inference pipeline. Extensive experiments show that our framework achieves 54.51% accuracy rate on the Lean4 version of MiniF2F-Test dataset, largely outperforming GPT-4 (22.95%), single-agent tree search (InternLM-Step-Prover, 50.70%), and whole-proof generation (DeepSeek-Prover-v1.5, 48.36%) baselines. Furthermore, our findings highlight the potential of combining Long CoT with formal verification for a more insightful generation in a broader perspective.

📄 PDF Abstract BibTeX arXiv:2503.03205

Code (1)

rickyskywalker/leanofthought-official 공식 구현 pytorch

Tasks

Automated Theorem ProvingTransfer Learning

Methods 이 논문이 사용한 방법론

Attention 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Residual Connection 설명 없음
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Similar Papers 제목 키워드 기반

Ego-R1: Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoning

2025-06-16 · Shulin Tian, Ruiqi Wang, Hongming Guo, Penghao Wu 외

We introduce Ego-R1, a novel framework for reasoning over ultra-long (i.e., in days and weeks) egocentric videos, which leverages a structured Chain-of-Tool-Thought (CoTT) process, orchestrated by an Ego-R1 Agent trained…

Reinforcement Learning (RL)

DRT-o1: Optimized Deep Reasoning Translation via Long Chain-of-Thought

2024-12-23 · Jiaan Wang, Fandong Meng, Yunlong Liang, Jie zhou

Recently, O1-like models have emerged as representative examples, illustrating the effectiveness of long chain-of-thought (CoT) in reasoning tasks such as math and coding tasks. In this paper, we introduce DRT-o1, an att…

Machine TranslationMathTranslation

From Long to Lean: Performance-aware and Adaptive Chain-of-Thought Compression via Multi-round Refinement

2025-09-26 · Jianzhi Yan, Le Liu, Youcheng Pan, Shiwei Chen 외 arxiv

Chain-of-Thought (CoT) reasoning improves performance on complex tasks but introduces significant inference latency due to verbosity. We propose Multiround Adaptive Chain-of-Thought Compression (MACC), a framework that l…

COTCAgent: Preventive Consultation via Probabilistic Chain-of-Thought Completion

2026-05-14 · Zihan Deng, Xiaozhen Zhong, Chuanzhi Xu arxiv

As large language models empower healthcare, intelligent clinical decision support has developed rapidly. Longitudinal electronic health records (EHR) provide essential temporal evidence for accurate clinical diagnosis a…

Seed-Prover: Deep and Broad Reasoning for Automated Theorem Proving

2025-07-31 · Luoxin Chen, Jinming Gu, Liankai Huang, Wenhao Huang 외 arxiv

LLMs have demonstrated strong mathematical reasoning abilities by leveraging reinforcement learning with long chain-of-thought, yet they continue to struggle with theorem proving due to the lack of clear supervision sign…

Automated Theorem ProvingReinforcement LearningMathematical Reasoning