paper-with-me

홈 › Papers

Learning a SAT Solver from Single-Bit Supervision

2018-02-11 · ICLR 2019 5 · Daniel Selsam, Matthew Lamm, Benedikt Bünz, Percy Liang, Leonardo de Moura, David L. Dill

We present NeuroSAT, a message passing neural network that learns to solve SAT problems after only being trained as a classifier to predict satisfiability. Although it is not competitive with state-of-the-art SAT solvers, NeuroSAT can solve problems that are substantially larger and more difficult than it ever saw during training by simply running for more iterations. Moreover, NeuroSAT generalizes to novel distributions; after training only on random SAT problems, at test time it can solve SAT problems encoding graph coloring, clique detection, dominating set, and vertex cover problems, all on a range of distributions over small random graphs.

📄 PDF Abstract BibTeX arXiv:1802.03685

Code (6)

corail-research/learning-generic-csp pytorch
dragonavelar/Learning-SAT-Solver tf
dselsam/neurosat tf
mister-bailey/TensorSAT tf
mluszczyk/deepsat tf
ryanzhangfan/NeuroSAT pytorch

Similar Papers 제목 키워드 기반

Execution-Verified Reinforcement Learning for Optimization Modeling

2026-04-01 · Runda Guan, Xiangqing Shen, Jiajun Zhang, Yifan Zhang 외 arxiv

Automating optimization modeling with LLMs is a promising path toward scalable decision intelligence, but existing approaches either rely on agentic pipelines built on closed-source LLMs with high inference latency, or f…

Reinforcement Learning

ACE: Self-Evolving LLM Coding Framework via Adversarial Unit Test Generation and Preference Optimization

2026-04-17 · Yixu Huang, Xinglei Yu, Zhongyu Wei arxiv

Large Language Models (LLMs) excel at code generation but remain heavily reliant on large-scale annotated solutions and verification-based supervision, which constrains scalability and hinders sustained self-improvement.…

Code Generation

CalibForge: Adversarial Solver Calibration for Scaling Learnable Terminal Tasks

2026-08-06 · Fanzhe Meng, Guoxin Chen, Jiale Zhao, Shuang Sun 외 arxiv

Training terminal agents requires executable and verifiable tasks that are not merely solvable, but appropriately challenging for learning. Executable validation establishes feasibility, yet does not reveal how a task be…

NPSolver: Neural Poisson Solver with Iterative Physics Supervision

2026-05-25 · Bocheng Zeng, Rui Zhang, Runze Mao, Mengtao Yan 외 arxiv

Efficiently solving Poisson equations on complex, irregular domains remains a fundamental challenge in scientific computing, as classical iterative solvers often suffer from prohibitive runtime due to ill-conditioned sys…

SATNet: Bridging deep learning and logical reasoning using a differentiable satisfiability solver

2019-05-29 · Po-Wei Wang, Priya L. Donti, Bryan Wilder, Zico Kolter

Integrating logical reasoning within deep learning architectures has been a major goal of modern AI systems. In this paper, we propose a new direction toward this goal by introducing a differentiable (smoothed) maximum s…

Deep LearningGame of SudokuLogical Reasoning