English
Related papers

Related papers: Neuro-Symbolic Proof Generation for Scaling System…

200 papers

Formal verification via theorem proving enables the expressive specification and rigorous proof of software correctness, but it is difficult to scale due to the significant manual effort and expertise required. While Large Language Models…

Software Engineering · Computer Science 2025-10-30 Minghai Lu , Zhe Zhou , Danning Xie , Songlin Jia , Benjamin Delaware , Tianyi Zhang

Large language models (LLMs) can translate natural language into optimization code, but silent failures pose a critical risk: code that executes and returns solver-feasible solutions may encode semantically incorrect formulations -- a…

Software Engineering · Computer Science 2026-04-30 Junbo Jacob Lian , Yujun Sun , Huiling Chen , Chaoyu Zhang , Hanzhang Qin , Chung-Piaw Teo

Language models have become increasingly powerful tools for formal mathematical reasoning. However, most existing approaches rely exclusively on either large general-purpose models or smaller specialized models, each with distinct…

Artificial Intelligence · Computer Science 2025-07-22 Nicolas Wischermann , Claudio Mayrink Verdun , Gabriel Poesia , Francesco Noseda

Training large language models (LLMs) with synthetic reasoning data has become a popular approach to enhancing their reasoning capabilities, while a key factor influencing the effectiveness of this paradigm is the quality of the generated…

Artificial Intelligence · Computer Science 2026-03-24 Zhuojie Yang , Wentao Wan , Keze Wang

Automated vulnerability detection in critical-infrastructure software confronts a fundamental barrier: industrial software is routinely deployed as stripped, symbol-free binaries that deprive conventional Software Composition Analysis of…

Software Engineering · Computer Science 2026-05-11 Bowei Ning , Xuejun Zong , Lian Lian , Kan He , Yifei Sun , Yuxiang Lei , Plamen Vasilev

Large language models (LLM), such as Google's Minerva and OpenAI's GPT families, are becoming increasingly capable of solving mathematical quantitative reasoning problems. However, they still make unjustified logical and computational…

Artificial Intelligence · Computer Science 2024-03-28 Jin Peng Zhou , Charles Staats , Wenda Li , Christian Szegedy , Kilian Q. Weinberger , Yuhuai Wu

Effectively translating between natural language (NL) and formal logics like Linear Temporal Logic (LTL) requires expertise that limits formal verification's reach in safety-critical development. Template-based approaches sacrifice…

Artificial Intelligence · Computer Science 2026-05-25 Paapa Kwesi Quansah , Ernest Bonnah

We present a novel approach to automated proof generation for the TLA+ Proof System (TLAPS) using Large Language Models (LLMs). Our method combines two key components: a sub-proof obligation generation phase that breaks down complex proof…

Logic in Computer Science · Computer Science 2025-01-07 Yuhao Zhou

We introduce a theorem proving approach to the specification and generation of temporal logical constraints for training neural networks. We formalise a deep embedding of linear temporal logic over finite traces (LTL$_f$) and an associated…

Artificial Intelligence · Computer Science 2022-07-11 Mark Chevallier , Matthew Whyte , Jacques D. Fleuriot

SMLP: Symbolic Machine Learning Prover an open source tool for exploration and optimization of systems represented by machine learning models. SMLP uses symbolic reasoning for ML model exploration and optimization under verification and…

Machine Learning · Computer Science 2024-05-17 Franz Brauße , Zurab Khasidashvili , Konstantin Korovin

Formal verification has emerged as a powerful approach to ensure the safety and reliability of deep neural networks. However, current verification tools are limited to only a handful of properties that can be expressed as first-order…

Artificial Intelligence · Computer Science 2022-03-03 Xuan Xie , Kristian Kersting , Daniel Neider

Despite their linguistic competence, Large Language Models (LLMs) often struggle to reason reliably and flexibly. To identify these shortcomings, we introduce the Non-Linear Reasoning (NLR) dataset, a collection of 55 unique, hand-designed…

Computation and Language · Computer Science 2025-12-02 Nasim Borazjanizadeh , Steven T. Piantadosi

One important approach to software verification is interactive theorem proving. However, writing formal proofs often requires substantial human effort, making proof automation highly important. Traditionally, proof automation has relied on…

Logic in Computer Science · Computer Science 2026-03-05 Jian Fang , Yican Sun , Yingfei Xiong

SOAR, a classic symbol-based cognitive architecture, has been fostering the development of general, human-like intelligent agents. Nevertheless, its practical adoption is hindered by the laborious manual rule coding. Emerging Large Language…

Computation and Language · Computer Science 2025-10-13 Fang Yuan , Junjie Zeng , Yue Hu , Zhengqiu Zhu , Quanjun Yin , Yuxiang Xie

Deep code generation is a topic of deep learning for software engineering (DL4SE), which adopts neural models to generate code for the intended functions. Since end-to-end neural methods lack domain knowledge and software hierarchy…

Software Engineering · Computer Science 2023-08-25 Jian Gu , Harald C. Gall

Feature transformation enhances data representation by deriving new features from the original data. Generative AI offers potential for this task, but faces challenges in stable generation (consistent outputs) and valid generation…

Machine Learning · Computer Science 2025-06-12 Xinyuan Wang , Haoyue Bai , Nanxu Gong , Wangyang Ying , Sixun Dong , Xiquan Cui , Yanjie Fu

Large Language Models (LLMs) are transforming scientific hypothesis generation and validation by enabling information synthesis, latent relationship discovery, and reasoning augmentation. This survey provides a structured overview of…

We present a novel method for symbolic regression (SR), the task of searching for compact programmatic hypotheses that best explain a dataset. The problem is commonly solved using genetic algorithms; we show that we can enhance such methods…

Machine Learning · Computer Science 2024-12-11 Arya Grayeli , Atharva Sehgal , Omar Costilla-Reyes , Miles Cranmer , Swarat Chaudhuri

Despite the success of large language models (LLMs), the task of theorem proving still remains one of the hardest reasoning tasks that is far from being fully solved. Prior methods using language models have demonstrated promising results,…

Large Language Models (LLMs) have shown strong performance on code understanding tasks, yet they fundamentally lack the ability to perform precise, exhaustive mathematical reasoning about program behavior. Existing benchmarks either focus…