Related papers: Automated Proof Generation for Rust Code via Self-…

Training models through self-play alone (without any human data) has been a longstanding goal in AI, but its effectiveness for training large language models remains unclear, particularly in code generation where rewards based on unit tests…

Verification is one of the central tasks in circuit and system design. While simulation and emulation are widely used, complete correctness can only be ensured based on formal proof techniques. But these approaches often have very high run…

Large Language Models (LLMs) have become powerful tools for automated code generation. However, these models often overlook critical security practices, which can result in the generation of insecure code that contains…

Automated random testing has shown to be an effective approach to finding faults but still faces a major unsolved issue: how to generate test inputs diverse enough to find many faults and find them quickly. Stateful testing, the automated…

We introduce Goedel-Prover, an open-source language model that achieves state-of-the-art (as of April 5 2025) performance in automated formal proof generation for mathematical problems. A key challenge in this field is the scarcity of…

Recent breakthroughs in generative simulation have harnessed Large Language Models (LLMs) to generate diverse robotic task curricula, yet these open-loop paradigms frequently produce linguistically coherent but physically infeasible goals,…

Large language models (LLMs) have significantly improved their reasoning capabilities; however, they still struggle with complex multi-step mathematical problem-solving due to error propagation, lack of self-correction, and limited…

Synthetic verification techniques such as generating test cases and reward modelling are common ways to enhance the coding capabilities of large language models (LLM) beyond predefined tests. Additionally, code verification has recently…

The emergence of vibe coding, a paradigm where non-technical users instruct Large Language Models (LLMs) to generate executable codes via natural language, presents both significant opportunities and severe risks for the construction…

Generative Pre-Trained Transformer models have been shown to be surprisingly effective at a variety of natural language processing tasks -- including generating computer code. We evaluate the effectiveness of open source GPT models for the…

Rust, an emerging programming language with explosive growth, provides a robust type system that enables programmers to write memory-safe and data-race free code. To allow access to a machine's hardware and to support low-level performance…

Proof engineering is notoriously labor-intensive: proofs that are straightforward on paper often require lengthy scripts in theorem provers. Recent advances in large language models (LLMs) create new opportunities for proof automation:…

The increasing complexity of modern system-on-chip designs amplifies hardware security risks and makes manual security property specification a major bottleneck in formal property verification. This paper presents Assertain, an automated…

Interactive theorem provers such as Coq are powerful tools to formally guarantee the correctness of software. However, using these tools requires significant manual effort and expertise. While Large Language Models (LLMs) have shown promise…

Automated software verification is a very active field of research which has made enormous progress both in theoretical and practical aspects. Recently, an important amount of research effort has been put into applying these techniques on…

Rust is a young programming language gaining increased attention from software developers since it was introduced to the world by Mozilla in 2010. In this study, we attempt to answer several research questions. Does Rust deserve such…

Test instability in a floating-point program occurs when the control flow of the program diverges from its ideal execution assuming real arithmetic. This phenomenon is caused by the presence of round-off errors that affect the evaluation of…

Automated proof generation for formal software verification remains largely unresolved despite advances in large language models (LLMs). While LLMs perform well in NLP, vision, and code generation, formal verification still requires…

Reliable verification of proofs remains a bottleneck for training and evaluating AI systems on hard mathematical reasoning. Fully formal proofs, in languages like Lean, are easy to verify because they are unambiguous and modular. Most…

Software is omnipresent within all factors of society. It is thus important to ensure that software are well tested to mitigate bad user experiences as well as the potential for severe financial and human losses. Software testing is however…