Can large language models reason about program invariants?

K Pei, D Bieber, K Shi, C Sutton… - … Conference on Machine …, 2023 - proceedings.mlr.press
Identifying invariants is an important program analysis task with applications towards
program understanding, bug finding, vulnerability analysis, and formal verification. Existing …

Finding invariants of distributed systems: It's a small (enough) world after all

T Hance, M Heule, R Martins, B Parno - 18th USENIX symposium on …, 2021 - usenix.org
Today's distributed systems are increasingly complex, leading to subtle bugs that are difficult
to detect with standard testing methods. Formal verification can provably rule out such bugs …

Finding inductive loop invariants using large language models

A Kamath, A Senthilnathan, S Chakraborty… - arxiv preprint arxiv …, 2023 - arxiv.org
Loop invariants are fundamental to reasoning about programs with loops. They establish
properties about a given loop's behavior. When they additionally are inductive, they become …

Lemur: Integrating large language models in automated program verification

H Wu, C Barrett, N Narodytska - arxiv preprint arxiv:2310.04870, 2023 - arxiv.org
The demonstrated code-understanding capability of LLMs raises the question of whether
they can be used for automated program verification, a task that typically demands high …

Learning contract invariants using reinforcement learning

J Liu, Y Chen, B Tan, I Dillig, Y Feng - Proceedings of the 37th IEEE/ACM …, 2022 - dl.acm.org
Due to the popularity of smart contracts in the modern financial ecosystem, there has been
growing interest in formally verifying their correctness and security properties. Most existing …

Almost correct invariants: Synthesizing inductive invariants by fuzzing proofs

S Lahiri, S Roy - Proceedings of the 31st ACM SIGSOFT International …, 2022 - dl.acm.org
Real-life programs contain multiple operations whose semantics are unavailable to
verification engines, like third-party library calls, inline assembly and SIMD instructions …

Learning to find proofs and theorems by learning to refine search strategies: The case of loop invariant synthesis

J Laurent, A Platzer - Advances in Neural Information …, 2022 - proceedings.neurips.cc
We propose a new approach to automated theorem proving where an AlphaZero-style agent
is self-training to refine a generic high-level expert strategy expressed as a nondeterministic …

Formal mathematical reasoning: A new frontier in ai

K Yang, G Poesia, J He, W Li, K Lauter… - arxiv preprint arxiv …, 2024 - arxiv.org
AI for Mathematics (AI4Math) is not only intriguing intellectually but also crucial for AI-driven
discovery in science, engineering, and beyond. Extensive efforts on AI4Math have mirrored …

Survey of machine learning for software-assisted hardware design verification: Past, present, and prospect

N Wu, Y Li, H Yang, H Chen, S Dai, C Hao… - ACM Transactions on …, 2024 - dl.acm.org
With the ever-increasing hardware design complexity comes the realization that efforts
required for hardware verification increase at an even faster rate. Driven by the push from …

Reinforcement Learning and Data-Generation for Syntax-Guided Synthesis

J Parsert, E Polgreen - Proceedings of the AAAI Conference on Artificial …, 2024 - ojs.aaai.org
Program synthesis is the task of automatically generating code based on a specification. In
Syntax-Guided Synthesis (SyGuS) this specification is a combination of a syntactic template …