arXiv AI September 10, 2026 By Dimitrios Stamatios Bouras, Yihan Dai, Tairan Wang, Yingfei Xiong, Sergey Mechtaev

HoarePrompt: Structural Reasoning About Program Correctness in Natural Language

HoarePrompt is a new method that applies program verification concepts to natural language requirements, using large language models to generate step‑by‑step natural language descriptions of program states. It incorporates a few‑shot k‑induction technique to handle loops and then evaluates whether the annotated program satisfies the requirements. On the CoCoClaNeL dataset, HoarePrompt raises the Matthews correlation coefficient by 61% over zero‑shot chain‑of‑thought prompts and by 106% over test‑generation classifiers, with the inductive reasoning component adding a 26% MCC improvement.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

llms

arXiv AI

Aug 3

RePaCA: Leveraging Reasoning Large Language Models for Static Automated Patch Correctness Assessment

arXiv:2507. 22580v2 Announce Type: replace-cross Abstract: Automated Program Repair (APR) seeks to automatically correct software bugs without requiring human intervention.

By Marcos Fuster-Pena, David de-Fitero-Dominguez, Antonio Garcia-Cabot, Eva Garcia-Lopez

llms reinforcement-learning benchmarks

arXiv Machine Learning

Jun 5

Can LLMs Write Correct TLA+ Specifications? Evaluating Natural-Language-to-TLA+ Generation

arXiv:2606. 05792v1 Announce Type: cross Abstract: TLA+ has supported industrial verification at companies such as Amazon and Microsoft, yet writing correct TLA+ specifications from natural language still requires time and expertise, which limits adoption.

By Arslan Bisharat, Brian Ortiz, Eric Spencer, Khushboo Bhadauria, TaiNing Wang, George K. Thiruvathukal, Konstantin Laufer, Mohammed Abuhamad

llms safety

arXiv Machine Learning

Aug 11

MetaLint: Easy-to-Hard Generalization for Code Linting

arXiv:2507. 11687v5 Announce Type: replace-cross Abstract: Large language models excel at code generation but struggle with code linting, particularly in generalizing to unseen or evolving best practices beyond those observed during training.

By Atharva Naik, Lawanya Baghel, Dhakshin Govindarajan, Darsh Agrawal, Yiqing Xie, Daniel Fried, Carolyn Rose

llms fine-tuning benchmarks

arXiv AI

Sep 2

Predicting Program Exit Code with LLMs and Programming Language Semantics

The paper introduces Program Executability Prediction (PrEx), a task that asks large language models (LLMs) to determine whether a program is semantically valid or invalid and, if invalid, to identify the violated formal rule. To evaluate this, the authors create a dataset of systematically generated invalid programs derived from valid ones and test open‑source coding LLMs across different semantic formalisms, semantic shifts, and program splits (human‑written, LLM‑translated, fuzzer‑generated). Results show that LLMs rely more on pre‑training priors than on the provided semantics, performing poorly on modified semantics and with increasing program complexity.

By Lara Marinov, Aditya Thimmaiah, Jayanth Srinivasa, Junyi Jessy Li, Milos Gligoric

llms

arXiv AI

Jul 3

Prompt Coverage Adequacy

arXiv:2607. 02057v1 Announce Type: cross Abstract: In recent years, it has become increasingly evident that large language models (LLMs) and autonomous agents raise the level of abstraction in software development by shifting the focus from writing precise procedures to expressing intents and goals.

By Florian Tambon, Michael Konstantinou, Cedric Richter, Charles Chenouard, Mark Harman, Mike Papadakis

llms agents

arXiv AI

Jul 28

Reason Popper-ly: Patching In-Context Reasoning with Inductive Logic Programming

arXiv:2607. 23019v1 Announce Type: new Abstract: Chain-of-thought (CoT) prompting enables large language models (LLMs) to tackle multi-step reasoning tasks, yet the generated intermediate steps are not guaranteed to be logically sound.

By Zirong Chen, Meiyi Ma

llms benchmarks

One email a morning, machine-written

Related stories

RePaCA: Leveraging Reasoning Large Language Models for Static Automated Patch Correctness Assessment

Can LLMs Write Correct TLA+ Specifications? Evaluating Natural-Language-to-TLA+ Generation

MetaLint: Easy-to-Hard Generalization for Code Linting

Predicting Program Exit Code with LLMs and Programming Language Semantics

Prompt Coverage Adequacy

Reason Popper-ly: Patching In-Context Reasoning with Inductive Logic Programming