English
Related papers

Related papers: LExecutor: Learning-Guided Execution

200 papers

Large language models (LLMs) have shown remarkable capabilities across diverse coding tasks. However, their adoption requires a true understanding of program execution rather than relying on surface-level patterns. Existing benchmarks…

Machine Learning · Computer Science 2026-04-24 Eshgin Hasanov , Md Mahadi Hassan Sibat , Santu Karmaker , Aashish Yadavally

We present a technique to infer lower bounds on the worst-case runtime complexity of integer programs, where in contrast to earlier work, our approach is not restricted to tail-recursion. Our technique constructs symbolic representations of…

Logic in Computer Science · Computer Science 2020-09-29 Florian Frohn , Matthias Naaf , Marc Brockschmidt , Jürgen Giesl

As autonomous agents become increasingly sophisticated, validating their sequential behavior presents a significant challenge. Traditional testing approaches require manual specification, exact sequence matching, or thousands of training…

Artificial Intelligence · Computer Science 2026-05-06 Reshabh K Sharma , Gaurav Mittal , Yu Hu

Instruction-following made modern large language models (LLMs) helpful assistants. However, the key to taming LLMs on complex instructions remains mysterious, for that there are huge gaps between models trained by open-source community and…

Computation and Language · Computer Science 2025-09-30 Kaikai An , Li Sheng , Ganqu Cui , Shuzheng Si , Ning Ding , Yu Cheng , Baobao Chang

Code generation tasks aim to automate the conversion of user requirements into executable code, significantly reducing manual development efforts and enhancing software productivity. The emergence of large language models (LLMs) has…

Software Engineering · Computer Science 2026-01-15 Sicong Liu , Yanxian Huang , Mingwei Liu , Jiachi Chen , Ensheng Shi , Yuchi Ma , Hongyu Zhang , Yin Zhang , Yanlin Wang

Children acquire their native language with apparent ease by observing how language is used in context and attempting to use it themselves. They do so without laborious annotations, negative examples, or even direct corrections. We take a…

Computation and Language · Computer Science 2021-03-18 Christopher Wang , Candace Ross , Yen-Ling Kuo , Boris Katz , Andrei Barbu

A significant amount of research is focused on developing and evaluating large language models for a variety of code synthesis tasks. These include synthesizing code from natural language, synthesizing tests from code, and synthesizing…

Predicting program behavior and reasoning about code execution remain significant challenges in software engineering, particularly for large language models (LLMs) designed for code analysis. While these models excel at understanding static…

Software Engineering · Computer Science 2025-02-11 Cuong Chi Le , Hoang-Chau Truong-Vinh , Huy Nhat Phan , Dung Duy Le , Tien N. Nguyen , Nghi D. Q. Bui

As Large Language Models become integral to software development, with substantial portions of AI-suggested code entering production, understanding their internal correctness mechanisms becomes critical for safe deployment. We apply sparse…

Software Engineering · Computer Science 2025-10-06 Kriz Tahimic , Charibeth Cheng

Detecting buffer overruns from a source code is one of the most common and yet challenging tasks in program analysis. Current approaches have mainly relied on rigid rules and handcrafted features devised by a few experts, limiting…

Software Engineering · Computer Science 2017-03-08 Min-je Choi , Sehun Jeong , Hakjoo Oh , Jaegul Choo

LLMs demonstrate remarkable reasoning capabilities, yet whether they utilize internal world models or rely on sophisticated pattern matching remains open. We study LLMs through the lens of robustness of their code understanding using a…

Software Engineering · Computer Science 2026-04-21 Claudio Spiess , Prem Devanbu , Earl T. Barr

State-of-the-art code generation frameworks rely on mental simulation, where LLMs internally trace execution to verify correctness. We expose a fundamental limitation: the Mental-Reality Gap -- where models hallucinate execution traces and…

Software Engineering · Computer Science 2026-04-23 Woojin Lee , Jin-Xia Huang

Existing support for regular expressions in automated test generation or verification tools is lacking. Common aspects of regular expression engines found in mainstream programming languages, such as backreferences or greedy matching, are…

Programming Languages · Computer Science 2020-03-16 Blake Loring , Duncan Mitchell , Johannes Kinder

Language model-based instruction-following systems have lately shown increasing performance on many benchmark tasks, demonstrating the capability of adapting to a broad variety of instructions. However, such systems are often not designed…

Computation and Language · Computer Science 2024-03-20 Rahul Nadkarni , Yizhong Wang , Noah A. Smith

Currently, large pre-trained language models are widely applied in neural code completion systems. Though large code models significantly outperform their smaller counterparts, around 70\% of displayed code completions from Github Copilot…

Software Engineering · Computer Science 2024-08-12 Zhensu Sun , Xiaoning Du , Fu Song , Shangwen Wang , Mingze Ni , Li Li , David Lo

Large Language Models (LLMs) have demonstrated exceptional proficiency in instruction-following, becoming increasingly crucial across various applications. However, this capability brings with it the risk of prompt injection attacks, where…

Computation and Language · Computer Science 2023-11-28 Zekun Li , Baolin Peng , Pengcheng He , Xifeng Yan

Maintaining legacy software requires many software and systems engineering hours. Assembly code programs, which demand low-level control over the computer machine state and have no variable names, are particularly difficult for humans to…

Software Engineering · Computer Science 2024-03-18 Celine Lee , Abdulrahman Mahmoud , Michal Kurek , Simone Campanoni , David Brooks , Stephen Chong , Gu-Yeon Wei , Alexander M. Rush

Large Language Models (LLMs) like Codex are powerful tools for performing code completion and code generation tasks as they are trained on billions of lines of code from publicly available sources. Moreover, these models are capable of…

Software Engineering · Computer Science 2023-03-17 Catherine Tony , Markus Mutas , Nicolás E. Díaz Ferreyra , Riccardo Scandariato

Large language models (LLMs) are increasingly used for high-stakes decision-making, yet existing approaches struggle to reconcile scalability, interpretability, and reproducibility. Black-box models obscure their reasoning, while recent…

Code completion is a popular software development tool integrated into all major IDEs. Many neural language models have achieved promising results in completion suggestion prediction on synthetic benchmarks. However, a recent study When…

Software Engineering · Computer Science 2020-11-10 Gareth Ari Aye , Seohyun Kim , Hongyu Li