English
Related papers

Related papers: Python Symbolic Execution with LLM-powered Code Ge…

200 papers

LLM code-generation pipelines often sample multiple candidates and select one final answer without access to a complete oracle. Existing pipelines mix textual voting, ranking, and execution-based agreement, but the relative contribution of…

Software Engineering · Computer Science 2026-05-12 Shan Jiang , Zijian Yi , Chenguang Zhu

Memory corruption is a serious class of software vulnerabilities, which requires careful attention to be detected and removed from applications before getting exploited and harming the system users. Symbolic execution is a well-known method…

Cryptography and Security · Computer Science 2025-09-16 Sara Baradaran , Mahdi Heidari , Ali Kamali , Maryam Mouzarani

In this paper we evaluate the capabilities of LLM Agents in generating code for real-world problems. Specifically, we explore code synthesis for microservice-based applications, a widely used architectural pattern for building applications.…

Software Engineering · Computer Science 2025-10-28 Daniel M. Yellin

Large language models (LLMs) achieve impressive results over various tasks, and ever-expanding public repositories contain an abundance of pre-trained models. Therefore, identifying the best-performing LLM for a given task is a significant…

Computation and Language · Computer Science 2025-11-13 Idan Kashani , Avi Mendelson , Yaniv Nemcovsky

The high rate of false alarms from static analysis tools and Large Language Models (LLMs) complicates vulnerability detection in Solidity Smart Contracts, demanding methods that can formally or empirically prove the presence of defects.…

Software Engineering · Computer Science 2025-09-17 Ştefan-Claudiu Susan , Andrei Arusoaie , Dorel Lucanu

Replicating human-level intelligence in the execution of embodied tasks remains challenging due to the unconstrained nature of real-world environments. Novel use of large language models (LLMs) for task planning seeks to address the…

We introduce SIMCOPILOT, a benchmark that simulates the role of large language models (LLMs) as interactive, "copilot"-style coding assistants. Targeting both completion (finishing incomplete methods or code blocks) and infill tasks…

Machine Learning · Computer Science 2025-05-29 Mingchao Jiang , Abhinav Jain , Sophia Zorek , Chris Jermaine

Large Language Models (LLMs) have shown promise in solving natural language-described planning tasks, but their direct use often leads to inconsistent reasoning and hallucination. While hybrid LLM-symbolic planning pipelines have emerged as…

Artificial Intelligence · Computer Science 2024-09-25 Sukai Huang , Nir Lipovetzky , Trevor Cohn

Testing plays a crucial role in the software development cycle, enabling the detection of bugs, vulnerabilities, and other undesirable behaviors. To perform software testing, testers need to write code snippets that execute the program…

Software Engineering · Computer Science 2025-02-04 Wenhan Wang , Chenyuan Yang , Zhijie Wang , Yuheng Huang , Zhaoyang Chu , Da Song , Lingming Zhang , An Ran Chen , Lei Ma

Simulating learner actions helps stress-test open-ended interactive learning environments and prototype new adaptations before deployment. While recent studies show the promise of using large language models (LLMs) for simulating human…

Artificial Intelligence · Computer Science 2024-10-15 Amogh Mannekote , Adam Davies , Jina Kang , Kristy Elizabeth Boyer

Although Large Language Models (LLMs) have demonstrated remarkable code-generation ability, they still struggle with complex tasks. In real-world software development, humans usually tackle complex tasks through collaborative teamwork, a…

Software Engineering · Computer Science 2024-05-14 Yihong Dong , Xue Jiang , Zhi Jin , Ge Li

The iterative and incremental nature of software development using models typically makes a model of a system incomplete (i.e., partial) until a more advanced and complete stage of development is reached. Existing model execution approaches…

Software Engineering · Computer Science 2021-04-01 Mojtaba Bagherzadeh , Nafiseh Kahani , Karim Jahed , Juergen Dingel

Since their inception, programming languages have trended towards greater readability and lower barriers for programmers. Following this trend, natural language can be a promising type of programming language that provides great flexibility…

Computation and Language · Computer Science 2024-05-24 Shuyuan Xu , Zelong Li , Kai Mei , Yongfeng Zhang

Conventional Task and Motion Planning (TAMP) approaches rely on manually crafted interfaces connecting symbolic task planning with continuous motion generation. These domain-specific and labor-intensive modules are limited in addressing…

Robotics · Computer Science 2024-08-22 Shu Wang , Muzhi Han , Ziyuan Jiao , Zeyu Zhang , Ying Nian Wu , Song-Chun Zhu , Hangxin Liu

Concolic testing mixes symbolic and concrete execution to generate test cases covering paths effectively. Its benefits have been demonstrated for more than 15 years to test imperative programs. Other programming paradigms, like logic…

Logic in Computer Science · Computer Science 2020-02-18 Sophie Fortz , Fred Mesnard , Etienne Payet , Gilles Perrouin , Wim Vanhoof , German Vidal

Recent advances in Large language models (LLMs) have demonstrated their promising capabilities of generating robot operation code to enable LLM-driven robots. To enhance the reliability of operation code generated by LLMs, corrective…

Robotics · Computer Science 2026-02-25 Wenhao Wang , Yi Rong , Yanyan Li , Long Jiao , Jiawei Yuan

While recent advances in large language models (LLMs) have shown promise in automating test generation for regression testing, they often suffer from limited reasoning about program execution, resulting in stagnated coverage growth - a…

Software Engineering · Computer Science 2026-01-28 Cuong Chi Le , Cuong Duc Van , Tung Duy Vu , Thai Minh Pham Vu , Hoang Nhat Phan , Huy Nhat Phan , Tien N. Nguyen

Large Language Models (LLMs) have shown great potential in automating code generation; however, their ability to generate accurate circuit-level SPICE code remains limited due to a lack of hardware-specific knowledge. In this paper, we…

Hardware Architecture · Computer Science 2024-10-29 Deepak Vungarala , Sakila Alam , Arnob Ghosh , Shaahin Angizi

Large Language Models (LLMs) have become increasingly capable of handling diverse tasks with the aid of well-crafted prompts and integration of external tools, but as task complexity rises, the workflow involving LLMs can be complicated and…

Artificial Intelligence · Computer Science 2024-06-21 Honghua Dong , Qidong Su , Yubo Gao , Zhaoyu Li , Yangjun Ruan , Gennady Pekhimenko , Chris J. Maddison , Xujie Si

Large language model (LLM) agents integrate external tools with one or more LLMs to accomplish specific tasks. Agents have rapidly been adopted by developers, and they are starting to be deployed in industrial workflows, such as their use…

Software Engineering · Computer Science 2026-02-03 Sungmin Kang , Haifeng Ruan , Abhik Roychoudhury