Related papers: UniDebugger: Hierarchical Multi-Agent Framework fo…
Emergency departments worldwide face rising patient volumes, workforce shortages, and variability in triage decisions that threaten the delivery of timely and accurate care. Current triage methods rely primarily on vital signs, routine…
Repairing system crashes discovered by kernel fuzzers like Syzkaller is a critical yet underexplored challenge in software engineering. While recent works have introduced Large Language Model (LLM) based agents for Linux kernel…
Aim: With the advent of LLMs, sophisticated agentic program repair has become viable at large organizations with large codebases. In this work, we develop an Engineering Agent that fixes the source code based on test failures at scale…
Finite Element Analysis (FEA) serves as the cornerstone of modern engineering design. However, its workflow is inherently complex and relies heavily on domain expertise. Although recent efforts have integrated Large Language Models (LLMs)…
Existing benchmarks for hardware design primarily evaluate Large Language Models (LLMs) on isolated, component-level tasks such as generating HDL modules from specifications, leaving repository-scale evaluation unaddressed. We introduce…
Manual software beta testing is costly and time-consuming, while single-agent large language model (LLM) approaches suffer from hallucinations and inconsistent behavior. We propose a multi-agent committee framework in which diverse…
The use of large language models (LLMs) for automated code generation has emerged as a significant focus within AI research. As these pretrained models continue to evolve, their ability to understand and generate complex code structures has…
Bug fixing holds significant importance in software development and maintenance. Recent research has made notable progress in exploring the potential of large language models (LLMs) for automatic bug fixing. However, existing studies often…
Autonomous agents have recently achieved remarkable progress across diverse domains, yet most evaluations focus on short-horizon, fully observable tasks. In contrast, many critical real-world tasks, such as large-scale software development,…
Code translation transforms code between programming languages while preserving functionality, which is critical in software development and maintenance. While traditional learning-based code translation methods have limited effectiveness…
Unlike code completion, debugging requires localizing faults and applying targeted edits. We observe that frontier LLMs often regenerate correct but over-edited solutions during debugging. To evaluate how far LLMs are from precise…
As software grows increasingly complex, the quantity and diversity of concerns to be addressed also rises. To answer this diversity of concerns, developers may end up using multiple programming languages in a single software project, a…
LLMs generate buggy code: 29.6% of SWE-bench solved patches fail, 62% of BaxBench solutions have vulnerabilities, and existing tools only catch 65% of bugs with 35% false positives. We built CodeX-Verify, a multi-agent system that uses four…
The widespread adoption of open-source software (OSS) has accelerated software innovation but also increased security risks due to the rapid propagation of vulnerabilities and silent patch releases. In recent years, large language models…
This paper presents a novel framework for automated code generation and debugging, designed to improve accuracy, efficiency, and scalability in software development. The proposed system integrates three core components LangGraph, GLM4…
Visual compliance verification is a critical yet underexplored problem in computer vision, especially in domains such as media, entertainment, and advertising where content must adhere to complex and evolving policy rules. Existing methods…
Automated software debugging is a crucial task for improving the productivity of software developers. Many neural-based techniques have been proven effective for debugging-related tasks such as bug localization and program repair (or bug…
Software development life cycle is profoundly influenced by bugs: their introduction, identification, and eventual resolution account for a significant portion of software cost. This has motivated software engineering researchers and…
Large language models (LLMs) have advanced code generation from single-function tasks to competitive-programming problems, but existing multi-agent solutions either rely on costly large-scale (>30B) models or collapse when downsized to…
LLMs are transforming software development, yet current code generation and code repair benchmarks mainly assess syntactic and functional correctness in simple, single-error cases. LLMs' capabilities to autonomously find and fix runtime…