Related papers: Multi-Agent Code Verification via Information Theo…

Agent-based program repair offers to automatically resolve complex bugs end-to-end by combining the planning, tool use, and code generation abilities of modern LLMs. Recent work has explored the use of agent-based repair approaches on the…

Large Language Models (LLMs) have transformed software development and AI applications. While LLMs are designed for text processing, LLM agents extend this capability by enabling autonomous actions, tool use, and multi-step task completion.…

Software bugs cost technology providers (e.g., AT&T) billions annually and cause developers to spend roughly 50% of their time on bug resolution. Traditional methods for bug localization often analyze the suspiciousness of code components…

High quality bugs are key to training the next generation of language model based software engineering (SWE) agents. We introduce a novel method for synthetic generation of difficult and diverse bugs. Our method instructs SWE Agents to…

GitHub issue resolving recently has attracted significant attention from academia and industry. SWE-bench is proposed to measure the performance in resolving issues. In this paper, we propose CodeR, which adopts a multi-agent framework and…

Large language models (LLMs) exhibit strong performance on self-contained programming tasks. However, they still struggle with repository-level software engineering (SWE), which demands (1) deep codebase navigation with effective context…

Large Language Models (LLMs) have revolutionized intelligent application development. While standalone LLMs cannot perform any actions, LLM agents address the limitation by integrating tools. However, debugging LLM agents is difficult and…

Run the same LLM agent on the same task twice: do you get the same behavior? We find the answer is often no. In a study of 3,000 agent runs across three models (Llama 3.1 70B, GPT-4o, and Claude Sonnet 4.5) on HotpotQA, we observe that…

AI coding agents demonstrate strong performance on general-purpose software benchmarks. However, their ability to handle 5G network engineering tasks remains unexplored. We propose SWE-Bench~5G, the first benchmark designed to investigate…

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…

Large Language Model (LLM)-based multi-agent systems are increasingly applied to automate computational workflows in science and engineering. However, how inter-agent dynamics influence reasoning quality and verification reliability remains…

LLM agents have been widely adopted in real-world applications, relying on agent frameworks for workflow execution and multi-agent coordination. As these systems scale, understanding bugs in the underlying agent frameworks becomes critical.…

Agentic AI and Multi-Agent Systems are poised to dominate industry and society imminently. Powered by goal-driven autonomy, they represent a powerful form of generative AI, marking a transition from reactive content generation into…

Large language models (LLMs) have shown promise for automated patching, but their effectiveness depends strongly on how they are integrated into patching systems. While prior work explores prompting strategies and individual agent designs,…

Large Language Model (LLM) agents, which integrate planning, memory, reflection, and tool-use modules, have shown promise in solving complex, multi-step tasks. Yet their sophisticated architectures amplify vulnerability to cascading…

SWE-Bench-Verified, a dataset comprising 500 issues, serves as a de facto benchmark for evaluating various large language models (LLMs) on their ability to resolve GitHub issues. But this benchmark may overlap with model training data. If…

Coding agents represent a new paradigm in automated software engineering, combining the reasoning capabilities of Large Language Models (LLMs) with tool-augmented interaction loops. However, coding agents still have severe limitations.…

Large Language Models (LLMs) in Software Engineering (SE) can offer assistance for coding. To facilitate a rigorous evaluation of LLMs in practical coding contexts, Carlos et al. introduced the SWE-bench dataset, which comprises 2,294…

Multi-agent systems achieve state-of-the-art outcomes through peer collaboration. However, when an agent in the pipeline silently drops a constraint, the system's final output may look correct even though the reasoning chain was quietly…

The proliferation of Large Language Models (LLMs) in recent years has realized many applications in various domains. Being trained with a huge of amount of data coming from various sources, LLMs can be deployed to solve different tasks,…