Related papers: Beyond Accuracy: Behavioral Dynamics of Agentic Mu…
Automated program repair techniques aim to aid software developers with the challenging task of fixing bugs. In heuristic-based program repair, a search space of program variants, created via mutations on software, is explored to find…
Recent research advocates deploying smaller, specialized code LLMs in agentic frameworks alongside frontier models, sparking interest in efficient strategies for multi-task learning that balance performance, constraints, and costs. We…
Large Language Models (LLMs) often generate code with subtle but critical bugs, especially for complex tasks. Existing automated repair methods typically rely on superficial pass/fail signals, offering limited visibility into program…
We investigate whether giving LLM agents the collaborative tools and autonomy that humans naturally use for problem solving can improve their performance. We equip Claude Code agents with MCP-based social media and journaling tools and…
Translating algorithms from high-level languages like MATLAB to hardware description languages (HDLs) is a resource-intensive but necessary step for deployment on FPGAs and ASICs. While large language models (LLMs) offer a path to…
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,…
Using multiple agents was found to improve the debugging capabilities of Large Language Models. However, increasing the number of LLM-agents has several drawbacks such as increasing the running costs and rising the risk for the agents to…
Diagram-grounded geometry problem solving is a critical benchmark for multimodal large language models (MLLMs), yet the benefits of multi-agent design over single-agent remain unclear. We systematically compare single-agent and multi-agent…
Crash reports are central to software maintenance, yet many lack the diagnostic detail developers need to debug efficiently. We examine whether large language models can enhance crash reports by adding fault locations, root-cause…
Large Language Models (LLMs) frequently generate buggy code with complex logic errors that are challenging to diagnose. While existing LLM-based self-repair approaches conduct intensive static semantic analysis or reply on superficial…
When LLM agents autonomously design ML experiments, do they perform genuine architecture search -- or do they default to hyperparameter tuning within a narrow region of the design space? We answer this question by analyzing 10,469…
Automated program repair has emerged as a powerful technique to mitigate the impact of software bugs on system reliability and user experience. This paper introduces RepairAgent, the first work to address the program repair challenge…
Context: Learning-based automatic program repair techniques are showing promise to provide quality fix suggestions for detected bugs in the source code of the software. These tools mostly exploit historical data of buggy and fixed code…
While significant progress has been made in automating various aspects of software development through coding agents, there is still significant room for improvement in their bug fixing capabilities. Debugging and investigation of runtime…
Automated program repair (APR) aims to help developers improve software reliability by generating patches for buggy programs. Although many code language models (CLM) are developed and effective in many software tasks such as code…
System prompts for LLM-based coding agents are software artifacts that govern agent behavior, yet lack the testing infrastructure applied to conventional software. We present Arbiter, a framework combining formal evaluation rules with…
Large language model-based multi-agent systems have shown great abilities across various tasks due to the collaboration of expert agents, each focusing on a specific domain. However, the impact of clumsy or even malicious agents--those who…
Modern software systems require code that is not only functional but also maintainable and well-structured. Although Large Language Models (LLMs) are increasingly used to automate software development, most studies focus on isolated,…
Tangled code changes, commits that conflate unrelated modifications such as bug fixes, refactorings, and enhancements, introduce significant noise into bug datasets and adversely affect the performance of bug prediction models. Addressing…
Context: Code reviews are crucial for software quality. Recent AI advances have allowed large language models (LLMs) to review and fix code; now, there are tools that perform these reviews. However, their reliability and accuracy have not…