Related papers: SWE-Master: Unleashing the Potential of Software E…

The convergence of large language models and agents is catalyzing a new era of scientific discovery: Agentic Science. While the scientific method is inherently iterative, existing agent frameworks are predominantly static, narrowly scoped,…

In recent years, Large Language Models (LLMs) have achieved remarkable progress in automated code generation. In real-world software engineering, the growing demand for rapid iteration and continuous delivery underscores the importance of…

Context: Empirical Software Engineering (ESE) faces increasing challenges due to data scale, methodological complexity, and reproducibility concerns. Large Language Models (LLMs) have emerged as promising tools to support empirical…

This study evaluates large language models (LLMs) in generating code from algorithm descriptions in recent NLP papers. The task requires two key competencies: (1) algorithm comprehension: synthesizing information from papers and academic…

Current code-agent benchmarks primarily evaluate localized issue resolution within a single target repository, leaving under-tested many software engineering tasks that require external knowledge or broader repository-level changes. We…

The emergence of "vibe coding" platforms, where users describe applications in natural language and AI agents autonomously generate full-stack software, has created a need for rigorous evaluation beyond code-level benchmarks. In order to…

Test-time scaling has become a powerful way to improve large language models. However, existing methods are best suited to short, bounded outputs that can be directly compared, ranked or refined. Long-horizon coding agents violate this…

Software engineering agents (swe-agents), as key innovations in intelligent software engineering, are poised in the industry's end-of-programming debate to transcend from assistance to primary roles. we argue the importance of swe-agents'…

The advent of Large Language Models (LLMs) has spurred the development of coding agents for real-world code generation. As a widely used benchmark for evaluating the code generation capabilities of these agents, SWE-Bench uses real-world…

Large language models (LLMs) have shown strong reasoning and coding capabilities, yet they struggle to generalize to real-world software engineering (SWE) problems that are long-horizon and out of distribution. Existing systems often rely…

Composer 2 is a specialized model designed for agentic software engineering. The model demonstrates strong long-term planning and coding intelligence while maintaining the ability to efficiently solve problems for interactive use. The model…

Despite the rapid advancements in LLM agents, they still face the challenge of generating meaningful reflections due to inadequate error analysis and a reliance on rare successful trajectories, especially in complex tasks. In this work, we…

In recent years, Large Language Models (LLMs) have achieved remarkable success and have been widely used in various downstream tasks, especially in the tasks of the software engineering (SE) field. We find that many studies combining LLMs…

Resolving issues on code repositories is an important part of software engineering. Various recent systems automatically resolve issues using large language models and agents, often with impressive performance. Unfortunately, most of these…

Scaling test-time compute is a promising axis for improving LLM capabilities. However, test-time compute can be scaled in a variety of ways, and effectively combining different approaches remains an active area of research. Here, we explore…

Large language model (LLM) agents need to perform multi-turn interactions in real-world tasks. However, existing multi-turn RL algorithms for optimizing LLM agents fail to perform effective credit assignment over multiple turns while…

Large Language Models (LLMs) face persistent and evolving trustworthiness issues, motivating developers to seek automated and flexible repair methods that enable convenient deployment across diverse scenarios. Existing repair methods like…

We introduce Agent2 RL-Bench, a compact diagnostic benchmark for evaluating agentic RL post-training, which tests whether LLM agents can autonomously design, implement, debug, and execute post-training pipelines that improve foundation…

The task of issue resolving is to modify a codebase to generate a patch that addresses a given issue. However, existing benchmarks, such as SWE-bench, focus almost exclusively on Python, making them insufficient for evaluating Large…

Tool use has turned large language models (LLMs) into powerful agents that can perform complex multi-step tasks by dynamically utilising external software components. However, these tools must be implemented in advance by human developers,…