Related papers: SWE-Next: Scalable Real-World Software Engineering…
Agents aspire to eliminate the need for task-specific prompt crafting through autonomous reason-act-observe loops. Still, they are commonly instructed to follow a task-specific plan for guidance, e.g., to resolve software issues following…
The deployment of coding agents in privacy-sensitive and resource-constrained environments drives the demand for capable open-weight Small Language Models (SLMs). However, they suffer from a fundamental capability gap: unlike frontier large…
LLM agents have demonstrated remarkable capabilities in software development, but their performance is hampered by long interaction contexts, which incur high API costs and latency. While various context compression approaches such as…
Large Language Models (LLMs) have recently attracted wide interest for tackling software engineering tasks. In contrast to code generation, refactoring demands precise, semantics-preserving edits that improve program structure, which also…
Verification is critical for improving agents: it provides the reward signal for Reinforcement Learning and enables inference-time gains through Test-Time Scaling (TTS). Despite its importance, verification in software engineering (SWE)…
We tackle the challenge of training reliable code-fixing agents in real repositories, where complex builds and shifting dependencies make evaluation unstable. We developed a verifiable pipeline with success defined as post-fix build…
Prior representative ReAct-style approaches in autonomous Software Engineering (SWE) typically lack the explicit System-2 reasoning required for deep analysis and handling complex edge cases. While recent reasoning models demonstrate the…
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…
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…
Foundation models (FMs), particularly large language models (LLMs), have shown significant promise in various software engineering (SE) tasks, including code generation, debugging, and requirement refinement. Despite these advances,…
A software engineering issue (SWE issue) is easier to resolve when accompanied by a reproduction test. Unfortunately, most issues do not come with functioning reproduction tests, so this paper explores how to generate them automatically.…
High-quality labeled datasets are crucial for training and evaluating foundation models in software engineering, but creating them is often prohibitively expensive and labor-intensive. We introduce SPICE, a scalable, automated pipeline for…
Background: Sustainable software engineering (SSE) means creating software in a way that meets present needs without undermining our collective capacity to meet our future needs. It is typically conceptualized as several intersecting…
Existing traffic engineering (TE) solutions performs well for software defined network (SDN) in average cases. However, during peak hours, bursty traffic spikes are challenging to handle, because it is difficult to react in time and…
Research on applications of reinforcement learning (RL) to large language models has mostly been focused on single-turn problems, such as mathematical reasoning or single-shot code generation. While these problems can be viewed as…
This paper explores Site Reliability Engineering (SRE), a modern approach to maintaining scalable and reliable software systems. It presents observations on how structured SRE processes improve operational efficiency, reduce system…
Large Language Model (LLM) agents are increasingly deployed for complex, multi-step software engineering (SWE) tasks. However, their trajectories often contain costly inefficiencies, such as redundant exploration, looping, and failure to…
While Sustainable Software Engineering (SSE) tools are widely studied in academia, their practical feasibility in industrial workflows, particularly in regulated environments, remains poorly understood. This study investigates how software…
The SWE-Bench Verified leaderboard is approaching saturation, with the top system achieving 78.80%. However, we show that this performance is inflated. Our re-evaluation reveals that one in five "solved" patches from the top-30 agents are…
World models are central to building agents that can reason, plan, and generalize beyond their training data. However, research on world models is currently fragmented, with disparate codebases, data pipelines, and evaluation protocols…