Related papers: Coherence Collapse: Diagnosing Why Code Agents Fai…
Resolving real-world software engineering (SWE) issues with autonomous agents requires complex, long-horizon reasoning. Current pipelines are bottlenecked by unoptimized demonstration data, sparse execution rewards, and computationally…
AI coding agents can resolve real-world software issues, yet they frequently introduce regressions -- breaking tests that previously passed. Current benchmarks focus almost exclusively on resolution rate, leaving regression behavior…
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…
Automatic program repair at project level may open yet to be seen opportunities in various fields of human activity. Since the SWE-Bench challenge was presented, we have seen numerous of solutions. Patch generation is a part of program…
LLMs increasingly require surgical model editing to enhance domain-specific capabilities without incurring the computational cost or catastrophic forgetting associated with full fine-tuning. Sparse Autoencoders (SAEs) have emerged as a…
Repository-level code agents have shown strong promise in real-world feature addition tasks, making reliable evaluation of their capabilities increasingly important. However, existing benchmarks primarily evaluate these agents as black…
As agentic coding systems decompose work across multiple model instances, a critical safety question is whether those instances can coordinate to achieve a hidden malicious objective while remaining aligned with user intent. We introduce…
We present SWE-Gym, the first environment for training real-world software engineering (SWE) agents. SWE-Gym contains 2,438 real-world Python task instances, each comprising a codebase with an executable runtime environment, unit tests, and…
LLM agents are expected to complete end-to-end units of work across software tools, business services, and local workspaces. Yet many agent benchmarks freeze a curated task set at release time and grade mainly the final response, making it…
LLM-agent training pipelines routinely discard failed trajectories even though GPT-4o achieves only 14-20% on WebArena and below 55% pass@1 on ToolBench; even specialised systems at 50-65% leave the majority of trajectories unused. We…
Agent skills today are static artifact: authored once -- by human curation or one-shot generation from parametric knowledge -- and then consumed unchanged, with no mechanism to improve from real use. We propose \textbf{SkillEvolver}, a…
Identifying which software versions are affected by a vulnerability is critical for patching, risk mitigation. Despite a growing body of tools, their real-world effectiveness remains unclear due to narrow evaluation scopes often limited to…
Evaluating and improving the security capabilities of code agents requires high-quality, executable vulnerability tasks. However, existing works rely on costly, unscalable manual reproduction and suffer from outdated data distributions. To…
We introduce SWE-ZERO to SWE-HERO, a two-stage SFT recipe that achieves state-of-the-art results on SWE-bench by distilling open-weight frontier LLMs. Our pipeline replaces resource-heavy dependencies with an evolutionary refinement…
LLM-based code agents treat repositories as unstructured text, applying edits through brittle string matching that frequently fails due to formatting drift or ambiguous patterns. We propose reframing the codebase as a structured action…
Software vulnerabilities can cause numerous problems, including crashes, data loss, and security breaches. These issues greatly compromise quality and can negatively impact the market adoption of software applications and systems.…
In recent years, AI-based software engineering has progressed from pre-trained models to advanced agentic workflows, with Software Development Agents representing the next major leap. These agents, capable of reasoning, planning, and…
Achieving mastery in real world software engineering tasks is fundamentally bottlenecked by the scarcity of large scale, high quality training data. Scaling such data has been limited by the complexity of environment setup, unit test…
Automated environment configuration is a critical bottleneck in scaling software engineering (SWE) automation. To provide a reliable evaluation standard for this task, we present Multi-Docker-Eval benchmark. It includes 40 real-world…
Large Language Models (LLMs) have enabled intelligent agents that autonomously interact with environments and invoke external tools. Recently, agent-based software repair has drawn wide attention, as repair agents can localize bugs,…