Large Language Model (LLM)-based agents have shown effectiveness across many
applications. However, their use in data science scenarios requiring solving long-term …

Automated Program Repair (APR) aims to automatically generate patches for buggy
programs. Traditional APR techniques suffer from a lack of patch variety as they rely heavily …

Contemporary evaluation techniques are inadequate for agentic systems. These
approaches either focus exclusively on final outcomes--ignoring the step-by-step nature of …

The robustness of LLMs to jailbreak attacks, where users design prompts to circumvent
safety measures and misuse model capabilities, has been studied primarily for LLMs acting …

Large language models (LLMs) for code have become indispensable in various domains,
including code generation, reasoning tasks and agent systems. While open-access code …

Recent advances in large language models (LLMs) have shown significant potential to
automate various software development tasks, including code completion, test generation …

Autonomous program improvement typically involves automatically producing bug fixes and
feature additions. Such program improvement can be accomplished by a combination of …

Large Language Models (LLMs) excel in code generation yet struggle with modern AI
software engineering tasks. Unlike traditional function-level or file-level coding tasks, AI …

We present AutoGLM, a new series in the ChatGLM family, designed to serve as foundation
agents for autonomous control of digital devices through Graphical User Interfaces (GUIs) …

Large language model (LLM) agents have shown great potential in solving real-world
software engineering (SWE) problems. The most advanced open-source SWE agent can …