Related papers: Huxley-G\"odel Machine: Human-Level Coding Agent D…

Automatic code generation has gained significant momentum with the advent of Large Language Models (LLMs) such as GPT-4. Although many studies focus on improving the effectiveness of LLMs for code generation, very limited work tries to…

Large language models (LLMs) have fundamentally transformed automated software development by enabling direct translation of natural language descriptions into functional code, driving commercial adoption through tools like Github Copilot…

Large Language Models (LLMs) show promise for automated code optimization but struggle without performance context. This work introduces Opal, a modular framework that connects performance analytics insights with the vast body of published…

Large language model (LLM)-powered multi-agent systems (MAS) have demonstrated cognitive and execution capabilities that far exceed those of single LLM agents, yet their capacity for self-evolution remains hampered by underdeveloped memory…

We present AgentGA, a framework that evolves autonomous code-generation runs by optimizing the agent seed: the task prompt plus optional parent archives that initialize a fresh workspace. The outer loop searches over these reusable starting…

The performance of modern AI systems is fundamentally constrained by the quality of their underlying kernels, which translate high-level algorithmic semantics into low-level hardware operations. Achieving near-optimal kernels requires…

To accelerate mechanical design and enhance design quality and innovation, we present a Multidisciplinary Design and Optimization (MDO) Agent driven by Large Language Models (LLMs). The agent semi-automates the end-to-end workflow by…

Large language models (LLMs) are increasingly used as simulated participants in social science experiments, but their behavior is often unstable and highly sensitive to design choices. Prior evaluations frequently conflate base-model…

Recently, the frontier of Large Language Model (LLM) capabilities has shifted from single-turn code generation to agentic software engineering-a paradigm where models autonomously navigate, edit, and test complex repositories. While…

Although Large Language Models (LLMs) have demonstrated remarkable code-generation ability, they still struggle with complex tasks. In real-world software development, humans usually tackle complex tasks through collaborative teamwork, a…

Multimodal Large Language Models (MLLMs) have achieved notable success in enhancing translation performance by integrating multimodal information. However, existing research primarily focuses on image-guided methods, whose applicability is…

Formal verification offers a path to provably correct software, but writing verified code remains expensive enough that the technique is rarely used in production. Recent large language models can accelerate this work, and recent benchmarks…

The development of LLM-based autonomous agents for end-to-end software development represents a significant paradigm shift in software engineering. However, the scientific evaluation of these systems is hampered by significant challenges,…

With software maintenance accounting for 50% of the cost of developing software, enhancing code quality and reliability has become more critical than ever. In response to this challenge, this doctoral research proposal aims to explore…

LLM-based agents for machine learning engineering (MLE) predominantly rely on tree search, a form of gradient-free optimization that uses scalar validation scores to rank candidates. As LLM reasoning capabilities improve, exhaustive…

Code has emerged as a precise and executable medium for reasoning and action in the agent era. Yet, progress has largely focused on language-centric tasks such as program synthesis and debugging, leaving visual-centric coding underexplored.…

To address the gaps between the static pre-set "thinking-planning-action" of humanoid robots in unfamiliar scenarios and the highly programmed "call tool-return result" due to the lack of autonomous coding capabilities, this work designs a…

Agentic AI systems built on large language models (LLMs) offer significant potential for automating complex workflows, from software development to customer support. However, LLM agents often underperform due to suboptimal configurations;…

Recent advancements in large language models (LLMs) have greatly improved code generation, specifically at the function level. For instance, GPT-4o has achieved a 91.0\% pass rate on HumanEval. However, this draws into question the adequacy…

Large Language Model (LLM) tools have demonstrated their potential to deliver high-quality assistance by providing instant, personalized feedback that is crucial for effective programming education. However, many of these tools operate…