Related papers: GA4GC: Greener Agent for Greener Code via Multi-Ob…
This study presents a comprehensive empirical evaluation of six state-of-the-art large language models (LLMs) for code generation, including both general-purpose and code-specialized models. Using a dataset of 944 real-world LeetCode…
Large Language Models (LLM) are increasingly used for software development, yet existing benchmarks for LLM-based coding assistance do not reflect the constraints of High Energy Physics (HEP) and High Performance Computing (HPC) software.…
As the quality of code generated by Large Language Models (LLMs) improves, their adoption in the software industry for automated code generation continues to grow. Researchers primarily focus on enhancing the functional correctness of the…
Autonomous AI coding agents are becoming a core tool for ML practitioners in industry and research alike. Despite this growing adoption, no standardized benchmark exists to evaluate their ability to design, implement, and train models from…
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…
3D Gaussian splatting (3DGS) is a transformative technique with profound implications on novel view synthesis and real-time rendering. Given its importance, there have been many attempts to improve its performance. However, with the…
Large Language Models (LLMs) have become an integral part of many real-world workflows. However, LLMs consume a lot of energy, which becomes a large concern in the scale of the demand for these tools. As LLMs become integrated into…
Large language model (LLM) coding agents increasingly operate at the repository level, motivating benchmarks that evaluate their ability to optimize entire codebases under realistic constraints. Existing code benchmarks largely rely on…
We introduce DA-Code, a code generation benchmark specifically designed to assess LLMs on agent-based data science tasks. This benchmark features three core elements: First, the tasks within DA-Code are inherently challenging, setting them…
The move toward open Sixth-Generation (6G) networks necessitates a novel approach to full-stack simulation environments for evaluating complex technology developments before prototyping and real-world implementation. This paper introduces…
Even though high-level synthesis (HLS) tools mitigate the challenges of programming domain-specific accelerators (DSAs) by raising the abstraction level, optimizing hardware directive parameters remains a significant hurdle. Existing…
Training capable Large Language Model (LLM) agents is critically bottlenecked by the high cost and static nature of real-world interaction data. We address this by introducing GenEnv, a framework that establishes a difficulty-aligned…
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…
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…
The discussion around AI-Engineering, that is, Software Engineering (SE) for AI-enabled Systems, cannot ignore a crucial class of software systems that are increasingly becoming AI-enhanced: Those used to enable or support the SE process,…
Modern causal discovery methods face critical limitations in scalability, computational efficiency, and adaptability to mixed data types, as evidenced by benchmarks on node scalability (30, $\le 50$, $\ge 70$ nodes), computational energy…
Auto-regressive LLM-based software engineering (SWE) agents, henceforth SWE agents, have made tremendous progress (>60% on SWE-Bench Verified) on real-world coding challenges including GitHub issue resolution. SWE agents use a combination…
Effective prompt design is essential for improving the planning capabilities of large language model (LLM)-driven agents. However, existing structured prompting strategies are typically limited to single-agent, plan-only settings, and often…
Optimizing software performance through automated code refinement offers a promising avenue for enhancing execution speed and efficiency. Despite recent advancements in LLMs, a significant gap remains in their ability to perform in-depth…
The global demand for sustainable protein sources has accelerated the need for intelligent tools that can rapidly process and synthesise domain-specific scientific knowledge. In this study, we present a proof-of-concept multi-agent…