Related papers: MARCO: Multi-Agent Code Optimization with Real-Tim…

Optimizing scientific software is a difficult task because codebases are often large and complex, and performance can depend upon several factors including the algorithm, its implementation, and hardware among others. Causes of poor…

Combinatorial optimization problems involving multiple agents are notoriously challenging due to their NP-hard nature and the necessity for effective agent coordination. Despite advancements in learning-based methods, existing approaches…

While large language models (LLMs) have recently made tremendous progress towards solving challenging AI problems, they have done so at increasingly steep computational and API costs. We propose a novel strategy where we combine multiple…

Large language models (LLMs) show the promise in supporting scientific research implementation, yet their ability to generate correct and executable code remains limited. Existing works largely adopt one-shot settings, ignoring the…

Large language models (LLMs) have demonstrated strong code generation capabilities, yet the runtime performance of generated code is not guaranteed, and there have been few attempts to train LLMs using runtime performance as a reward in the…

In this paper, we present NEMO, a system that translates Natural-language descriptions of decision problems into formal Executable Mathematical Optimization implementations, operating collaboratively with users or autonomously. Existing…

In this study, we propose VibeCodeHPC, a multi-agent system based on large language models (LLMs) for the automatic tuning of high-performance computing (HPC) programs on supercomputers. VibeCodeHPC adopts Claude Code as its backend and…

Large language models (LLMs) typically operate in a question-answering paradigm, where the quality of the input prompt critically affects the response. Automated Prompt Optimization (APO) aims to overcome the cognitive biases of manually…

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…

Large language models (LLMs) have achieved remarkable success in natural language tasks, but their inference incurs substantial computational and memory overhead. To improve efficiency, parallel decoding methods like Skeleton-of-Thought…

Although LLM-based agents have attracted significant attention in domains such as software engineering and machine learning research, their role in advancing combinatorial optimization (CO) remains relatively underexplored. This gap…

Recent advances in large language models (LLMs) have given rise to powerful coding agents, making it possible for code assistants to evolve into code engineers. However, existing methods still face significant challenges in achieving…

Register Transfer Level(RTL) code optimization is crucial for achieving high performance and low power consumption in digital circuit design. However, traditional optimization methods often rely on manual tuning and heuristics, which can be…

To address the limitations of Large Language Models (LLMs) in the International Classification of Diseases (ICD) coding task, where they often produce inaccurate and incomplete prediction results due to the high-dimensional and skewed…

Sample efficiency remains a key challenge in multi-agent reinforcement learning (MARL). A promising approach is to learn a meaningful latent representation space through auxiliary learning objectives alongside the MARL objective to aid in…

Large Language Models (LLMs) excel at code-related tasks but often struggle in realistic software repositories, where project-specific APIs and cross-file dependencies are crucial. Retrieval-augmented methods mitigate this by injecting…

Neural Combinatorial Optimization (NCO) is an emerging domain where deep learning techniques are employed to address combinatorial optimization problems as a standalone solver. Despite their potential, existing NCO methods often suffer from…

While large language models (LLMs) have shown strong performance in math and logic reasoning, their ability to handle combinatorial optimization (CO) -- searching high-dimensional solution spaces under hard constraints -- remains…

Addressing the challenge of effectively processing long contexts has become a critical issue for Large Language Models (LLMs). Two common strategies have emerged: 1) reducing the input length, such as retrieving relevant chunks by…

The optimal assignment of Large Language Models (LLMs) to specialized roles in multi-agent systems is a significant challenge, defined by a vast combinatorial search space, expensive black-box evaluations, and an inherent trade-off between…