English
Related papers

Related papers: What Do Evolutionary Coding Agents Evolve?

200 papers

Large language models (LLMs) have shown remarkable performance on various tasks, but existing evaluation benchmarks are often static and insufficient to fully assess their robustness and generalization in realistic scenarios. Prior work…

Computation and Language · Computer Science 2025-07-01 JiaRu Wu , Mingwei Liu

How to evaluate Large Language Models (LLMs) in code generation is an open question. Existing benchmarks demonstrate poor alignment with real-world code repositories and are insufficient to evaluate the coding abilities of LLMs. This paper…

Computation and Language · Computer Science 2024-04-02 Jia Li , Ge Li , Xuanming Zhang , Yihong Dong , Zhi Jin

Large Language Models (LLMs) have unveiled remarkable capabilities in understanding and generating both natural language and code, but LLM reasoning is prone to hallucination and struggle with complex, novel scenarios, often getting stuck…

Neural and Evolutionary Computing · Computer Science 2025-05-12 Antonio Jimeno Yepes , Pieter Barnard

Robot navigation is a crucial task with applications to social robots in dynamic human environments. While Reinforcement Learning (RL) has shown great promise for this problem, the policy quality is highly sensitive to the specification of…

Robotics · Computer Science 2026-05-13 Zhikai Zhao , Chuanbo Hua , Federico Berto , Zihan Ma , Kanghoon Lee , Jiachen Li , Jinkyoo Park

The process of extracting valuable and novel insights from raw data involves a series of complex steps. In the realm of Automated Machine Learning (AutoML), a significant research focus is on automating aspects of this process, specifically…

Machine Learning · Computer Science 2024-02-06 Rafael Barbudo , Aurora Ramírez , José Raúl Romero

The digital transformation of automation places new demands on data acquisition and processing in industrial processes. Logical relationships between acquired data and cyclic process sequences must be correctly interpreted and evaluated. To…

Neural and Evolutionary Computing · Computer Science 2023-04-13 Marlon Löppenberg , Andreas Schwung

Large Language Models (LLMs) exhibit world knowledge and inference capabilities, making them powerful tools for various applications. This paper proposes a feedback loop mechanism that leverages these capabilities to tune Evolution…

Machine Learning · Computer Science 2024-05-21 Oliver Kramer

Causal inference is central to scientific discovery, yet choosing appropriate methods remains challenging because of the complexity of both statistical methodology and real-world data. Inspired by the success of artificial intelligence in…

Artificial Intelligence · Computer Science 2026-04-07 Can Wang , Hongyu Zhao , Yiqun Chen

Code translation is a crucial task in software development and maintenance. While recent advancements in large language models (LLMs) have improved automated code translation accuracy, these gains often come at the cost of increased…

Software Engineering · Computer Science 2025-10-22 Yanlin Wang , Rongyi Ou , Yanli Wang , Mingwei Liu , Jiachi Chen , Ensheng Shi , Xilin Liu , Yuchi Ma , Zibin Zheng

Pre-trained Vision-Language Models (VLMs) have been exploited in various Computer Vision tasks (e.g., few-shot recognition) via model adaptation, such as prompt tuning and adapters. However, existing adaptation methods are designed by human…

Computer Vision and Pattern Recognition · Computer Science 2025-08-05 Kun Ding , Ying Wang , Shiming Xiang

Software logs record system activities, aiding maintainers in identifying the underlying causes for failures and enabling prompt mitigation actions. However, maintainers need to inspect a large volume of daily logs to identify the anomalous…

Software Engineering · Computer Science 2023-08-16 Yintong Huo , Cheryl Lee , Yuxin Su , Shiwen Shan , Jinyang Liu , Michael R. Lyu

Understanding a program's runtime reasoning behavior, meaning how intermediate states and control flows lead to final execution results, is essential for reliable code generation, debugging, and automated reasoning. Although large language…

Software Engineering · Computer Science 2025-12-02 Mohammad Abdollahi , Khandaker Rifah Tasnia , Soumit Kanti Saha , Jinqiu Yang , Song Wang , Hadi Hemmati

Recent advances in large multimodal models (LMMs) have enabled impressive reasoning and perception abilities, yet most existing training pipelines still depend on human-curated data or externally verified reward models, limiting their…

Computer Vision and Pattern Recognition · Computer Science 2026-03-16 Omkar Thawakar , Shravan Venkatraman , Ritesh Thawkar , Abdelrahman Shaker , Hisham Cholakkal , Rao Muhammad Anwer , Salman Khan , Fahad Khan

Large language models (LLMs) have made impressive progress in natural language processing. These models rely on proper human instructions (or prompts) to generate suitable responses. However, the potential of LLMs are not fully harnessed by…

Computation and Language · Computer Science 2023-10-24 Xinyu Hu , Pengfei Tang , Simiao Zuo , Zihan Wang , Bowen Song , Qiang Lou , Jian Jiao , Denis Charles

We introduce EvaLearn, a pioneering benchmark designed to evaluate large language models (LLMs) on their learning capability and efficiency in challenging tasks, a critical, yet underexplored aspect of model potential. EvaLearn contains 648…

Code refactoring is a fundamental software engineering practice aimed at improving code quality and maintainability. Despite its importance, developers often neglect refactoring due to the significant time, effort, and resources it…

Large Language Model (LLM)-guided evolutionary search is increasingly used for automated algorithm discovery, yet most current methods track search progress primarily through executable programs and scalar fitness. Even when…

Computation and Language · Computer Science 2026-05-11 Sichun Luo , Yi Huang , Haochen Luo , Fengyuan Liu , Guanzhi Deng , Lei Li , Qinghua Yao , Zefa Hu , Junlan Feng , Qi Liu

Coding agents represent a new paradigm in automated software engineering, combining the reasoning capabilities of Large Language Models (LLMs) with tool-augmented interaction loops. However, coding agents still have severe limitations.…

Software Engineering · Computer Science 2026-04-06 Tural Mehtiyev , Wesley Assunção

Pre-trained large language models (LLMs) exhibit powerful capabilities for generating natural text. Evolutionary algorithms (EAs) can discover diverse solutions to complex real-world problems. Motivated by the common collective and…

Neural and Evolutionary Computing · Computer Science 2025-03-10 Chao Wang , Jiaxuan Zhao , Licheng Jiao , Lingling Li , Fang Liu , Shuyuan Yang

Building agentic systems that can autonomously self-improve from experience is a longstanding goal of AI. Large language models (LLMs) today primarily self-improve via two mechanisms: self-reflection for context updates, and reinforcement…

Artificial Intelligence · Computer Science 2026-02-26 Lunjun Zhang , Ryan Chen , Bradly C. Stadie