AI Agent

Rubric Is All You Need: Enhancing LLM-based Code Evaluation With Question-Specific Rubrics

Aditya Pathak, Rachit Gandhi, Vaibhav Uttam, Arnav Ramamoorthy, Pratyush Ghosh, Aaryan Raj Jindal, Shreyash Verma, Aditya Mittal, Aashna Ased, Chirag Khatri, Yashwanth Nakka, Devansh, Jagat Sesh Challa, Dhruv Kumar

机构 * BITS Pilani（比特斯理工学院） 纠错

专题命中 软件智能体 ：agentic(abstract)；分类 cs.AI、cs.SE

Comments Accepted in ICER 2025

Large Language Model Powered Automated Modeling and Optimization of Active Distribution Network Dispatch Problems

Xu Yang, Chenhui Lin, Yue Yang, Qi Wang, Haotian Liu, Haizhou Hua, Wenchuan Wu

专题命中 软件智能体 ：agent(abstract)；分类 cs.AI、cs.LG

VizGenie: Toward Self-Refining, Domain-Aware Workflows for Next-Generation Scientific Visualization

Ayan Biswas, Terece L. Turton, Nishath Rajiv Ranasinghe, Shawn Jones, Bradley Love, William Jones, Aric Hagberg, Han-Wei Shen, Nathan DeBardeleben, Earl Lawrence

机构 * Los Alamos National Laboratory（洛斯阿拉莫斯国家实验室） ； Coastal Carolina University（海岸卡罗来纳大学） ； Ohio State University（俄亥俄州立大学） 纠错

专题命中 软件智能体 ：agentic(abstract)；分类 cs.AI、cs.LG

The AI Definition and a Program Which Satisfies this Definition

Dimiter Dobrev

专题命中 软件智能体 ：agent(abstract)；分类 cs.AI、cs.LG

Journal ref Serdica Journal of Computing 18(1), 2024, pp. 61-96

LLM as a code generator in Agile Model Driven Development

Ahmed R. Sadik, Sebastian Brulin, Markus Olhofer

机构 * Honda Research Institute Europe（本田欧洲研究机构） 纠错

专题命中 软件智能体 ：agent(abstract)；分类 cs.AI、cs.SE

Survey of GenAI for Automotive Software Development: From Requirements to Executable Code

Nenad Petrovic, Vahid Zolfaghari, Andre Schamschurko, Sven Kirchner, Fengjunjie Pan, Chengdng Wu, Nils Purschke, Aleksei Velsh, Krzysztof Lebioda, Yinglei Song, Yi Zhang, Lukasz Mazur, Alois Knoll

机构 * Chair of Robotics, Artificial Intelligence and Real-Time Systems（机器人、人工智能与实时系统教授席） 纠错

专题命中 软件智能体 ：workflow(abstract)；分类 cs.AI、cs.SE

Comments Conference paper accepted for GACLM 2025

Self-Improving Safety Performance of Reinforcement Learning Based Driving with Black-Box Verification Algorithms

Resul Dagdanov, Halil Durmus, Nazim Kemal Ure

机构 * ITU Artificial Intelligence and Data Science Research Center（伊斯坦布尔技术大学人工智能与数据科学研究中心） ； Department of Aeronautical Engineering（航空工程系） ； Eatron Technologies（Eatron技术公司） ； Department of Electronics and Communication Engineering（电子与通信工程系） ； ITU Artificial Intelligence and Data Science Application and Research Center（伊斯坦布尔技术大学人工智能与数据科学应用与研究中心） ； Department of Computer Engineering（计算机工程系） 纠错

专题命中 软件智能体 ：agent(abstract)；分类 cs.AI、cs.LG

Comments 7 pages, 7 figures, 2 tables, published in IEEE International Conference on Robotics and Automation (ICRA), June 2, 2023, London, UK

Journal ref IEEE International Conference on Robotics and Automation (ICRA), 2023, pp. 5631-5637

Fly, Fail, Fix: Iterative Game Repair with Reinforcement Learning and Large Multimodal Models

Alex Zook, Josef Spjut, Jonathan Tremblay

专题命中 软件智能体 ：agent(abstract)；分类 cs.AI、cs.LG

Comments Published at Reinforcement Learning and Video Games workshop https://sites.google.com/view/rlvg-workshop-2025/home

Advancing Retrieval-Augmented Generation for Structured Enterprise and Internal Data

Chandana Cheerla

机构 * IIT Roorkee（罗尔基大学） 纠错

专题命中 软件智能体 ：agent(abstract)；分类 cs.AI、cs.CL

Code Simulation as a Proxy for High-order Tasks in Large Language Models

Emanuele La Malfa, Christoph Weinhuber, Orazio Torre, Fangru Lin, X. Angelo Huang, Samuele Marro, Anthony Cohn, Nigel Shadbolt, Michael Wooldridge

机构 * Department of Computer Science, University of Oxford ； Faculty of Linguistics, Philology ； Phonetics, University of Oxford ； Department of Engineering, University of Oxford ； Department of Computer Science, ETH Zurich ； Faculty of Engineering ； Physical Sciences, University of Leeds ； University of Salerno ； The Alan Turing Institute 纠错

专题命中 软件智能体 ：planning(abstract)；分类 cs.AI、cs.LG

Comments arXiv admin note: substantial text overlap with arXiv:2401.09074 Authors note: this article is a substantial revision of arXiv:2401.09074 (same team) 04/07/2025: We added the Acknowledgments

GAIus: Combining Genai with Legal Clauses Retrieval for Knowledge-based Assistant

Michał Matak, Jarosław A. Chudziak

机构 * Faculty of Electronics and Information Technology（电子与信息技术学院） 纠错

专题命中 软件智能体 ：agent(abstract)；分类 cs.AI、cs.CL

Comments 8 pages, 2 figures, presented at ICAART 2025, in proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART

An AST-guided LLM Approach for SVRF Code Synthesis

Abanoub E. Abdelmalak, Mohamed A. Elsayed, David Abercrombie, Ilhami Torunoglu

机构 * Calibre Yield Enhancement Services（Calibre 良率增强服务） ； Siemens EDA（西门子 EDA） ； Calibre Research & Development（Calibre 研究与开发） ； Calibre Product Management（Calibre 产品管理） 纠错

专题命中 软件智能体 ：workflow(abstract)；分类 cs.AI、cs.SE

Comments 9 Pages, 5 Figures, 2 Tables

VoyagerVision: Investigating the Role of Multi-modal Information for Open-ended Learning Systems

Ethan Smyth, Alessandro Suglia

机构 * School of Mathematical and Computer Sciences（数学与计算机科学学院） ； Heriot-Watt University（赫瑞斯韦大学） 纠错

专题命中 软件智能体 ：agent(abstract)；分类 cs.AI、cs.LG

Comments website: https://esmyth-dev.github.io/VoyagerVision.github.io/

TracLLM: A Generic Framework for Attributing Long Context LLMs

Yanting Wang, Wei Zou, Runpeng Geng, Jinyuan Jia

机构 * Pennsylvania State University（宾夕法尼亚州立大学） 纠错

专题命中 软件智能体 ：agent(abstract)；分类 cs.AI、cs.LG

Comments To appear in USENIX Security Symposium 2025. The code and data are at: https://github.com/Wang-Yanting/TracLLM

Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering Tasks

Hongyuan Tao, Ying Zhang, Zhenhao Tang, Hongen Peng, Xukun Zhu, Bingchang Liu, Yingguang Yang, Ziyin Zhang, Zhaogui Xu, Haipeng Zhang, Linchao Zhu, Rui Wang, Hang Yu, Jianguo Li, Peng Di

机构 * Ant Group（蚂蚁集团） ； ShanghaiTech University（上海科技大学） ； Zhejiang University（浙江大学） ； Shanghai Jiaotong University（上海交通大学） 纠错

专题命中 软件智能体 ：agent(abstract)；分类 cs.LG、cs.SE

Comments 35 pages, 10 figures

Steering Conceptual Bias via Transformer Latent-Subspace Activation

Vansh Sharma, Venkat Raman

专题命中 软件智能体 ：agentic(abstract)；分类 cs.AI、cs.LG

Large Language Model Guided Self-Debugging Code Generation

Muntasir Adnan, Zhiwei Xu, Carlos C. N. Kuhn

机构 * Open Source Institute, Faculty of Science and Technology, University of Canberra（开源研究院，科学与技术学院，堪培拉大学） 纠错

专题命中 软件智能体 ：agent(abstract)；分类 cs.AI、cs.SE

GenerationPrograms: Fine-grained Attribution with Executable Programs

David Wan, Eran Hirsch, Elias Stengel-Eskin, Ido Dagan, Mohit Bansal

机构 * UNC Chapel Hill（北卡罗来纳大学教堂山分校） ； Bar-Ilan University（巴伊兰大学） 纠错

专题命中 软件智能体 ：agent(abstract)；分类 cs.AI、cs.CL

Comments 27 Pages. Code: https://github.com/meetdavidwan/generationprograms

A Fast, Reliable, and Secure Programming Language for LLM Agents with Code Actions

Stephen Mell, Botong Zhang, David Mell, Shuo Li, Ramya Ramalingam, Nathan Yu, Steve Zdancewic, Osbert Bastani

专题命中 软件智能体 ：agent(abstract)；分类 cs.AI、cs.LG

Robot-Gated Interactive Imitation Learning with Adaptive Intervention Mechanism

Haoyuan Cai, Zhenghao Peng, Bolei Zhou

机构 * Computer Science Department, University of California, Los Angeles (UCLA)（加州大学洛杉矶分校计算机科学系） 纠错

专题命中 软件智能体 ：agent(abstract)；分类 cs.AI、cs.LG

Comments ICML 2025 Poster

Training Software Engineering Agents and Verifiers with SWE-Gym

Jiayi Pan, Xingyao Wang, Graham Neubig, Navdeep Jaitly, Heng Ji, Alane Suhr, Yizhe Zhang

专题命中 软件智能体 ：agent(abstract)；分类 cs.CL、cs.SE

Comments Accepted at ICML 2025. Code at https://github.com/SWE-Gym/SWE-Gym

The Hitchhiker's Guide to Program Analysis, Part II: Deep Thoughts by LLMs

Haonan Li, Hang Zhang, Kexin Pei, Zhiyun Qian

机构 * UC Riverside（UC河滨分校） ； Indiana University（印第安纳大学） ； University of Chicago（芝加哥大学） 纠错

专题命中 软件智能体 ：workflow(abstract)；分类 cs.AI、cs.SE

Enhancing LLM-Based Code Generation with Complexity Metrics: A Feedback-Driven Approach

Melika Sepidband, Hamed Taherkhani, Song Wang, Hadi Hemmati

机构 * Lassonde School of Eng. York University（埃克塞特工程学院约克大学） 纠错

专题命中 软件智能体 ：agent(abstract)；分类 cs.AI、cs.SE

Comments 11 pages, 5 figures. Accepted to COMPSAC 2025

Beyond The Rainbow: High Performance Deep Reinforcement Learning on a Desktop PC

Tyler Clark, Mark Towers, Christine Evers, Jonathon Hare

专题命中 软件智能体 ：agent(abstract)；分类 cs.AI、cs.LG

Comments 9 main pages, 28 total. Accepted at ICML 2025 (Poster)

DynamicRAG: Leveraging Outputs of Large Language Model as Feedback for Dynamic Reranking in Retrieval-Augmented Generation

Jiashuo Sun, Xianrui Zhong, Sizhe Zhou, Jiawei Han

机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） 纠错

专题命中 软件智能体 ：agent(abstract)；分类 cs.AI、cs.CL

Comments 24 pages, 7 figures, 15 tables

On Minimizing Adversarial Counterfactual Error in Adversarial RL

Roman Belaire, Arunesh Sinha, Pradeep Varakantham

机构 * Singapore Management University（新加坡国立管理学院） ； Rutgers University（罗格斯大学） 纠错

专题命中 软件智能体 ：agent(abstract)；分类 cs.AI、cs.LG

Comments Presented at ICLR 2025

Empowering AI to Generate Better AI Code: Guided Generation of Deep Learning Projects with LLMs

Chen Xie, Mingsheng Jiao, Xiaodong Gu, Beijun Shen

机构 * School of Computer Science, Shanghai Jiao Tong University（计算机科学学院，上海交通大学） 纠错

专题命中 软件智能体 ：planning(abstract)；分类 cs.AI、cs.SE

Migrating Code At Scale With LLMs At Google

Celal Ziftci, Stoyan Nikolov, Anna Sjövall, Bo Kim, Daniele Codecasa, Max Kim

专题命中 软件智能体 ：workflow(abstract)；分类 cs.AI、cs.SE

Evaluating Large Language Models in Code Generation: INFINITE Methodology for Defining the Inference Index

Nicholas Christakis, Dimitris Drikakis

专题命中 软件智能体 ：workflow(abstract)；分类 cs.AI、cs.SE

Comments 20 pages, 6 figures

Journal ref Appl. Sci. 2025, 15, 3784

On Simulation-Guided LLM-based Code Generation for Safe Autonomous Driving Software

Ali Nouri, Johan Andersson, Kailash De Jesus Hornig, Zhennan Fei, Emil Knabe, Hakan Sivencrona, Beatriz Cabrero-Daniel, Christian Berger

专题命中 软件智能体 ：agent(abstract)；分类 cs.AI、cs.SE

Comments Accepted in the 29th International Conference on Evaluation and Assessment in Software Engineering (EASE)