AI Agent

Beyond Domain Randomization: Event-Inspired Perception for Visually Robust Adversarial Imitation from Videos

Andrea Ramazzina, Vittorio Giammarino, Matteo El-Hariry, Mario Bijelic

机构 * Mercedes-Benz AG（梅赛德斯-奔驰集团） ； Technical University of Munich（慕尼黑技术大学） ； Purdue University（普渡大学） ； Space Robotics Research Group, SnT, University of Luxembourg（卢森堡大学空间机器人研究组） ； Torc Robotics（Torc机器人公司） ； Princeton University（普林斯顿大学） 纠错

专题命中 软件智能体 ：agent(abstract)；分类 cs.LG

Fixing 7,400 Bugs for 1$: Cheap Crash-Site Program Repair

Han Zheng, Ilia Shumailov, Tianqi Fan, Aiden Hall, Mathias Payer

专题命中 软件智能体 ：agent(abstract)；分类 cs.SE

Code Retrieval for MILP Instance Generation

Tianxing Yang, Huigen Ye, Hua Xu

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

GE-Chat: A Graph Enhanced RAG Framework for Evidential Response Generation of LLMs

Longchao Da, Parth Mitesh Shah, Kuan-Ru Liou, Jiaxing Zhang, Hua Wei

机构 * Arizona State University（亚利桑那州立大学） ； New Jersey Institute of Technology（新泽西理工学院） ； Arizona（亚利桑那） ； New Jersey（新泽西） 纠错

专题命中 软件智能体 ：agent(abstract)；分类 cs.CL

Comments 5 pages, 4 figures, accepted to IJCAI2025 demo track

MLE-Dojo: Interactive Environments for Empowering LLM Agents in Machine Learning Engineering

Rushi Qiang, Yuchen Zhuang, Yinghao Li, Dingu Sagar V K, Rongzhi Zhang, Changhao Li, Ian Shu-Hei Wong, Sherry Yang, Percy Liang, Chao Zhang, Bo Dai

机构 * Georgia Institute of Technology（佐治亚理工学院） ； Stanford University（斯坦福大学） 纠错

专题命中 软件智能体 ：agent(abstract)；分类 cs.LG

Web-Bench: A LLM Code Benchmark Based on Web Standards and Frameworks

Kai Xu, YiWei Mao, XinYi Guan, ZiLong Feng

机构 * ByteDance（字节跳动） 纠错

专题命中 软件智能体 ：agent(abstract)；分类 cs.AI

Comments 28 pages, 15 figures

Private LoRA Fine-tuning of Open-Source LLMs with Homomorphic Encryption

Jordan Frery, Roman Bredehoft, Jakub Klemsa, Arthur Meyre, Andrei Stoian

机构 * institutetext: Zama（Zama） 纠错

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

LLM-Guided Probabilistic Program Induction for POMDP Model Estimation

Aidan Curtis, Hao Tang, Thiago Veloso, Kevin Ellis, Joshua Tenenbaum, Tomás Lozano-Pérez, Leslie Pack Kaelbling

机构 * MIT（麻省理工学院） ； Cornell University（康奈尔大学） 纠错

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

Neural Pathways to Program Success: Hopfield Networks for PERT Analysis

Azgar Ali Noor Ahamed

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

Optimization of Infectious Disease Intervention Measures Based on Reinforcement Learning -- Empirical analysis based on UK COVID-19 epidemic data

Baida Zhang, Yakai Chen, Huichun Li, Zhenghu Zu

专题命中 软件智能体 ：agent(abstract)；分类 cs.LG

Identification and Optimization of Redundant Code Using Large Language Models

Shamse Tasnim Cynthia

专题命中 软件智能体 ：agent(abstract)；分类 cs.SE

MANILA: A Low-Code Application to Benchmark Machine Learning Models and Fairness-Enhancing Methods

Giordano d'Aloisio

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

Comments Accepted at FSE 2025 Demonstration Track

Unmasking the Shadows: Pinpoint the Implementations of Anti-Dynamic Analysis Techniques in Malware Using LLM

Haizhou Wang, Nanqing Luo, Xusheng Li, Peng LIu

机构 * Pennsylvania State University（宾夕法尼亚州立大学） ； Vector 35 Inc.（Vector 35公司） 纠错

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

Cracking the Code of Action: a Generative Approach to Affordances for Reinforcement Learning

Lynn Cherif, Flemming Kondrup, David Venuto, Ankit Anand, Doina Precup, Khimya Khetarpal

机构 * McGill University（麦吉尔大学） ； Mila ； Google DeepMind（谷歌DeepMind） 纠错

专题命中 软件智能体 ：agent(abstract)；分类 cs.AI

OLAF: An Open Life Science Analysis Framework for Conversational Bioinformatics Powered by Large Language Models

Dylan Riffle, Nima Shirooni, Cody He, Manush Murali, Sovit Nayak, Rishikumar Gopalan, Diego Gonzalez Lopez

专题命中 软件智能体 ：agent(abstract)；分类 cs.AI

RP-SAM2: Refining Point Prompts for Stable Surgical Instrument Segmentation

Nuren Zhaksylyk, Ibrahim Almakky, Jay Paranjape, S. Swaroop Vedula, Shameema Sikder, Vishal M. Patel, Mohammad Yaqub

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

Generalising from Self-Produced Data: Model Training Beyond Human Constraints

Alfath Daryl Alhajir, Jennifer Dodgson, Joseph Lim, Truong Ma Phi, Julian Peh, Akira Rafhael Janson Pattirane, Lokesh Poovaragan

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

Comments 16 pages, 2 figures

Flow State: Humans Enabling AI Systems to Program Themselves

Helena Zhang, Jakobi Haskell, Yosef Frost

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

Comments 25 pages, 4 figures, 5 tables. Describes a minimalist framework for human-AI co-design of compound AI systems

Design of AI-Powered Tool for Self-Regulation Support in Programming Education

Huiyong Li, Boxuan Ma

专题命中 软件智能体 ：agent(abstract)；分类 cs.AI

Contextual Augmented Multi-Model Programming (CAMP): A Hybrid Local-Cloud Copilot Framework

Yuchen Wang, Shangxin Guo, Chee Wei Tan

专题命中 软件智能体 ：agent(abstract)；分类 cs.AI

Comments This work is accepted to IEEE CAI2025

Talk2X -- An Open-Source Toolkit Facilitating Deployment of LLM-Powered Chatbots on the Web

Lars Krupp, Daniel Geißler, Peter Hevesi, Marco Hirsch, Paul Lukowicz, Jakob Karolus

专题命中 软件智能体 ：agent(abstract)；分类 cs.AI

SPDNet: Seasonal-Periodic Decomposition Network for Advanced Residential Demand Forecasting

Reza Nematirad, Anil Pahwa, Balasubramaniam Natarajan

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

Neural Exploratory Landscape Analysis for Meta-Black-Box-Optimization

Zeyuan Ma, Jiacheng Chen, Hongshu Guo, Yue-Jiao Gong

专题命中 软件智能体 ：agent(abstract)；分类 cs.LG

A new approach for encoding code and assisting code understanding

Mengdan Fan, Wei Zhang, Haiyan Zhao, Zhi Jin

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

Comments 10 page, 14 figures

Evolving the Computational Notebook: A Two-Dimensional Canvas for Enhanced Human-AI Interaction

Konstantin Grotov, Dmitry Botov

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

A New Segment Routing method with Swap Node Selection Strategy Based on Deep Reinforcement Learning for Software Defined Network

Miao Ye, Jihao Zheng, Qiuxiang Jiang, Yuan Huang, Ziheng Wang, Yong Wang

专题命中 软件智能体 ：agent(abstract)；分类 cs.AI

Information maximization for a broad variety of multi-armed bandit games

Alex Barbier-Chebbah, Christian L. Vestergaard, Jean-Baptiste Masson

专题命中 软件智能体 ：agent(abstract)；分类 cs.LG

OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models

Siming Huang, Tianhao Cheng, J. K. Liu, Jiaran Hao, Liuyihan Song, Yang Xu, J. Yang, Jiaheng Liu, Chenchen Zhang, Linzheng Chai, Ruifeng Yuan, Zhaoxiang Zhang, Jie Fu, Qian Liu, Ge Zhang, Zili Wang, Yuan Qi, Yinghui Xu, Wei Chu

专题命中 软件智能体 ：agent(abstract)；分类 cs.CL

The KoLMogorov Test: Compression by Code Generation

Ori Yoran, Kunhao Zheng, Fabian Gloeckle, Jonas Gehring, Gabriel Synnaeve, Taco Cohen

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

Precise Insulin Delivery for Artificial Pancreas: A Reinforcement Learning Optimized Adaptive Fuzzy Control Approach

Omar Mameche, Abdelhadi Abedou, Taqwa Mezaache, Mohamed Tadjine

专题命中 软件智能体 ：agent(abstract)；分类 cs.LG