AI Agent

GOAL: A Generalist Combinatorial Optimization Agent Learner

Darko Drakulic, Sofia Michel, Jean-Marc Andreoli

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

Comments Accepted to ICLR 2025

Fortran2CPP: Automating Fortran-to-C++ Translation using LLMs via Multi-Turn Dialogue and Dual-Agent Integration

Le Chen, Bin Lei, Dunzhi Zhou, Pei-Hung Lin, Chunhua Liao, Caiwen Ding, Ali Jannesari

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

Learning-by-teaching with ChatGPT: The effect of teachable ChatGPT agent on programming education

Angxuan Chen, Yuang Wei, Huixiao Le, Yan Zhang

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

Game Agent Driven by Free-Form Text Command: Using LLM-based Code Generation and Behavior Branch

Ray Ito, Junichiro Takahashi

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

Comments This paper is posted at JSAI 2024 Conference

Journal ref Proceedings of the Annual Conference of JSAI, 2024, Volume JSAI2024, 38th (2024), Session ID 1I5-OS-31b-05, Pages 1I5OS31b05

Neeko: Leveraging Dynamic LoRA for Efficient Multi-Character Role-Playing Agent

Xiaoyan Yu, Tongxu Luo, Yifan Wei, Fangyu Lei, Yiming Huang, Hao Peng, Liehuang Zhu

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

Comments EMNLP 2024

SurgBox: Agent-Driven Operating Room Sandbox with Surgery Copilot

Jinlin Wu, Xusheng Liang, Xuexue Bai, Zhen Chen

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

Comments This work is accepted by IEEE Big Data 2024

CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges

Kechi Zhang, Jia Li, Ge Li, Xianjie Shi, Zhi Jin

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

Comments Camera Ready version for ACL 2024 (main)

Building Living Software Systems with Generative & Agentic AI

Jules White

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

TaskWeaver: A Code-First Agent Framework

Bo Qiao, Liqun Li, Xu Zhang, Shilin He, Yu Kang, Chaoyun Zhang, Fangkai Yang, Hang Dong, Jue Zhang, Lu Wang, Minghua Ma, Pu Zhao, Si Qin, Xiaoting Qin, Chao Du, Yong Xu, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang

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

Small Agent Can Also Rock! Empowering Small Language Models as Hallucination Detector

Xiaoxue Cheng, Junyi Li, Wayne Xin Zhao, Hongzhi Zhang, Fuzheng Zhang, Di Zhang, Kun Gai, Ji-Rong Wen

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

Agent-Aware Training for Agent-Agnostic Action Advising in Deep Reinforcement Learning

Yaoquan Wei, Shunyu Liu, Jie Song, Tongya Zheng, Kaixuan Chen, Yong Wang, Mingli Song

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

Towards the generation of synchronized and believable non-verbal facial behaviors of a talking virtual agent

Alice Delbosc, Magalie Ochs, Nicolas Sabouret, Brian Ravenet, Stéphane Ayache

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

Journal ref INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION (ICMI '23 Companion), Oct 2023, Paris, France

CodePlan: Repository-level Coding using LLMs and Planning

Ramakrishna Bairi, Atharv Sonwane, Aditya Kanade, Vageesh D C, Arun Iyer, Suresh Parthasarathy, Sriram Rajamani, B. Ashok, Shashank Shet

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

Efficient and Interpretable Compressive Text Summarisation with Unsupervised Dual-Agent Reinforcement Learning

Peggy Tang, Junbin Gao, Lei Zhang, Zhiyong Wang

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

Comments The 4th Workshop on Simple and Efficient Natural Language Processing (SustaiNLP 2023), co-located with ACL 2023

Emergent Agentic Transformer from Chain of Hindsight Experience

Hao Liu, Pieter Abbeel

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

Comments International Conference on Machine Learning (ICML) 2023

AIDA: An Active Inference-based Design Agent for Audio Processing Algorithms

Albert Podusenko, Bart van Erp, Magnus Koudahl, Bert de Vries

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

TWEAC: Transformer with Extendable QA Agent Classifiers

Gregor Geigle, Nils Reimers, Andreas Rücklé, Iryna Gurevych

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

CareCall: a Call-Based Active Monitoring Dialog Agent for Managing COVID-19 Pandemic

Sang-Woo Lee, Hyunhoon Jung, SukHyun Ko, Sunyoung Kim, Hyewon Kim, Kyoungtae Doh, Hyunjung Park, Joseph Yeo, Sang-Houn Ok, Joonhaeng Lee, Sungsoon Lim, Minyoung Jeong, Seongjae Choi, SeungTae Hwang, Eun-Young Park, Gwang-Ja Ma, Seok-Joo Han, Kwang-Seung Cha, Nako Sung, Jung-Woo Ha

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

FML-based Dynamic Assessment Agent for Human-Machine Cooperative System on Game of Go

Chang-Shing Lee, Mei-Hui Wang, Sheng-Chi Yang, Pi-Hsia Hung, Su-Wei Lin, Nan Shuo, Naoyuki Kubota, Chun-Hsun Chou, Ping-Chiang Chou, Chia-Hsiu Kao

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

Comments 26 pages, 14 figures

Deep Pepper: Expert Iteration based Chess agent in the Reinforcement Learning Setting

Sai Krishna G. V., Kyle Goyette, Ahmad Chamseddine, Breandan Considine

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

Comments Tabula Rasa, Chess engine, Learning Fast and Slow, Reinforcement Learning, Alpha Zero

Modelling Office Energy Consumption: An Agent Based Approach

Tao Zhang, Peer-Olaf Siebers, Uwe Aickelin

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

Comments Proceedings of the 3rd World Congress on Social Simulation (WCSS2010), 5-9 Sep, Kassel, Germany, 2010. arXiv admin note: substantial text overlap with arXiv:1305.7437

Agent Based Software Testing Framework (ABSTF) for Application Maintenance

K. Karnavel, V. Divya, Gnanakeerthika, P. Karthika

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

Modelling Electricity Consumption in Office Buildings: An Agent Based Approach

Tao Zhang, Peer-Olaf Siebers, Uwe Aickelin

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

Comments Energy and Buildings 43(10), 2882-2892, 2011

Probabilistic Agent Programs

Juergen Dix, Mirco Nanni, VS Subrahmanian

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

Comments 44 pages, 1 figure, Appendix

Agent Programming with Declarative Goals

F. S. de Boer, K. V. Hindriks, W. van der Hoek, J. -J. Ch. Meyer

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

Beware of Agentic Botnets: Scalable Untargeted Promptware Attacks via Universal and Transferable Adversarial HalluSquatting

警惕智能体僵尸网络：通过通用且可转移的对抗性幻觉蹲点进行可扩展的无目标提示软件攻击

Aya Spira, Stav Cohen, Elad Feldman, Ron Bitton, Avishai Wool, Ben Nassi

专题命中 软件智能体 ：agentic(title,abstract)

AI总结 研究针对实际威胁模型中无直接渠道时攻击者能否利用LLM应用的问题，提出对抗性幻觉蹲点技术，通过识别热门资源计算幻觉分布抢先注册对抗性提示，利用幻觉特性扩大无目标提示软件攻击范围并建立僵尸网络，实验证明该技术可行性及幻觉可转移性。

Comments Website: https://sites.google.com/view/agentic-botnets/home

SIAgent: Spatial Interaction Agent via LLM-powered Eye-Hand Motion Intent Understanding in VR

SIAgent：通过LLM驱动的眼手运动意图理解实现VR中的空间交互代理

Zhimin Wang, Chenyu Gu, Feng Lu

专题命中 软件智能体 ：agent(title,abstract)

AI总结 SIAgent通过LLM驱动的意图识别与代理执行，实现VR中基于自然眼手运动的高容忍度交互框架。

Comments Virtual reality, spatial interaction, intent recognition, agent-based execution, large language models

KAT-Coder-V2.5 Technical Report

KAT-Coder-V2.5技术报告

Bo Huang, Fengxiang Li, Hao Xu, Haoyang Huang, Hongyi Fu, Jinhua Hao, Kun Yuan, Minglei Zhang, Pengcheng Xu, Shiyang Liu, Wenhao Zhuang, Yuze Shi, Zongxian Feng, Chao Wang, Cheng He, Chongling Rao, Deyu Cao, Fan Yang, Gang Xiong, Haochen Liu, Jiabao Li, Jian Liang, Jinghui Jia, Jingwen Chang, Jun Du, Junyu Shi, Min Li, Mingqi Wu, Qiang Gao, Shangpeng Yan, Shaotong Qi, Shu Xu, Shuo Zhou, Tiankuo Xu, Tong Zheng, Weilun Zhao, Xiancheng Meng, Xianda Sun, Xiaoyu Jiang, Xunhao Jia, Yao Xia, Yimeng Xu, Yinghan Cui, Yingpeng Chen, Yiwen Ning, Yong Wang, Yuxuan Sun, Zhongsheng Liu, Ming Sun, Cheng Luo, Chen Yang, Han Li, Kun Gai

机构 * KwaiKAT Team（快手KwaiKAT团队） 纠错

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

AI总结 介绍KAT-Coder-V2.5这一专注编码的智能模型，针对其受环境等因素限制的问题，通过端到端框架及多种技术手段解决，经多方法扩展强化学习并统一专家知识，在多个基准测试中取得优异成绩。

Comments 24 pages, 5 figures

Library-Aware Doubles and Iterative Repair for Large Language Model-Generated Unit Tests in OpenSIL Firmware

面向OpenSIL固件中大语言模型生成的单元测试的库感知双打与迭代修复

Ma Toan Bach, Yuchi Zheng, Haingo Razafindranto, Tanvir Alam, Aric Leather, Ranveer Sandhu, Jitesh Arora

机构 * School of Software Design and Data Science（软件设计与数据科学学院） ； Seneca Polytechnic（森纳学院） ； Advanced Micro Devices Canada（加拿大先进微器件公司） 纠错

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

AI总结 针对OpenSIL固件单元测试因构建约束易失败的问题，提出LLM引导的多智能体自动化测试生成与迭代修复流程，在76个函数中73个生成可编译测试，行覆盖率达98.8%。

Comments 20 pages, 10 figures, 1 Table. This work has been submitted to the IEEE for possible publication

ClawHub Security Signals: When VirusTotal, Static Analysis, and SkillSpector Disagree

ClawHub安全信号：当VirusTotal、静态分析和SkillSpector意见不一致时

Vincent Koc, Patrick Erichsen, Jacob Tomlinson, Agustin Rivera, Michael Appel, Nir Paz

机构 * OpenClaw Foundation USA（OpenClaw基金会美国） ； NVIDIA United Kingdom（NVIDIA英国分公司） ； NVIDIA USA（NVIDIA美国） 纠错

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

AI总结 研究ClawHub中67,453个公开技能版本，通过VirusTotal、静态启发式分析和NVIDIA SkillSpector三种扫描器的分歧，揭示智能体技能安全需要分层治理而非单一扫描器决策。

Comments 10 pages, 1 figure, 7 tables, 1 supplimentary dataset