AI Agent

Splitting method for spatio-temporal search efforts planning

时空搜索努力规划的拆分方法

Chouchane Mathieu, Paris Sébastien, Le Gland François, Ouladsine Mustapha

专题命中 工具调用 ：planning(title)

AI总结 提出基于广义拆分方法的新型随机优化算法，用于最大化检测智能随机移动目标的概率，无需状态空间离散化且能处理多种约束。

Comments Article rejected

Meta-Adaptive Beam Search Planning for Transformer-Based Reinforcement Learning Control of UAVs with Overhead Manipulators under Flight Disturbances

基于Transformer强化学习的无人机搭载顶置机械臂在飞行扰动下的元自适应波束搜索规划

Hazim Alzorgan, Sayed Pedram Haeri Boroujeni, Abolfazl Razi

专题命中 工具调用 ：planning(title)

AI总结 针对无人机与顶置机械臂耦合导致的末端执行器跟踪误差问题，提出基于Transformer双深度Q网络（DDQN）的强化学习框架，通过自适应波束搜索规划器利用学习到的评论家进行前向估计，实现软件在环的短视域波束搜索，显著降低跟踪误差并提升奖励。

Comments The paper will be reworked significantly

AgentSecBench: Measuring Prompt Injection, Privacy Leakage, and Tool-Use Integrity in LLM Agents

AgentSecBench：测量LLM智能体中的提示注入、隐私泄露和工具使用完整性

Faruk Alpay, Taylan Alpay

专题命中 工具调用 ：tool-use(title)

AI总结 提出AgentSecBench框架，通过定义意图到执行的无干扰游戏，系统评估LLM智能体在指令完整性、检索机密性和能力完整性方面的安全风险，并实验验证防御措施的有效性。

Comments 24 pages, 3 figures. Ancillary files provided

Patho-AgenticRAG: Towards Multimodal Agentic Retrieval-Augmented Generation for Pathology VLMs via Reinforcement Learning

病理代理RAG：通过强化学习实现多模态代理检索增强生成用于病理学视觉语言模型

Wenchuan Zhang, Jingru Guo, Hengzhe Zhang, Penghao Zhang, Jie Chen, Shuwan Zhang, Zhang Zhang, Yuhao Yi, Hong Bu

专题命中 工具调用 ：agentic(title)

AI总结 本文提出Patho-AgenticRAG，通过强化学习实现多模态代理检索增强生成，解决病理学视觉语言模型在高分辨率、复杂组织结构和临床语义上的挑战，提升诊断准确性。

Journal ref Proceedings of the AAAI Conference on Artificial Intelligence, 40(35): 29921-29929, 2026

AeroGen: Agentic Drone Autonomy through Single-Shot Structured Prompting & Drone SDK

AeroGen：通过单次结构提示与无人机SDK实现代理无人机自主性

Kautuk Astu, Yogesh Simmhan

专题命中 工具调用 ：agentic(title)

AI总结 本文提出AeroGen框架，通过结构化提示和AeroDaaS SDK实现无人机自主控制程序的可靠生成，验证了其在多种环境下的有效性。

RPT*: Global Planning with Probabilistic Terminals for Target Search in Complex Environments

RPT*: 带概率终端的全局规划用于复杂环境中的目标搜索

Yunpeng Lyu, Chao Cao, Ji Zhang, Howie Choset, Zhongqiang Ren

机构 * Global College, Shanghai Jiao Tong University（上海交通大学全球学院） ； Robotics Institute, Carnegie Mellon University（卡内基梅隆大学机器人研究所） 纠错

专题命中 工具调用 ：planning(title)

AI总结 RPT*通过动态规划和新启发式方法解决复杂环境中的目标搜索问题，实现最优路径规划与高效探索的平衡。

Agentic AI meets Neural Architecture Search: Proactive Traffic Prediction for AI-RAN

Abdelaziz Salama, Mohammed M. H. Qazzaz, Zeinab Nezami, Maryam Hafeez, Syed Ali Raza Zaidi

专题命中 工具调用 ：agentic(title)

Emotional Multifaceted Feedback on AI Tool Use in EFL Learning Initiation: Chain-Mediated Effects of Motivation and Metacognitive Strategies in an Optimized TAM Model

Le Yao, Yantong Liu

专题命中 工具调用 ：tool use(title)

Enhancing Reinforcement Learning in Sensor Fusion: A Comparative Analysis of Cubature and Sampling-based Integration Methods for Rover Search Planning

Jan-Hendrik Ewers, Sarah Swinton, David Anderson, Euan McGookin, Douglas Thomson

专题命中 工具调用 ：planning(title)

Comments Submitted to IROS 2024

Model Predictive Trees: Sample-Efficient Receding Horizon Planning with Reusable Tree Search

John Lathrop, Benjamin Rivi`ere, Jedidiah Alindogan, Soon-Jo Chung

专题命中 工具调用 ：planning(title)

Comments Presented at the 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems

VisionGPT: Vision-Language Understanding Agent Using Generalized Multimodal Framework

Chris Kelly, Luhui Hu, Bang Yang, Yu Tian, Deshun Yang, Cindy Yang, Zaoshan Huang, Zihao Li, Jiayin Hu, Yuexian Zou

专题命中 工具调用 ：agent(title)

Comments 17 pages, 5 figures, and 1 table. arXiv admin note: substantial text overlap with arXiv:2311.10125

Quantum Search Approaches to Sampling-Based Motion Planning

Paul Lathrop, Beth Boardman, Sonia Martínez

专题命中 工具调用 ：planning(title)

Comments 15 pages, 11 figures

Journal ref IEEE Access, vol. 11, pp. 89506-89519, 2023

Probabilistic Planning for Maritime Search and Rescue

Luís Marques, Jose Javier Escribano Macias, Panagiotis Angeloudis

专题命中 工具调用 ：planning(title)

Comments 4 pages. 3 figures. To appear in 6th International Conference on Dynamics of Disasters (DOD 2023)

DataChat: Prototyping a Conversational Agent for Dataset Search and Visualization

Lizhou Fan, Sara Lafia, Lingyao Li, Fangyuan Yang, Libby Hemphill

专题命中 工具调用 ：agent(title)

Comments 6 pages, 2 figures, and 1 table. Accepted to the 86th Annual Meeting of the Association for Information Science & Technology

Simulation Analysis of Exploration Strategies and UAV Planning for Search and Rescue

Phuoc Nguyen Thuan, Jorge Peña Queralta, Tomi Westerlund

专题命中 工具调用 ：planning(title)

Decentralized Search and Track with Multiple Autonomous Agents

Savvas Papaioannou, Panayiotis Kolios, Theocharis Theocharides, Christos G. Panayiotou, Marios M. Polycarpou

专题命中 工具调用 ：autonomous agent(title)

Journal ref 2019 IEEE 58th Conference on Decision and Control (CDC), Nice, France, 2019, pp. 909-915

Search-Based Path Planning Algorithm for Autonomous Parking:Multi-Heuristic Hybrid A*

Jihao Huang, Zhitao Liu, Xuemin Chi, Feng Hong, Hongye Su

专题命中 工具调用 ：planning(title)

SEED: Series Elastic End Effectors in 6D for Visuotactile Tool Use

H. J. Terry Suh, Naveen Kuppuswamy, Tao Pang, Paul Mitiguy, Alex Alspach, Russ Tedrake

专题命中 工具调用 ：tool use(title)

Comments Submitted to Robosoft 2022

ToolNet: Using Commonsense Generalization for Predicting Tool Use for Robot Plan Synthesis

Rajas Bansal, Shreshth Tuli, Rohan Paul, Mausam

专题命中 工具调用 ：tool use(title)

Comments Advances & Challenges in Imitation Learning for Robotics Workshop in Robotics Science and Systems (RSS) 2020. The first two authors contributed equally

A good body is all you need: avoiding catastrophic interference via agent architecture search

Joshua Powers, Ryan Grindle, Lapo Frati, Josh Bongard

专题命中 工具调用 ：agent(title)

Comments arXiv admin note: text overlap with arXiv:1910.07487

Search-based Kinodynamic Motion Planning for Omnidirectional Quadruped Robots

Pei Wang, Xiaoyu Zhou, Qingteng Zhao, Jun Wu, Qiuguo Zhu

专题命中 工具调用 ：planning(title)

Comments 7 pages

Anticipatory Human-Robot Path Planning for Search and Rescue

Barnabas Gavin Cangan, Larkin Heintzman, Amanda Hashimoto, Nicole Abaid, Ryan K. Williams

专题命中 工具调用 ：planning(title)

Comments IROS 2019 - Workshop on Informed Scientific Sampling in Large-scale Outdoor Environments

The Birkhoff Diamond as Double Agent

James A. Tilley

专题命中 工具调用 ：agent(title)

Comments 10 pages, 5 figures; earlier version of an article that has since been retitled to "Kempe-locking configurations" and submitted in revised form to and accepted by Mathematics for a special issue on graph theory

Say Hi to Eliza. An Embodied Conversational Agent on the Web

Gerard Llorach, Josep Blat

专题命中 工具调用 ：agent(title)

Comments 4 Pages, 1 figure, 17th International Conference Intelligence Virtual Agents (IVA)

Current status of MCNP6 as a simulation tool useful for space and accelerator applications

S. G. Mashnik, J. S. Bull, H. G. Hughes, R. E. Prael, A. J. Sierk

专题命中 工具调用 ：tool use(title)

Comments 4 pages, 3 figures, Proc. 11th Conference on the Intersections of Particle and Nuclear Physics (CIPANP 2012), St. Petersburg, FL, May 28 - June 3, 2012

IntelligentWeb Agent for Search Engines

Avinash N Bhute, B. B. Meshram

专题命中 工具调用 ：agent(title)

Comments 5 pages. International Conference on Trends and Advances in Computation and Engineering TRACE -2010. arXiv admin note: text overlap with arXiv:1205.2891 by other authors

Intelligent Agent Based Semantic Web in Cloud Computing Environment

Debajyoti Mukhopadhyay, Manoj Sharma, Gajanan Joshi, Trupti Pagare, Adarsha Palwe

专题命中 工具调用 ：agent(title)

Comments 10 pages, 10 figures

EviDx: Evidence-Aware Active Diagnosis with Scaffolded LLM Agents

EviDx：基于证据感知的支架式大语言模型智能体主动诊断框架

Lihang Zeng, Shaoting Zhang, Xiaofan Zhang

专题命中 工具调用 ：tool use(abstract)；agentic(abstract)；分类 cs.AI

AI总结 EviDx是结合患者诊断环境、临床诊断支架与运行时控制模块的证据感知主动诊断框架，可提升LLM的诊断性能与过程稳定性，还能揭示模型的能力边界。

Illuminating the Three Dogmas of Reinforcement Learning under Evolutionary Light

在进化之光下揭示强化学习的三个教条

Mani Hamidi, Terrence W. Deacon

机构 * Department of Computer Science, University of Tübingen（图宾根大学计算机科学系） ； Department of Anthropology, University of California, Berkeley（加州大学伯克利分校人类学系） 纠错

专题命中 工具调用 ：agent(abstract)；autonomous agent(abstract)；分类 cs.AI

AI总结 本文从人工生命视角批判强化学习的三个核心假设，提出将学习视为适应而非优化，并利用开放新颖性搜索和热力学理论构建更生物真实的智能体模型。

Where World Models Break: Natural-Input Failure Discovery

世界模型何时失效：自然输入的故障发现

Zhanpeng Shi, Zi Liang, Rong Feng, Shiqin Tang, Xuyang Chen, Hongzong Li

机构 * School of Computer Science, Northwestern Polytechnical University（西北工业大学计算机学院） ； The Hong Kong Polytechnic University（香港理工大学） ； City University of Hong Kong（香港城市大学） ； Department of Electrical and Computer Engineering, National University of Singapore（新加坡国立大学电气与计算机工程系） ； Generative AI Research and Development Center, The Hong Kong University of Science and Technology（香港科技大学生成式人工智能研发中心） 纠错

专题命中 工具调用 ：agent(abstract)；planning(abstract)；分类 cs.AI

AI总结 本文针对现有世界模型评估忽略灾难性故障风险的问题，提出 BasinLens 方法，可在有限查询预算下发现自然输入引发的可复现、局部持续的世界模型故障，暴露常规基准未覆盖的漏洞。