大模型推理能力

Planning ride-pooling services with detour restrictions for spatially heterogeneous demand: A multi-zone queuing network approach

Yining Liu, Yanfeng Ouyang

专题命中 规划推理 ：planning(title)

Multi-agent Multi-target Path Planning in Markov Decision Processes

Farhad Nawaz, Melkior Ornik

专题命中 规划推理 ：planning(title)

Comments IEEE Xplore link: https://ieeexplore.ieee.org/document/10154136

Journal ref IEEE Transactions on Automatic Control, VOL. 69, NO. 04, 2024 (tentative)

Learn to Flap: Foil Non-parametric Path Planning via Deep Reinforcement Learning

Z. P. Wang, R. J. Lin, Z. Y. Zhao, P. M. Guo, N. Yang, D. X. Fan

专题命中 规划推理 ：planning(title)

Comments submitted to Journal of Fluid Mechanics rapids

Multimodal Grounding for Embodied AI via Augmented Reality Headsets for Natural Language Driven Task Planning

Selma Wanna, Fabian Parra, Robert Valner, Karl Kruusamäe, Mitch Pryor

专题命中 规划推理 ：planning(title)

Comments 18 pages, 15 figures

AMSwarm: An Alternating Minimization Approach for Safe Motion Planning of Quadrotor Swarms in Cluttered Environments

Vivek K. Adajania, Siqi Zhou, Arun Kumar Singh, Angela P. Schoellig

专题命中 规划推理 ：planning(title)

Comments Accepted to IEEE ICRA 2023

Strategic Planning for Flexible Agent Availability in Large Taxi Fleets

Rajiv Ranjan Kumar, Pradeep Varakantham, Shih-Fen Cheng

专题命中 规划推理 ：planning(title)

Comments Accepted to the 22nd International Conference on Autonomous Agents and Multiagent Systems (AAMAS-23)

Shadoks Approach to Low-Makespan Coordinated Motion Planning

Loïc Crombez, Guilherme D. da Fonseca, Yan Gerard, Aldo Gonzalez-Lorenzo, Pascal Lafourcade, Luc Libralesso

专题命中 规划推理 ：planning(title)

Comments Journal version to appear on ACM Journal on Algorithmics

Journal ref ACM Journal of Experimental Algorithmics, 27, 3.2, 1-17, 2022

SMA-NBO: A Sequential Multi-Agent Planning with Nominal Belief-State Optimization in Target Tracking

Tianqi Li, Lucas W. Krakow, Swaminathan Gopalswamy

专题命中 规划推理 ：planning(title)

Integrated Task Assignment and Path Planning for Capacitated Multi-Agent Pickup and Delivery

Zhe Chen, Javier Alonso-Mora, Xiaoshan Bai, Daniel D. Harabor, Peter J. Stuckey

专题命中 规划推理 ：planning(title)

Journal ref IEEE Robotics and Automation Letters, vol. 6, no. 3, pp. 5816-5823, July 2021

Energy-Optimal Motion Planning for Agents: Barycentric Motion and Collision Avoidance Constraints

Logan E. Beaver, Michael Dorothy, Christopher Kroninger, Andreas A. Malikopoulos

专题命中 规划推理 ：planning(title)

Comments 6 pages, no figures

Journal ref 2021 American Control Conference (ACC), pp 1037-1042

Scalable Planning in Multi-Agent MDPs

Dinuka Sahabandu, Luyao Niu, Andrew Clark, Radha Poovendran

专题命中 规划推理 ：planning(title)

Efficient Trajectory Planning for Multiple Non-holonomic Mobile Robots via Prioritized Trajectory Optimization

Juncheng Li, Maopeng Ran, Lihua Xie

专题命中 规划推理 ：planning(title)

Comments 8 pages, to be published in IEEE Robotics and Automation Letters (RA-L), source code is available at: https://github.com/LIJUNCHENG001/multi_robot_traj_planner

Scalable and Safe Multi-Agent Motion Planning with Nonlinear Dynamics and Bounded Disturbances

Jingkai Chen, Jiaoyang Li, Chuchu Fan, Brian Williams

专题命中 规划推理 ：planning(title)

Comments Accepted at AAAI2021. 9 pages, 5 figures, 1 table

Where to Map? Iterative Rover-Copter Path Planning for Mars Exploration

Takahiro Sasaki, Kyohei Otsu, Rohan Thakker, Sofie Haesaert, Ali-akbar Agha-mohammadi

专题命中 规划推理 ：planning(title)

Comments 8 pages, 7 figures

Journal ref IEEE Robotics and Automation Letters, Volume: 5 , Issue: 2 , April 2020

LFC: Combining Autonomous Agents and Automated Planning in the Multi-Agent Programming Contest

Rafael C. Cardoso, Angelo Ferrando, Fabio Papacchini

专题命中 规划推理 ：planning(title)

Online Trajectory Generation with Distributed Model Predictive Control for Multi-Robot Motion Planning

Carlos E. Luis, Marijan Vukosavljev, Angela P. Schoellig

专题命中 规划推理 ：planning(title)

Comments 8 pages, 8 figures

Journal ref IEEE Robotics and Automation Letters, vol. 5, iss. 2, pp. 604-611, 2020

How Shall I Drive? Interaction Modeling and Motion Planning towards Empathetic and Socially-Graceful Driving

Yi Ren, Steven Elliott, Yiwei Wang, Yezhou Yang, Wenlong Zhang

专题命中 规划推理 ：planning(title)

Comments accepted to 2019 International Conference on Robotics and Automation

Globally Optimal AC Power System Upgrade Planning under Operational Policy Constraints

Sandro Merkli, Alexander Domahidi, Juan Jerez, Roy S. Smith

专题命中 规划推理 ：planning(title)

Comments Presented at the European Control Conference 2018 in Limassol, Cyprus

Automatic View Planning with Multi-scale Deep Reinforcement Learning Agents

Amir Alansary, Loic Le Folgoc, Ghislain Vaillant, Ozan Oktay, Yuanwei Li, Wenjia Bai, Jonathan Passerat-Palmbach, Ricardo Guerrero, Konstantinos Kamnitsas, Benjamin Hou, Steven McDonagh, Ben Glocker, Bernhard Kainz, Daniel Rueckert

专题命中 规划推理 ：planning(title)

Comments Accepted for MICCAI2018

Monte Carlo Planning method estimates planning horizons during interactive social exchange

Andreas Hula, P. Read Montague, Peter Dayan

专题命中 规划推理 ：planning(title)

Time-Inconsistent Planning: A Computational Problem in Behavioral Economics

Jon Kleinberg, Sigal Oren

专题命中 规划推理 ：planning(title)

Weighted Memory Tree: Remembering What Matters for Long-Horizon LLM Agents

加权记忆树：为长视野大语言模型智能体记住重要信息

Quang Dao, Purvi Kathalkar, Kenneth Eaton

机构 * Rose-Hulman Institute of Technology（罗斯-霍曼理工学院） ； Georgia Institute of Technology（佐治亚理工学院） ； Georgia Tech Research Institute（佐治亚理工学院研究院） 纠错

专题命中 规划推理 ：reasoning(abstract)；planning(abstract)；分类 cs.AI

AI总结 提出加权记忆树（WMT）分层记忆系统，在GAIA-Text数据集上使LLM智能体准确率平均提升9.97个百分点、令牌用量减32.8%，可抑制低效用内容与不可靠信息传播。

Comments 16 pages, 2 figures

A Survey on Foundations and Frontiers of Multimodal Agentic Frameworks: Techniques and Applications

多模态智能体框架的基础与前沿：技术及应用综述

Neel Mokaria, Rishie Raj, Dheeraj Baiju, Xiaoqian Shen, Shraman Pramanick, Kevin Qinghong Lin, Arda Senocak, Mike Zheng Shou, Philip Torr, Mohamed Elhoseiny, Yapeng Tian, Ruohan Gao, Salman Khan, Sayan Nag, Sanjoy Chowdhury, Dinesh Manocha

专题命中 规划推理 ：reasoning(abstract)；planning(abstract)；分类 cs.AI

AI总结 本综述针对多模态在智能体框架核心模块的作用展开系统分析，梳理了其架构整合方式、应用领域及效率权衡，为通用智能系统研究指明方向。

Comments Accepted at TMLR

Recognizing Artificial Minds: A Philosophical Defense of AI Cognition

识别人工心智：对AI认知的哲学辩护

Herman Cappelen, Josh Dever

专题命中 规划推理 ：reasoning(abstract)；planning(abstract)；分类 cs.AI

AI总结 该研究为“全猪论题”辩护，主张LLMs是具备认知状态的成熟智能体，反驳相关质疑并推测其可能拥有人类概念体系外的内容。

Comments Pre-publication draft. Forthcoming as Open Access from Oxford University Press. Please cite the OUP version when available. Note title change: previously, "Going Whole Hog: A Philosophical Defence of AI Cognition"

BrainWAM: Action-Space Coordination of Semantic Priors and Predictive Dynamics for Autonomous Driving

BrainWAM：面向自动驾驶的语义先验与预测动力学的动作空间协调框架

Bing Zhan, Shuyao Shang, Shuo Lu, Yuan Xu, Zhao Wang, Yida Wang, Xueyang Zhang, Kun Zhan, Jiahao Gu

机构 * Institute of Automation, Chinese Academy of Sciences (CASIA)（中国科学院自动化研究所） ； Li Auto Inc.（理想汽车） 纠错

专题命中 规划推理 ：reasoning(abstract)；planning(abstract)；分类 cs.AI

AI总结 该研究针对自动驾驶中语义与预测动力学的规划需求，提出BrainWAM框架，通过结构化动作空间协调及异步整流流推理，在NAVSIM数据集上实现最优性能，优于仅VLA或仅WAM方法。

Uncertainty-Aware Decision Making in Multimodal Large Language Models

多模态大语言模型中的不确定性感知决策

Abderrahmene Boudiaf, Irfan Hussain, Sajid Javed

机构 * Khalifa University of Science and Technology（哈利法科技大学） 纠错

专题命中 规划推理 ：reasoning(abstract)；verifier(abstract)；分类 cs.CL

AI总结 本调查围绕决策中心框架，综述多模态大语言模型（MLLMs）的不确定性感知决策相关研究，对比同类调查并指出源感知分解等开放问题，核心是不确定性需改善多模态证据下的系统行为。

HyMem: Hierarchical Context Management for Long-Horizon Agents via Information Isolation

HyMem：基于信息隔离的长程智能体分层上下文管理

XinQi Wang, Jinwei Xiao, Sijia Cui, Hongming Zhang, Yanna Wang, Qingyang Zhang, Bo Xu

机构 * Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所） ； University of Chinese Academy of Sciences（中国科学院大学） ； Nanjing Artificial Intelligence Research of IA（IA南京人工智能研究院） 纠错

专题命中 规划推理 ：reasoning(abstract)；planning(abstract)；分类 cs.AI

AI总结 针对LLM智能体长程任务上下文杂乱导致推理性能下降的问题，提出分层上下文管理框架HyMem，通过功能分层隔离推理与规划，在GAIA、Browsecomp-plus数据集上取得优于基线的性能。

An Agentic Framework Using Rules and LLMs for Embedding and Annotating Descriptive Document Layouts: A Plant Science Use Case

一种结合规则与大语言模型（LLM）的智能体框架，用于描述性文档布局的嵌入与标注：植物科学应用案例

Nicolas Turenne, Youcef Sklab, Eric Chenin, Jean-Daniel Zucker

专题命中 规划推理 ：reasoning(abstract)；planning(abstract)；分类 cs.AI

AI总结 本研究提出结合规则与LLM的智能体框架，用于植物性状提取，在三个区域植物数据集上实现高效标注，提升了性状覆盖度与标注量，验证了其稳健性与可扩展性。

Efficient Block-Layer Parallel Inference for Vision-Language-Action on Hybrid Architectures

面向混合架构的视觉-语言-动作（VLA）高效块级并行推理

Haibo HU, Lianming Huang, Qiao Li, Nan Guan, Chun Jason Xue

专题命中 规划推理 ：reasoning(abstract)；planning(abstract)；分类 cs.AI

AI总结 该研究针对VLA模型部署于车载平台的延迟与内存压力问题，提出混合CPU-GPU推理框架，通过块级划分实现资源调度，在Bench2Drive数据集及实车部署中均取得性能提升。

Budget-Aware Tool Use Enables Effective Agent Scaling

预算感知的工具使用实现有效的代理扩展

Tengxiao Liu, Zifeng Wang, Jin Miao, I-Hung Hsu, Jun Yan, Jiefeng Chen, Rujun Han, Fangyuan Xu, Yanfei Chen, Ke Jiang, Samira Daruki, Yi Liang, William Yang Wang, Tomas Pfister, Chen-Yu Lee

机构 * Google Cloud AI Research（谷歌云人工智能研究） ； Google DeepMind（谷歌DeepMind） ； New York University（纽约大学） ； UC Santa Barbara（加州大学圣塔芭芭拉分校） 纠错

专题命中 规划推理 ：reasoning(abstract)；planning(abstract)；分类 cs.AI

AI总结 本研究提出BATS框架，通过预算感知机制提升工具增强代理的扩展效率，实现更优的成本-性能平衡。

Comments Accepted to COLM 2026