arXivDaily arXiv每日学术速递 周一至周五更新

AI 大模型

大模型推理能力

大模型数学、逻辑、规划、多步推理和测试时计算能力。

共收录 11076 信号源:cs.CL, cs.AI, cs.LG

1. 规划推理 11076 篇

1810.08460 2018-10-22 cs.AI 70%

Planification par fusions incrémentales de graphes

Damien Pellier, lias. Belaidi

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

Comments in French

Journal ref Journées Francophones de Planification, Décision, Apprentissage pour la conduite de systèmes (JFPDA). 2008, Metz, France

详情

展开后加载摘要…

URL PDF HTML 收藏
1810.07007 2018-10-17 cs.AI 70%

Tentacular Artificial Intelligence, and the Architecture Thereof, Introduced

Selmer Bringsjord, Naveen Sundar Govindarajulu, Atriya Sen, Matthew Peveler, Biplav Srivastava, Kartik Talamadupula

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

Comments FAIM Workshop on Architectures And Evaluation For Generality, Autonomy & Progress in AI July 15, 2018, Stockholm, Sweden, 1st International Workshop Held In Conjunction With IJCAI-ECAI 2018, Aamas 2018 and ICML 2018

详情

展开后加载摘要…

URL PDF HTML 收藏
1810.06374 2018-10-16 cs.AI 70%

SmartPM: Automatic Adaptation of Dynamic Processes at Run-Time

Andrea Marrella

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

Comments Postprint of PhD Thesis of Andrea Marrella, published on October 2013

详情

展开后加载摘要…

URL PDF HTML 收藏
1806.11298 2018-08-15 cs.AI 70%

A General Multi-agent Epistemic Planner Based on Higher-order Belief Change

Xiao Huang, Biqing Fang, Hai Wan, Yongmei Liu

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

Comments One of the authors think it's not appropriate to show this work there days. Then we discussed, we want submit a new work and this one together later

Journal ref IJCAI. (2017) 1093-1101

详情

展开后加载摘要…

URL PDF HTML 收藏
1807.05196 2018-07-16 cs.RO cs.AI 70%

Artificial Intelligence for Long-Term Robot Autonomy: A Survey

Lars Kunze, Nick Hawes, Tom Duckett, Marc Hanheide, Tomáš Krajník

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

Comments Accepted for publication in the IEEE Robotics and Automation Letters (RA-L)

详情

展开后加载摘要…

URL PDF HTML 收藏
1806.07135 2018-06-20 cs.AI 70%

SMarTplan: a Task Planner for Smart Factories

Arthur Bit-Monnot, Francesco Leofante, Luca Pulina, Erika Abraham, Armando Tacchella

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

详情

展开后加载摘要…

URL PDF HTML 收藏
1804.01396 2018-04-05 cs.AI cs.CV 70%

Artificial Intelligence and its Role in Near Future

Jahanzaib Shabbir, Tarique Anwer

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

详情

展开后加载摘要…

URL PDF HTML 收藏
1803.05156 2018-03-15 cs.AI 70%

The 2017 AIBIRDS Competition

Matthew Stephenson, Jochen Renz, Xiaoyu Ge, Peng Zhang

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

详情

展开后加载摘要…

URL PDF HTML 收藏
1802.01780 2018-02-07 cs.RO cs.AI cs.HC 70%

Goal Inference Improves Objective and Perceived Performance in Human-Robot Collaboration

Chang Liu, Jessica B. Hamrick, Jaime F. Fisac, Anca D. Dragan, J. Karl Hedrick, S. Shankar Sastry, Thomas L. Griffiths

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

Comments Published at the International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2016)

Journal ref C. Liu, J. Hamrick, J. Fisac, A. Dragan, J. K. Hedrick, S. Sastry, T. Griffiths. "Goal Inference Improves Objective and Perceived Performance in Human-Robot Collaboration". Autonomous Agents and Multiagent Systems (AAMAS), 2016

详情

展开后加载摘要…

URL PDF HTML 收藏
1409.0302 2014-09-02 cs.MA cs.AI 70%

Team Behavior in Interactive Dynamic Influence Diagrams with Applications to Ad Hoc Teams

Muthukumaran Chandrasekaran, Prashant Doshi, Yifeng Zeng, Yingke Chen

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

Comments 8 pages, Appeared in the MSDM Workshop at AAMAS 2014, Extended Abstract version appeared at AAMAS 2014, France

详情

展开后加载摘要…

URL PDF HTML 收藏
1405.5443 2014-05-22 cs.AI cs.MA 70%

Towards an ASP-Based Architecture for Autonomous UAVs in Dynamic Environments (Extended Abstract)

Marcello Balduccini, William C. Regli, Duc N. Nguyen

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

Comments To appear in Theory and Practice of Logic Programming (TPLP). arXiv admin note: substantial text overlap with arXiv:1405.1124

详情

展开后加载摘要…

URL PDF HTML 收藏
1304.5961 2013-04-23 cs.AI cs.CC cs.LO 70%

Backdoors to Abduction

Andreas Pfandler, Stefan Rümmele, Stefan Szeider

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

Comments 12 pages, a short version will appear in the proceedings of the 23rd International Joint Conference on Artificial Intelligence (IJCAI 2013)

详情

展开后加载摘要…

URL PDF HTML 收藏
1302.1544 2013-02-08 cs.AI cs.GT 70%

Problem-Focused Incremental Elicitation of Multi-Attribute Utility Models

Vu A. Ha, Peter Haddawy

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

Comments Appears in Proceedings of the Thirteenth Conference on Uncertainty in Artificial Intelligence (UAI1997)

详情

展开后加载摘要…

URL PDF HTML 收藏
1206.3281 2012-06-18 cs.AI 70%

Model-Based Bayesian Reinforcement Learning in Large Structured Domains

Stephane Ross, Joelle Pineau

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

Comments Appears in Proceedings of the Twenty-Fourth Conference on Uncertainty in Artificial Intelligence (UAI2008)

详情

展开后加载摘要…

URL PDF HTML 收藏
cmp-lg/9409009 2009-11-30 cmp-lg cs.CL 70%

Linguistics Computation, Automatic Model Generation, and Intensions

Cyrus F. Nourani

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

Comments The paper is plain text.

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.10758 2026-07-08 cs.CR 版本更新 69%

Agents at Risk: How Users Unwittingly Undermine LLM Safety

处于风险中的智能体:用户如何在不知情的情况下破坏大语言模型的安全性

Fengchao Chen, Tingmin Wu, Van Nguyen, Surya. Nepal, Carsten Rudolph

专题命中 规划推理 :planning(abstract,comments);reasoning(abstract)

AI总结 研究基于大语言模型的智能体安全问题,介绍用户中继上下文操纵攻击,通过让良性用户在请求中传递对抗性内容,实验表明该攻击在多种防御下优于提示注入基线,揭示当前智能体框架设计缺陷。

Comments User-relayed Context Manipulation; LLM-based Agents; Agent Security; Human Factors in Cybersecurity; Web-Use Agents; Planning Agents

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.01016 2025-09-03 cs.AI cs.CL cs.LG cs.NE 69%

Analysis of Error Sources in LLM-based Hypothesis Search for Few-Shot Rule Induction

Aishni Parab, Hongjing Lu, Ying Nian Wu, Sumit Gulwani

机构 * Department of Statistics, University of California, Los Angeles(统计学系,加州大学洛杉矶分校) Microsoft, Redmond, WA(微软公司,西雅图,华盛顿州) Department of Psychology, University of California, Los Angeles(心理学系,加州大学洛杉矶分校)

专题命中 规划推理 :reasoning(abstract,comments);分类 cs.CL、cs.AI、cs.LG

Comments This is the preprint version corresponding to our NeurIPS 2025 Workshop on Multimodal Algorithmic Reasoning submission

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.22718 2025-04-01 cs.MA 69%

LLM-ABM for Transportation: Assessing the Potential of LLM Agents in System Analysis

Tianming Liu, Jirong Yang, Yafeng Yin

专题命中 规划推理 :planning(abstract,comments);reasoning(abstract)

Comments Accepted by The 1st Workshop on AI for Urban Planning at AAAI 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.11119 2026-08-25 cs.LG cs.AI cs.CL 版本更新 67%

TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning

TRACE:一种用于高效智能体强化学习的统一展开预算分配框架

Heming Zou, Qi Wang, Yun Qu, Yuhang Jiang, Lizhou Cai, Yixiu Mao, Ru Peng, Xin Xu, Weijie Liu, Kai Yang, Saiyong Yang, Xiangyang Ji

机构 * Tsinghua University(清华大学) Tencent(腾讯)

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

AI总结 针对多轮智能体强化学习中奖励对比度不足的问题,提出TRACE框架,通过将每个ReAct式思考-行动-观察步骤建模为语义节点,在固定采样预算内将预算分配到提示根和中间前缀,增强奖励对比,提升策略更新信号。

Comments Accepted by EMNLP 2026 Main Conference, 32 pages, 12 figures, 6 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.15395 2026-08-25 cs.RO 版本更新 67%

Foundation Models in Robotics: A Comprehensive Review of Methods, Models, Datasets, Challenges and Future Research Directions

机器人中的基础模型:方法、模型、数据集、挑战及未来研究方向的全面综述

Aggelos Psiris, Vasileios Argyriou, Evangelos K. Markakis, Panagiotis Sarigiannidis, Efstratios Gavves, Kostas Bekris, Arash Ajoudani, Georgios Th. Papadopoulos

机构 * Department of Informatics and Telematics, Harokopio University of Athens(信息与电信系,哈罗科比欧大学)

专题命中 规划推理 :reasoning(abstract);planning(abstract)

AI总结 本文综述了机器人中基础模型的发展,涵盖方法、模型、数据集、挑战及未来方向,分析了不同阶段的研究演变及关键方面。

Journal ref Transactions on Machine Learning Research (TMLR), 07/2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.20953 2026-08-24 cs.CL cs.AI cs.LG cs.PF 新提交 67%

Quantization-Aware Healing: A Practical Recipe for Recovering Compressed, 4-Bit LLMs

量化感知修复:恢复压缩4位大语言模型的实用方案

Bakbergen Ryskulov, Iker García-Ferrero, David Montero, David Jansen, Ali Hashemi, Jezabel R. Garcia, Antonio Tiene, Román Orús

机构 * Multiverse Computing(多元宇宙计算公司)

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

AI总结 针对压缩4位大模型部署时性能下降问题,提出量化感知修复方案,直接从原始未压缩模型蒸馏4位学生模型,在多基准测试中表现优于量化感知训练,且部署便捷。

Comments Patent Application Number: 26382838.6 / P202602102EP

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.17970 2026-08-19 cs.CY 新提交 67%

Quo Vadis? Scientific Discovery in the Age of Artificial Intelligence

何去何从?人工智能时代的科学发现

Petr O. Jedlicka

专题命中 规划推理 :reasoning(abstract);planning(abstract)

AI总结 本文梳理AI在科学发现中的作用,提出AI系统类型学,概述多学科近期成果,指出其存在的限制与风险,引发人机认知劳动分工的思考。

Comments To be published in Theory of Science

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.10413 2026-08-12 cs.CV 新提交 67%

DriveVLA-M0: Failure-Aware Memory Augmentation for Autonomous Driving

DriveVLA-M0:面向自动驾驶的故障感知记忆增强方法

Zebin Xing, Yupeng Zheng, Qiang Chen, Linbo Wang, Yichen Zhang, Pengxuan Yang, Junli Wang, Deheng Qian, Xiaoqing Ye, Junyu Han, Yifeng Pan, Qichao Zhang, Dongbin Zhao

机构 * Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所) Chongqing Chang’an Technology Co., Ltd.(重庆长安科技有限公司)

专题命中 规划推理 :reasoning(abstract);planning(abstract)

AI总结 本文提出DriveVLA-M0,一种具备故障感知潜在记忆的检索增强型VLA模型,通过故障案例记忆与针对性修正机制,在NAVSIM基准上优于现有方法,实现自动驾驶性能提升。

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.08485 2026-08-11 cs.AI cs.CL cs.LG 新提交 67%

HoloAegis: Frozen Representation, Topological Inference: Minimally Parametric Safety Manifolds for Zero-Shot LLM Guardrails

HoloAegis:冻结表示、拓扑推理:用于零样本大语言模型(LLM)护栏的最小参数安全流形

Tak Ho Alex Li, Kaijie Liu, Lik-Hang Lee, Kin Chung Ho, Ping Shum, Michael K. Ng

机构 * Hong Kong Baptist University(香港浸会大学) Guangdong Polytechnic Normal University(广东技术师范大学) Guangdong Institute of Digital Industry(广东数字产业研究院) The Hong Kong Polytechnic University(香港理工大学) The Education University of Hong Kong(香港教育大学) Southern University of Science and Technology(南方科技大学)

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

AI总结 HoloAegis是一种最小参数拓扑推理框架,通过冻结语义表示的纯几何推理实现零样本LLM安全护栏,在8个基准测试中达到最先进准确率,兼具低延迟、零冷启动数据和跨语言迁移能力。

Comments Preprint, August 2026. 10 tables, 2 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.08175 2026-08-11 cs.MA 新提交 67%

AOC-CBS: Anytime-Optimal Continuous-time Conflict-Based Search for Generalised Multi-Agent Path Finding

AOC-CBS:适用于通用多智能体路径规划的任何时候最优连续时间基于冲突的搜索算法

Alvin Combrink, Sabino Francesco Roselli, Martin Fabian

专题命中 规划推理 :planning(abstract,abstract_cn)

AI总结 本研究针对通用多智能体路径规划问题,提出AOC-CBS算法,该算法可 anytime-optimal 求解,实验表明其在接受有界最优性间隙时能将可扩展性从数十智能体扩展到数百个。

Comments 65 pages, 19 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.24744 2026-08-11 cs.RO cs.CV 版本更新 67%

Data Pyramid for Embodied Manipulation: A Survey

用于具身操纵的数据金字塔

Yifan Ye, Yankai Fu, Yaoxu Lv, Bohan Hou, Jun Cen, Lingdong Kong, Duo Zheng, Tianxing Chen, Jiaming Liu, Ziang Cao, Yunfan Lou, Wei Chow, Xian Sun, Yingshuo Wang, Kuangzhi Ge, Xiaowei Chi, Xidong Zhang, Zhibo Pang, Yiwu Zhong, Sirui Han, Zhihe Lu, Weihao Yuan, Qifeng Chen, Michael Yu Wang, Yao Mu, Ziwei Liu, Jianfei Yang, Ping Luo, Shanghang Zhang

机构 * PKU(北京大学) NTU(南洋理工大学) HKUST(香港科技大学) NUS(新加坡国立大学) CUHK(香港中文大学) HKU(香港大学) Duke(杜克大学) UCB(加州大学伯克利分校) GBU(未提及具体中文名的机构) NJU(南京大学) SJTU(上海交通大学)

专题命中 规划推理 :reasoning(abstract);planning(abstract)

AI总结 研究围绕具身操纵数据生态系统展开,构建跨越五个互补数据源的“数据金字塔”,通过数据配方分析具身基础模型,将数据组成与多种能力联系起来,并讨论了六个开放挑战,为下一代具身系统设计奠定基础。

Comments Awesome Embodied Data Pyramid; Project Page at https://jasper-aaa.github.io/embodied-data-pyramid/ GitHub Repo at https://github.com/worldbench/awesome-embodied-data-pyramid

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.06701 2026-08-10 cs.SE cs.AI cs.CL cs.LG 新提交 67%

Online Monitoring and Corrective Steering of Programming Agents

编程智能体的在线监控与纠正引导

Shuyang Liu, Saman Dehghan, Ji Young Kim, Jatin Ganhotra, Martin Hirzel, Reyhaneh Jabbarvand

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

AI总结 本文提出LivePlan,通过解耦判断与建议的设计,在SWE-agent基础上实现编程智能体的在线监控与纠正,在SWE-bench数据集上显著提升问题解决率,且成本增量极小。

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.06651 2026-08-10 cs.CR cs.SE 新提交 67%

CyberLLM: A Multi-Agent LLM Framework for Autonomous Detection and Guarded Response in Automotive Cybersecurity

CyberLLM:面向汽车网络安全的多智能体大语言模型框架,用于自主检测与受管控响应

Nenad Petrovic, Oussama Jeddou, Feres Ben Fraj, Vahid Zolfaghari, Fengjunjie Pan, Andre Schamschurko, Alois Knoll

专题命中 规划推理 :reasoning(abstract);planning(abstract)

AI总结 CyberLLM是由大语言模型编排的多智能体框架,结合确定性检测层与大语言模型精化,在安全防护下实现汽车漏洞自主检测与修复,在基准测试中覆盖约70%漏洞且零误报,验证了LLM智能体自主防御的可行性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.00028 2026-08-10 cs.CL cs.AI cs.LG cs.SI 版本更新 67%

Harnessing the Synergy between LLM Agents and Knowledge Graphs for Urban Socioeconomic Prediction

利用大语言模型智能体与知识图谱的协同作用进行城市社会经济预测

Zhilun Zhou, Jingyang Fan, Yu Liu, Fengli Xu, Depeng Jin, Yong Li

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

AI总结 本研究提出LLM智能体与知识图谱的协同框架,结合二者优势完成城市社会经济预测,经实验验证该协同设计可提升预测效果,为跨任务信息共享提供思路。

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.12029 2026-08-05 cs.SE 版本更新 67%

Enhancing LLM Performance Through Debate: An Empirical Study on Multi-Agent Debate for Coding Tasks

通过辩论提升大语言模型性能:针对编码任务的多智能体辩论实证研究

Yong Jin Chun, Qihong Chen, Jiawei Li, Iftekhar Ahmed

专题命中 规划推理 :reasoning(abstract);planning(abstract)

AI总结 本研究探究多智能体辩论(MAD)在软件工程四类编码任务上的有效性,适配NLP的MAD框架并提出两种变体,证实结构化辩论可提升LLM编码性能,凸显其协作协同效应。

Comments accepted to ACM Transactions on Software Engineering and Methodology (TOSEM)

详情

展开后加载摘要…

URL PDF HTML 收藏