大模型推理能力

Large language model empowered participatory urban planning

Zhilun Zhou, Yuming Lin, Yong Li

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

Comments 26 pages, 7 figures, 2 tables

Natural Language based Context Modeling and Reasoning for Ubiquitous Computing with Large Language Models: A Tutorial

Haoyi Xiong, Jiang Bian, Sijia Yang, Xiaofei Zhang, Linghe Kong, Daqing Zhang

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

Comments Under review

No Train Still Gain. Unleash Mathematical Reasoning of Large Language Models with Monte Carlo Tree Search Guided by Energy Function

Haotian Xu

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

Comments still in progress

On the Planning, Search, and Memorization Capabilities of Large Language Models

Yunhao Yang, Anshul Tomar

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

Comments 13 pages, 2 figures

Deductive Additivity for Planning of Natural Language Proofs

Zayne Sprague, Kaj Bostrom, Swarat Chaudhuri, Greg Durrett

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

Translating Natural Language to Planning Goals with Large-Language Models

Yaqi Xie, Chen Yu, Tongyao Zhu, Jinbin Bai, Ze Gong, Harold Soh

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

PlanT: Explainable Planning Transformers via Object-Level Representations

Katrin Renz, Kashyap Chitta, Otniel-Bogdan Mercea, A. Sophia Koepke, Zeynep Akata, Andreas Geiger

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

Comments CoRL 2022. Project Page: https://www.katrinrenz.de/plant/

Generating Natural Language Proofs with Verifier-Guided Search

Kaiyu Yang, Jia Deng, Danqi Chen

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

Comments EMNLP 2022. Code and models are available at https://github.com/princeton-nlp/NLProofS. v3 added evaluation of GPT-3 and Codex

Deep Structured Reactive Planning

Jerry Liu, Wenyuan Zeng, Raquel Urtasun, Ersin Yumer

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

Comments ICRA 2021

Physically Embedded Planning Problems: New Challenges for Reinforcement Learning

Mehdi Mirza, Andrew Jaegle, Jonathan J. Hunt, Arthur Guez, Saran Tunyasuvunakool, Alistair Muldal, Théophane Weber, Peter Karkus, Sébastien Racanière, Lars Buesing, Timothy Lillicrap, Nicolas Heess

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

Comments 17 pages + appendix. Updated text and references

From proprioception to long-horizon planning in novel environments: A hierarchical RL model

Nishad Gothoskar, Miguel Lázaro-Gredilla, Dileep George

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

Search on the Replay Buffer: Bridging Planning and Reinforcement Learning

Benjamin Eysenbach, Ruslan Salakhutdinov, Sergey Levine

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

Comments Run our algorithm in your browser: http://bit.ly/rl_search

Automatic Ontology Construction Using LLMs as an External Layer of Memory, Verification, and Planning for Hybrid Intelligent Systems

利用LLMs构建自动本体：作为混合智能系统记忆、验证和规划的外部层

Pavel Salovskii, Iuliia Gorshkova

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

AI总结 本文提出了一种混合架构，通过扩展LLMs的外部本体记忆层，实现结构化知识图谱的构建与维护，提升多步推理性能并支持生成-验证-修正流程。

Comments Artificial Intelligence; Knowledge Representation and Reasoning; Information Retrieval; Machine Learning

A Roadmap to Guide the Integration of LLMs in Hierarchical Planning

引导大型语言模型在分层规划中整合的路线图

Israel Puerta-Merino, Carlos Núñez-Molina, Pablo Mesejo, Juan Fernández-Olivares

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

AI总结 本文提出了一条引导大型语言模型在分层规划中整合的路线图，通过分类整合方法和建立基准测试，探索LLMs在分层规划中的应用潜力。

Comments 5 pages, 0 figures, to be published in the AAAI Workshop on Planning in the Era of LLMs ( https://llmforplanning.github.io )

From System 1 to System 2: A Survey of Reasoning Large Language Models

Zhong-Zhi Li, Duzhen Zhang, Ming-Liang Zhang, Jiaxin Zhang, Zengyan Liu, Yuxuan Yao, Haotian Xu, Junhao Zheng, Pei-Jie Wang, Xiuyi Chen, Yingying Zhang, Fei Yin, Jiahua Dong, Zhiwei Li, Bao-Long Bi, Ling-Rui Mei, Junfeng Fang, Xiao Liang, Zhijiang Guo, Le Song, Cheng-Lin Liu

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

Comments Slow-thinking, Large Language Models, Human-like Reasoning, Decision Making in AI, AGI

Towards Zero-Shot, Controllable Dialog Planning with LLMs

Dirk Väth, Ngoc Thang Vu

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

Comments This paper has been accepted for publication at the AAAI 2022 Workshop on Planning in the Era of LLMs

Tree-of-Code: A Hybrid Approach for Robust Complex Task Planning and Execution

Ziyi Ni, Yifan Li, Daxiang Dong

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

Comments Submitted to the Neurips Workshop "System 2 Reasoning" in September, 2024. The openreview is avaliable at https://openreview.net/forum?id=8NKAL8Ngxk

PROC2PDDL: Open-Domain Planning Representations from Texts

Tianyi Zhang, Li Zhang, Zhaoyi Hou, Ziyu Wang, Yuling Gu, Peter Clark, Chris Callison-Burch, Niket Tandon

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

Comments In NLRSE 2024, the 2nd Natural Language Reasoning and Structured Explanations Workshop

LLM-SAP: Large Language Models Situational Awareness Based Planning

Liman Wang, Hanyang Zhong

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

Comments This article has been accepted by ICME2024 Workshop MML4SG. Website:https://github.com/HanyangZhong/Situational_Planning_datasets

Towards Using Promises for Multi-Agent Cooperation in Goal Reasoning

Daniel Swoboda, Till Hofmann, Tarik Viehmann, Gerhard Lakemeyer

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

Comments Presented at the ICAPS'22 Workshop on Planning and Robotics (PlanRob)

Efficient Multi-agent Epistemic Planning: Teaching Planners About Nested Belief

Christian Muise, Vaishak Belle, Paolo Felli, Sheila McIlraith, Tim Miller, Adrian R. Pearce, Liz Sonenberg

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

Comments Published in Special Issue of the Artificial Intelligence Journal (AIJ) on Epistemic Planning

Contingencies from Observations: Tractable Contingency Planning with Learned Behavior Models

Nicholas Rhinehart, Jeff He, Charles Packer, Matthew A. Wright, Rowan McAllister, Joseph E. Gonzalez, Sergey Levine

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

Comments To be published at ICRA 2021. Project page: https://sites.google.com/view/contingency-planning

Adaptive Informative Path Planning with Multimodal Sensing

Shushman Choudhury, Nate Gruver, Mykel J. Kochenderfer

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

Comments First two authors contributed equally; International Conference on Automated Planning and Scheduling (ICAPS) 2020

Towards Combining HTN Planning and Geometric Task Planning

Lavindra de Silva, Amit Kumar Pandey, Mamoun Gharbi, Rachid Alami

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

Comments RSS Workshop on Combined Robot Motion Planning and AI Planning for Practical Applications, June 2013

ReferTrack: Referring Then Tracking for Embodied Visual Tracking

ReferTrack：用于具身视觉跟踪的先指认后跟踪

Hanjing Ye, Tianle Zeng, Jiazhao Zhang, Shaoan Wang, Zibo Zhang, Weisi Situ, Yuchen Zhou, Yonggen Ling, Hong Zhang

机构 * SUSTech（南方科技大学） ； Tencent Robotics X（腾讯机器人X实验室） ； Peking University（北京大学） ； Futian Laboratory（福田实验室） 纠错

专题命中 规划推理 ：CoT(abstract,abstract_cn)；reasoning(abstract)；chain-of-thought(abstract)；planning(abstract)

AI总结 研究针对具身视觉跟踪问题，提出ReferTrack先指认后跟踪范式，用单个摄像头，先选目标再解码跟踪航点，通过滑动窗口队列保留运动线索，经数据集协同训练增强识别，在EVT - Bench上达先进单视图性能并验证了迁移能力。

Leveraging Inter-object Affordances for Efficient Planning in Contact-rich Tasks

利用物体间可供性实现接触密集型任务的高效规划

Pouya P. Niaz, Justus Piater, Alejandro Agostini

机构 * University of Innsbruck（因斯布鲁克大学） 纠错

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

AI总结 该研究针对传统TAMP方法在接触密集型任务中规划时间长、成功率低的问题，提出结合VLM与U-TAMP的方法，在模拟厨房场景中实现了更高的规划成功率与更快的规划速度。

LifePlanner: Evaluating LLM Agents for Geo-spatial Planning with Social Media Data

LifePlanner：利用社交媒体数据评估LLM智能体的地理空间规划能力

Zhen Dong, Yuning Peng, Yutao Shi, Lei Zhong, Yongsen Mao, Yuan Liu, Haiping Wang

机构 * Wuhan University（武汉大学） ； Hong Kong University of Science and Technology（香港科技大学） 纠错

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

AI总结 该研究推出LifePlanner基准测试，结合社交媒体数据评估LLM智能体的地理空间规划能力，发现前沿LLM在简单检索中表现好但复杂规划通过率仅40.2%，失败源于证据获取、工具使用及约束整合问题，需改进实际规划能力而非单纯扩大模型规模。

Comments 25 pages, 7 figures, 11 tables

OSCAR: Optimization-Steered Agentic Planning for Composed Image Retrieval

OSCAR：基于优化的代理规划用于组合图像检索

Teng Wang, Rong Shan, Jianghao Lin, Junjie Wu, Tianyi Xu, Jianping Zhang, Wenteng Chen, Changwang Zhang, Zhaoxiang Wang, Weinan Zhang, Jun Wang

机构 * Shanghai Jiao Tong University（上海交通大学） 纠错

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

AI总结 OSCAR通过优化引导的代理规划框架，提升组合图像检索的性能，仅用10%训练数据即超越现有最佳方法。

Comments EMNLP 2026 Main Conference

Efficient LLM Collaboration via Planning

通过规划实现高效的LLM协作

Byeongchan Lee, Jonghoon Lee, Dongyoung Kim, Jaehyung Kim, Kyungjoon Park, Dongjun Lee, Jinwoo Shin

机构 * KAIST（韩国科学技术院） ； Yonsei University（延世大学） 纠错

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

AI总结 本文提出COPE框架，通过规划模型与执行模型的协作，提升小模型和大模型在复杂任务中的性能，同时显著降低推理成本。

Comments Accepted at TMLR 2026

Geo-VLA: Geometry-Aware Vision-Language-Action Planning via Internalization of Map Semantics

Geo-VLA：通过内化地图语义实现几何感知的视觉-语言-动作规划

Ran Chen, Jiaxing Ren, Zhikun Zhang, Yunhao Hou, Junbao Zhuo, Bochao Zou

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

AI总结 该研究针对VLA模型在复杂驾驶场景中规划性能不足的问题，提出可即插即用的Geo-VLA框架，结合自研Geo-QA数据集，在NAVSIM v1上实现单目VLA规划器的新SOTA。