大模型推理能力 - arXivDaily 专题

2407.14414 2025-04-16 cs.AI cs.CL cs.LG 82%

System-1.x: Learning to Balance Fast and Slow Planning with Language Models

Swarnadeep Saha, Archiki Prasad, Justin Chih-Yao Chen, Peter Hase, Elias Stengel-Eskin, Mohit Bansal

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

Comments ICLR 2025 (Camera-Ready)

2409.19250 2025-04-01 cs.RO 82%

Fast and Accurate Task Planning using Neuro-Symbolic Language Models and Multi-level Goal Decomposition

Minseo Kwon, Yaesol Kim, Young J. Kim

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

2503.09276 2025-03-13 cs.CY 82%

Fine-Tuning Large Language Models for Educational Support: Leveraging Gagne's Nine Events of Instruction for Lesson Planning

Linzhao Jia, Changyong Qi, Yuang Wei, Han Sun, Xiaozhe Yang

专题命中规划推理：planning(title,abstract)；CoT(abstract)

2503.09024 2025-03-13 cs.RO cs.SY eess.IV eess.SY 82%

Traffic Regulation-aware Path Planning with Regulation Databases and Vision-Language Models

Xu Han, Zhiwen Wu, Xin Xia, Jiaqi Ma

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

Comments 7 pages, 7 figures, submitted to ICRA

2503.07608 2025-03-11 cs.CV cs.RO 82%

AlphaDrive: Unleashing the Power of VLMs in Autonomous Driving via Reinforcement Learning and Reasoning

Bo Jiang, Shaoyu Chen, Qian Zhang, Wenyu Liu, Xinggang Wang

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

Comments Project Page: https://github.com/hustvl/AlphaDrive

2503.02698 2025-03-05 cs.RO 82%

FlowPlan: Zero-Shot Task Planning with LLM Flow Engineering for Robotic Instruction Following

Zijun Lin, Chao Tang, Hanjing Ye, Hong Zhang

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

Comments 8 pages, 5 figures

2503.01007 2025-03-04 cs.RO 82%

From Vague Instructions to Task Plans: A Feedback-Driven HRC Task Planning Framework based on LLMs

Afagh Mehri Shervedani, Matthew R. Walter, Milos Zefran

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

2502.12862 2025-02-19 cs.RO cs.SY eess.SY 82%

RobotIQ: Empowering Mobile Robots with Human-Level Planning for Real-World Execution

Emmanuel K. Raptis, Athanasios Ch. Kapoutsis, Elias B. Kosmatopoulos

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

2405.14075 2025-02-18 cs.CL cs.AI cs.LG 82%

$T^2$ of Thoughts: Temperature Tree Elicits Reasoning in Large Language Models

Chengkun Cai, Xu Zhao, Yucheng Du, Haoliang Liu, Lei Li

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

Comments 8 pages, 4 figures

2408.00764 2025-02-07 cs.CL cs.AI cs.LG 82%

AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generation

Mengkang Hu, Pu Zhao, Can Xu, Qingfeng Sun, Jianguang Lou, Qingwei Lin, Ping Luo, Saravan Rajmohan

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

Comments Accepted by KDD 2025 (Research Track). Project page: https://agent-gen.github.io/

2407.10031 2025-01-14 cs.RO cs.MA 82%

LLaMAR: Long-Horizon Planning for Multi-Agent Robots in Partially Observable Environments

Siddharth Nayak, Adelmo Morrison Orozco, Marina Ten Have, Vittal Thirumalai, Jackson Zhang, Darren Chen, Aditya Kapoor, Eric Robinson, Karthik Gopalakrishnan, James Harrison, Brian Ichter, Anuj Mahajan, Hamsa Balakrishnan

专题命中规划推理：planning(title,abstract)；self-correction(abstract)

Comments 27 pages, 4 figures, 5 tables

2402.07204 2025-01-10 cs.AI cs.CL cs.LG 82%

ITINERA: Integrating Spatial Optimization with Large Language Models for Open-domain Urban Itinerary Planning

Yihong Tang, Zhaokai Wang, Ao Qu, Yihao Yan, Zhaofeng Wu, Dingyi Zhuang, Jushi Kai, Kebing Hou, Xiaotong Guo, Han Zheng, Tiange Luo, Jinhua Zhao, Zhan Zhao, Wei Ma

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

2501.01478 2025-01-06 cs.AI cs.CL cs.LG 82%

Enhancing Reasoning through Process Supervision with Monte Carlo Tree Search

Shuangtao Li, Shuaihao Dong, Kexin Luan, Xinhan Di, Chaofan Ding

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

Comments 5 pages, 1 figure, 2 tables accepted by aaai 2025 NeurMAD workshop

2405.14205 2025-01-06 cs.CL cs.AI cs.CV cs.LG cs.MA 82%

Agent Planning with World Knowledge Model

Shuofei Qiao, Runnan Fang, Ningyu Zhang, Yuqi Zhu, Xiang Chen, Shumin Deng, Yong Jiang, Pengjun Xie, Fei Huang, Huajun Chen

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

Comments NeurIPS 2024

2404.05545 2024-12-24 cs.LG cs.AI cs.CL stat.ME 82%

Evaluating Interventional Reasoning Capabilities of Large Language Models

Tejas Kasetty, Divyat Mahajan, Gintare Karolina Dziugaite, Alexandre Drouin, Dhanya Sridhar

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

Comments 17 pages

2412.11621 2024-12-17 cs.CV cs.MM 82%

VG-TVP: Multimodal Procedural Planning via Visually Grounded Text-Video Prompting

Muhammet Furkan Ilaslan, Ali Koksal, Kevin Qinhong Lin, Burak Satar, Mike Zheng Shou, Qianli Xu

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

Comments Accepted for The 39th Annual AAAI Conference on Artificial Intelligence 2025 in Main Track, 19 pages, 24 figures

2401.05577 2024-11-26 cs.CV 82%

VLP: Vision Language Planning for Autonomous Driving

Chenbin Pan, Burhaneddin Yaman, Tommaso Nesti, Abhirup Mallik, Alessandro G Allievi, Senem Velipasalar, Liu Ren

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

Comments CVPR2024

Journal ref CVPR2024

2411.09971 2024-11-18 cs.CV cs.RO 82%

Explanation for Trajectory Planning using Multi-modal Large Language Model for Autonomous Driving

Shota Yamazaki, Chenyu Zhang, Takuya Nanri, Akio Shigekane, Siyuan Wang, Jo Nishiyama, Tao Chu, Kohei Yokosawa

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

Comments Accepted and presented at ECCV 2024 2nd Workshop on Vision-Centric Autonomous Driving (VCAD) on September 30, 2024. 13 pages, 5 figures

2411.05212 2024-11-11 cs.RO 82%

RT-Grasp: Reasoning Tuning Robotic Grasping via Multi-modal Large Language Model

Jinxuan Xu, Shiyu Jin, Yutian Lei, Yuqian Zhang, Liangjun Zhang

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

Comments Accepted to IROS 2024

2408.12036 2024-11-04 cs.LG cs.AI cs.CL cs.IR 82%

Reasoning and Tools for Human-Level Forecasting

Elvis Hsieh, Preston Fu, Jonathan Chen

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

2410.19727 2024-10-28 cs.AI cs.CL cs.IR cs.LG 82%

FISHNET: Financial Intelligence from Sub-querying, Harmonizing, Neural-Conditioning, Expert Swarms, and Task Planning

Nicole Cho, Nishan Srishankar, Lucas Cecchi, William Watson

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

Comments Accepted at the 5th ACM International Conference on AI in Finance (ICAIF '24)

2410.00371 2024-10-02 cs.RO 82%

AHA: A Vision-Language-Model for Detecting and Reasoning Over Failures in Robotic Manipulation

Jiafei Duan, Wilbert Pumacay, Nishanth Kumar, Yi Ru Wang, Shulin Tian, Wentao Yuan, Ranjay Krishna, Dieter Fox, Ajay Mandlekar, Yijie Guo

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

Comments Appendix and details can be found in project website: https://aha-vlm.github.io/

2410.00079 2024-10-02 cs.MA cs.AI cs.CL cs.HC cs.LG 82%

Interactive Speculative Planning: Enhance Agent Efficiency through Co-design of System and User Interface

Wenyue Hua, Mengting Wan, Shashank Vadrevu, Ryan Nadel, Yongfeng Zhang, Chi Wang

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

Comments 27 pages, 22 figures

2409.20557 2024-10-01 cs.CV 82%

Propose, Assess, Search: Harnessing LLMs for Goal-Oriented Planning in Instructional Videos

Md Mohaiminul Islam, Tushar Nagarajan, Huiyu Wang, Fu-Jen Chu, Kris Kitani, Gedas Bertasius, Xitong Yang

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

Comments Accepted by ECCV 2024 (Oral)

2409.09513 2024-09-17 cs.LG cs.AI cs.CL 82%

Planning Transformer: Long-Horizon Offline Reinforcement Learning with Planning Tokens

Joseph Clinton, Robert Lieck

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

Comments 11 pages, 5 figures, Submitted to AAAI

2408.07531 2024-08-28 cs.AI cs.CL cs.LG 82%

Development of a Large Language Model-based Multi-Agent Clinical Decision Support System for Korean Triage and Acuity Scale (KTAS)-Based Triage and Treatment Planning in Emergency Departments

Seungjun Han, Wongyung Choi

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

2306.09237 2024-08-22 cs.CL cs.AI cs.LG 82%

One Law, Many Languages: Benchmarking Multilingual Legal Reasoning for Judicial Support

Ronja Stern, Vishvaksenan Rasiah, Veton Matoshi, Srinanda Brügger Bose, Matthias Stürmer, Ilias Chalkidis, Daniel E. Ho, Joel Niklaus

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

2404.04929 2024-07-31 cs.RO 82%

RoboMP$^2$: A Robotic Multimodal Perception-Planning Framework with Multimodal Large Language Models

Qi Lv, Hao Li, Xiang Deng, Rui Shao, Michael Yu Wang, Liqiang Nie

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

Comments Accepted by ICML 2024; Project page: https://aopolin-lv.github.io/RoboMP2.github.io/

Journal ref Proceedings of the 41st International Conference on Machine Learning, PMLR 235:33558-33574, 2024

2310.08582 2024-07-25 cs.CL cs.AI cs.LG cs.RO 82%

Tree-Planner: Efficient Close-loop Task Planning with Large Language Models

Mengkang Hu, Yao Mu, Xinmiao Yu, Mingyu Ding, Shiguang Wu, Wenqi Shao, Qiguang Chen, Bin Wang, Yu Qiao, Ping Luo

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

Comments Published in ICLR 2024

2402.06559 2024-07-18 cs.LG cs.AI cs.CL cs.RO 82%

Diffusion-ES: Gradient-free Planning with Diffusion for Autonomous Driving and Zero-Shot Instruction Following

Brian Yang, Huangyuan Su, Nikolaos Gkanatsios, Tsung-Wei Ke, Ayush Jain, Jeff Schneider, Katerina Fragkiadaki

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

1. 规划推理 11104 篇

System-1.x: Learning to Balance Fast and Slow Planning with Language Models

Fast and Accurate Task Planning using Neuro-Symbolic Language Models and Multi-level Goal Decomposition

Fine-Tuning Large Language Models for Educational Support: Leveraging Gagne's Nine Events of Instruction for Lesson Planning

Traffic Regulation-aware Path Planning with Regulation Databases and Vision-Language Models

AlphaDrive: Unleashing the Power of VLMs in Autonomous Driving via Reinforcement Learning and Reasoning

FlowPlan: Zero-Shot Task Planning with LLM Flow Engineering for Robotic Instruction Following

From Vague Instructions to Task Plans: A Feedback-Driven HRC Task Planning Framework based on LLMs

RobotIQ: Empowering Mobile Robots with Human-Level Planning for Real-World Execution

$T^2$ of Thoughts: Temperature Tree Elicits Reasoning in Large Language Models

AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generation

LLaMAR: Long-Horizon Planning for Multi-Agent Robots in Partially Observable Environments

ITINERA: Integrating Spatial Optimization with Large Language Models for Open-domain Urban Itinerary Planning

Enhancing Reasoning through Process Supervision with Monte Carlo Tree Search

Agent Planning with World Knowledge Model

Evaluating Interventional Reasoning Capabilities of Large Language Models

VG-TVP: Multimodal Procedural Planning via Visually Grounded Text-Video Prompting

VLP: Vision Language Planning for Autonomous Driving

Explanation for Trajectory Planning using Multi-modal Large Language Model for Autonomous Driving

RT-Grasp: Reasoning Tuning Robotic Grasping via Multi-modal Large Language Model

Reasoning and Tools for Human-Level Forecasting

FISHNET: Financial Intelligence from Sub-querying, Harmonizing, Neural-Conditioning, Expert Swarms, and Task Planning

AHA: A Vision-Language-Model for Detecting and Reasoning Over Failures in Robotic Manipulation

Interactive Speculative Planning: Enhance Agent Efficiency through Co-design of System and User Interface

Propose, Assess, Search: Harnessing LLMs for Goal-Oriented Planning in Instructional Videos

Planning Transformer: Long-Horizon Offline Reinforcement Learning with Planning Tokens

Development of a Large Language Model-based Multi-Agent Clinical Decision Support System for Korean Triage and Acuity Scale (KTAS)-Based Triage and Treatment Planning in Emergency Departments

One Law, Many Languages: Benchmarking Multilingual Legal Reasoning for Judicial Support

RoboMP$^2$: A Robotic Multimodal Perception-Planning Framework with Multimodal Large Language Models

Tree-Planner: Efficient Close-loop Task Planning with Large Language Models

Diffusion-ES: Gradient-free Planning with Diffusion for Autonomous Driving and Zero-Shot Instruction Following