语言大模型 / LLM - arXivDaily 专题

2310.08118 2023-10-13 cs.AI 89%

Can Large Language Models Really Improve by Self-critiquing Their Own Plans?

Karthik Valmeekam, Matthew Marquez, Subbarao Kambhampati

专题命中推理与问题求解：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.AI

2310.08034 2023-10-13 cs.HC cs.AI cs.RO 89%

Receive, Reason, and React: Drive as You Say with Large Language Models in Autonomous Vehicles

Can Cui, Yunsheng Ma, Xu Cao, Wenqian Ye, Ziran Wang

专题命中推理与问题求解：large language model(title,abstract)；language model(title,abstract)；prompting(abstract)；分类 cs.AI

Comments arXiv admin note: text overlap with arXiv:2309.10228

2305.14069 2023-10-13 cs.CL 89%

Evaluating Factual Consistency of Summaries with Large Language Models

Shiqi Chen, Siyang Gao, Junxian He

专题命中推理与问题求解：large language model(title,abstract)；language model(title,abstract)；prompting(abstract)；分类 cs.CL

2310.04560 2023-10-10 cs.LG 89%

Talk like a Graph: Encoding Graphs for Large Language Models

Bahare Fatemi, Jonathan Halcrow, Bryan Perozzi

专题命中推理与问题求解：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.LG

2309.06687 2023-10-03 cs.RO cs.AI 89%

Self-Refined Large Language Model as Automated Reward Function Designer for Deep Reinforcement Learning in Robotics

Jiayang Song, Zhehua Zhou, Jiawei Liu, Chunrong Fang, Zhan Shu, Lei Ma

专题命中推理与问题求解：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.AI

2309.16436 2023-09-29 cs.AI cs.LO 89%

Neuro Symbolic Reasoning for Planning: Counterexample Guided Inductive Synthesis using Large Language Models and Satisfiability Solving

Sumit Kumar Jha, Susmit Jha, Patrick Lincoln, Nathaniel D. Bastian, Alvaro Velasquez, Rickard Ewetz, Sandeep Neema

专题命中推理与问题求解：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.AI

Comments 25 pages, 7 figures

2307.06135 2023-09-29 cs.RO cs.AI 89%

SayPlan: Grounding Large Language Models using 3D Scene Graphs for Scalable Robot Task Planning

Krishan Rana, Jesse Haviland, Sourav Garg, Jad Abou-Chakra, Ian Reid, Niko Suenderhauf

专题命中推理与问题求解：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.AI

Comments Accepted for oral presentation at the Conference on Robot Learning (CoRL), 2023. Project page can be found here: https://sayplan.github.io

2309.12767 2023-09-25 cs.CL 89%

Furthest Reasoning with Plan Assessment: Stable Reasoning Path with Retrieval-Augmented Large Language Models

Yin Zhu, Zhiling Luo, Gong Cheng

专题命中推理与问题求解：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL

2309.12278 2023-09-22 cs.CL 89%

Inspire the Large Language Model by External Knowledge on BioMedical Named Entity Recognition

Junyi Bian, Jiaxuan Zheng, Yuyi Zhang, Shanfeng Zhu

专题命中推理与问题求解：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL

Comments 10 pages, 5 figures

2305.11483 2023-08-31 cs.HC cs.AI 89%

Sensecape: Enabling Multilevel Exploration and Sensemaking with Large Language Models

Sangho Suh, Bryan Min, Srishti Palani, Haijun Xia

专题命中推理与问题求解：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.AI

Comments 18 pages, 14 figures, Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology (UIST '23), San Francisco, CA, USA

2308.04709 2023-08-10 cs.CL 89%

A Comparative Study of Open-Source Large Language Models, GPT-4 and Claude 2: Multiple-Choice Test Taking in Nephrology

Sean Wu, Michael Koo, Lesley Blum, Andy Black, Liyo Kao, Fabien Scalzo, Ira Kurtz

专题命中推理与问题求解：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL

Comments 7 pages, 3 figures, 1 table

2307.09923 2023-07-20 cs.CL 89%

Large Language Models can accomplish Business Process Management Tasks

Michael Grohs, Luka Abb, Nourhan Elsayed, Jana-Rebecca Rehse

专题命中推理与问题求解：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL

Comments Accepted at NLP4BPM workshop at BPM 2023

2307.08922 2023-07-19 cs.CL 89%

Large Language Models Perform Diagnostic Reasoning

Cheng-Kuang Wu, Wei-Lin Chen, Hsin-Hsi Chen

专题命中推理与问题求解：large language model(title,abstract)；language model(title,abstract)；prompting(abstract)；分类 cs.CL

Comments Accepted as a Tiny Paper at ICLR 2023 (10 pages, 5 figures)

2307.07162 2023-07-17 cs.RO cs.CL 89%

Drive Like a Human: Rethinking Autonomous Driving with Large Language Models

Daocheng Fu, Xin Li, Licheng Wen, Min Dou, Pinlong Cai, Botian Shi, Yu Qiao

专题命中推理与问题求解：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL

2307.01848 2023-07-07 cs.CV cs.AI cs.RO 89%

Embodied Task Planning with Large Language Models

Zhenyu Wu, Ziwei Wang, Xiuwei Xu, Jiwen Lu, Haibin Yan

专题命中推理与问题求解：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.AI

Comments Project Page: https://gary3410.github.io/TaPA

2306.08891 2023-06-16 cs.CL 89%

Interleaving Pre-Trained Language Models and Large Language Models for Zero-Shot NL2SQL Generation

Zihui Gu, Ju Fan, Nan Tang, Songyue Zhang, Yuxin Zhang, Zui Chen, Lei Cao, Guoliang Li, Sam Madden, Xiaoyong Du

专题命中推理与问题求解：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL

Comments Working in progress

2305.16151 2023-05-26 cs.AI 89%

Understanding the Capabilities of Large Language Models for Automated Planning

Vishal Pallagani, Bharath Muppasani, Keerthiram Murugesan, Francesca Rossi, Biplav Srivastava, Lior Horesh, Francesco Fabiano, Andrea Loreggia

专题命中推理与问题求解：large language model(title,abstract)；language model(title,abstract)；prompting(abstract)；分类 cs.AI

Comments 12 pages

2305.04676 2023-05-09 cs.CL 89%

Enhancing Knowledge Graph Construction Using Large Language Models

Milena Trajanoska, Riste Stojanov, Dimitar Trajanov

专题命中推理与问题求解：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL

2303.14143 2023-03-27 cs.HC cs.AI 89%

"Get ready for a party": Exploring smarter smart spaces with help from large language models

Evan King, Haoxiang Yu, Sangsu Lee, Christine Julien

专题命中推理与问题求解：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.AI

Comments 7 pages, 4 figures

2608.13567 2026-08-17 cs.AI cs.CL cs.LG 新提交 89%

Modular Cognitive Architecture Emerges in Large Language Models

大型语言模型中出现的模块化认知架构

Pengrui Han, Jacob Andreas, Evelina Fedorenko, Andrea Gregor de Varda

专题命中推理与问题求解：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL、cs.AI、cs.LG；LLM(comments)

AI总结该研究探究大型语言模型是否会出现类似人类大脑的模块化认知架构，经对4个认知领域46项任务的回路分析，发现其会形成相似模块化架构，表明模块化可能是智能系统的基本属性。

Comments https://pengrui-han.github.io/LLM_Modularity_Page/

2504.11364 2025-10-29 cs.LG cs.AI cs.CL 89%

Offline Learning and Forgetting for Reasoning with Large Language Models

Tianwei Ni, Allen Nie, Sapana Chaudhary, Yao Liu, Huzefa Rangwala, Rasool Fakoor

机构 * Mila - Quebec AI Institute & Université de Montréal（魁北克AI研究所与蒙特利尔大学）； Amazon Web Services（亚马逊网络服务）

专题命中推理与问题求解：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL、cs.AI、cs.LG；LLM(comments)

Comments Published in Transactions on Machine Learning Research (TMLR), 2025. Code: https://github.com/twni2016/llm-reasoning-uft

2409.12262 2025-03-24 cs.RO 89%

Bootstrapping Object-level Planning with Large Language Models

David Paulius, Alejandro Agostini, Benedict Quartey, George Konidaris

专题命中推理与问题求解：large language model(title,abstract)；language model(title,abstract)；LLM(abstract,comments)

Comments Accepted to ICRA 2025; 11 pages (6 pages + 1 page references + 4 pages appendix); for demo videos, please see https://davidpaulius.github.io/olp_llm/

2402.05808 2024-03-19 cs.AI cs.CL cs.LG 89%

Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning

Zhiheng Xi, Wenxiang Chen, Boyang Hong, Senjie Jin, Rui Zheng, Wei He, Yiwen Ding, Shichun Liu, Xin Guo, Junzhe Wang, Honglin Guo, Wei Shen, Xiaoran Fan, Yuhao Zhou, Shihan Dou, Xiao Wang, Xinbo Zhang, Peng Sun, Tao Gui, Qi Zhang, Xuanjing Huang

专题命中推理与问题求解：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL、cs.AI、cs.LG；LLM(comments)

Comments Preprint. Codes released: https://github.com/WooooDyy/LLM-Reverse-Curriculum-RL

2604.01413 2026-08-17 cs.CL cs.AI 版本更新 89%

Adaptive Stopping for Multi-Turn LLM Reasoning

多轮LLM推理中的自适应停止

Xiaofan Zhou, Huy Nguyen, Bo Yu, Chenxi Liu, Lu Cheng

机构 * University of Illinois Chicago（伊利诺伊大学芝加哥分校）； Augustana College（奥古斯塔纳学院）； University of Utah（犹他大学）

专题命中推理与问题求解：LLM(title,title_cn)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

AI总结本文提出MiCP框架，通过分配不同误差预算实现多轮推理中的自适应停止，同时保证覆盖率，减少轮次、推理成本和预测集规模。

2608.09432 2026-08-11 cs.CL cs.AI 新提交 89%

ZetaGPT: A Reference Implementation of Positional--Encoding--Free State--Space--Attention Language Models

ZetaGPT：无位置编码的状态空间注意力语言模型的参考实现

Róisín Luo

专题命中推理与问题求解：language model(title,abstract)；RLHF(abstract,abstract_cn)；small language model(abstract)；pretraining(abstract)

AI总结 ZetaGPT是首款无显式位置编码的开源小型语言模型，它将因果状态空间方程与自注意力结合，提供全开源训练流水线，为无位置编码语言模型的研究提供紧凑可复现的参考实现。

2608.01078 2026-08-04 cs.CL cs.AI 新提交 89%

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization

关注自身思维：通过1.58比特量化视角打破推理型大语言模型的后训练量化障碍

Shigeng Wang, Chao Li, Yangyuxuan Kang, Jiawei Fan, Anbang Yao

机构 * Intel Labs China（英特尔中国实验室）

专题命中推理与问题求解：LLM(summary_cn,abstract)；post-training(title,abstract)；分类 cs.CL、cs.AI

AI总结该研究提出ScaleQ-1.58三值后训练量化框架，通过集成AYOT校准方法，提升推理型LLM量化性能，该框架可扩展且泛化性强，仅需少量校准token即可实现优异效果。

Comments This research work was completed and submitted for publication in early May 2026. The project page: https://github.com/IntelChina-AI/BitTern

2604.03472 2026-07-23 cs.CL cs.AI 版本更新 89%

Vocabulary Dropout for Curriculum Diversity in LLM Co-Evolution

词汇丢弃：LLM共同进化中的课程多样性

Jacob Dineen, Aswin RRV, Zhikun Xu, Ben Zhou

机构 * Arizona State University（亚利桑那州立大学）

专题命中推理与问题求解：LLM(title,title_cn)；language model(abstract)；分类 cs.CL、cs.AI

AI总结针对LLM共同进化中问题多样性崩溃的问题，提出词汇丢弃机制，通过在策略训练和课程生成时随机掩码输出logits维持多样性，在数学推理任务上提升求解器性能平均+4.4点。

Comments Accepted to COLM 2026

2607.14165 2026-07-17 cs.SE cs.AI cs.AR cs.LG 新提交 89%

Towards Reliable AI-Assisted Analog Design: Template-Constrained LLM Agents for SAR ADC Generation

迈向可靠的人工智能辅助模拟设计：用于逐次逼近寄存器型模数转换器生成的模板约束大语言模型智能体

Dimple Vijay Kochar, Hae-Seung Lee, Anantha P. Chandrakasan

机构 * Massachusetts Institute of Technology（麻省理工学院）

专题命中推理与问题求解：LLM(title,abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

AI总结研究针对大语言模型在模拟电子设计自动化应用的瓶颈，提出端到端多步骤的ATLAS框架，利用专家知识结合模板约束生成，能生成成功通过仿真验证的SAR ADC，为集成LLMs到可靠模拟设计方法奠定基础。

2606.26104 2026-07-14 cs.CL cs.AI 版本更新 89%

Assert, don't describe: Linguistic features that shift LLM reasoning about animal welfare

断言，而非描述：改变LLM关于动物福利推理的语言特征

Jasmine Brazilek, Harper Dunn

机构 * Compassion Aligned Machine Learning (CaML)（同情对齐机器学习实验室）； Independent researcher（独立研究者）

专题命中推理与问题求解：LLM(title,title_cn)；language model(abstract)；分类 cs.CL、cs.AI

AI总结研究通过词汇匹配的立场对比探针，测量十种语言特征对Llama-3.2-1B模型动物福利推理的影响，发现断言性确定性等七种特征增强支持动物福利，而模糊语言等两种特征削弱立场。

2511.06160 2026-07-02 cs.AI cs.CL cs.CY 版本更新 89%

Evaluating Implicit Biases in LLM Reasoning through Logic Grid Puzzles

通过逻辑网格谜题评估LLM推理中的隐性偏见

Fatima Jahara, Mark Dredze, Sharon Levy

机构 * Rutgers University（罗格斯大学）； Johns Hopkins University（约翰霍普金斯大学）

专题命中推理与问题求解：LLM(title,title_cn)；分类 cs.CL、cs.AI

AI总结提出PRIME框架，利用逻辑网格谜题系统探测LLM在复杂推理中受社会刻板印象的影响，发现模型在解与刻板印象一致时推理更准确。

Comments 26 pages (including appendix)

1. 推理与问题求解 18810 篇

Can Large Language Models Really Improve by Self-critiquing Their Own Plans?

Receive, Reason, and React: Drive as You Say with Large Language Models in Autonomous Vehicles

Evaluating Factual Consistency of Summaries with Large Language Models

Talk like a Graph: Encoding Graphs for Large Language Models

Self-Refined Large Language Model as Automated Reward Function Designer for Deep Reinforcement Learning in Robotics

Neuro Symbolic Reasoning for Planning: Counterexample Guided Inductive Synthesis using Large Language Models and Satisfiability Solving

SayPlan: Grounding Large Language Models using 3D Scene Graphs for Scalable Robot Task Planning

Furthest Reasoning with Plan Assessment: Stable Reasoning Path with Retrieval-Augmented Large Language Models

Inspire the Large Language Model by External Knowledge on BioMedical Named Entity Recognition

Sensecape: Enabling Multilevel Exploration and Sensemaking with Large Language Models

A Comparative Study of Open-Source Large Language Models, GPT-4 and Claude 2: Multiple-Choice Test Taking in Nephrology

Large Language Models can accomplish Business Process Management Tasks

Large Language Models Perform Diagnostic Reasoning

Drive Like a Human: Rethinking Autonomous Driving with Large Language Models

Embodied Task Planning with Large Language Models

Interleaving Pre-Trained Language Models and Large Language Models for Zero-Shot NL2SQL Generation

Understanding the Capabilities of Large Language Models for Automated Planning

Enhancing Knowledge Graph Construction Using Large Language Models

"Get ready for a party": Exploring smarter smart spaces with help from large language models

Modular Cognitive Architecture Emerges in Large Language Models

Offline Learning and Forgetting for Reasoning with Large Language Models

Bootstrapping Object-level Planning with Large Language Models

Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning

Adaptive Stopping for Multi-Turn LLM Reasoning

ZetaGPT: A Reference Implementation of Positional--Encoding--Free State--Space--Attention Language Models

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization

Vocabulary Dropout for Curriculum Diversity in LLM Co-Evolution

Towards Reliable AI-Assisted Analog Design: Template-Constrained LLM Agents for SAR ADC Generation

Assert, don't describe: Linguistic features that shift LLM reasoning about animal welfare

Evaluating Implicit Biases in LLM Reasoning through Logic Grid Puzzles