语言大模型 / LLM - arXivDaily 专题

2510.16091 2025-10-21 cs.CL cs.AI 92%

Evaluating Prompting Strategies and Large Language Models in Systematic Literature Review Screening: Relevance and Task-Stage Classification

Binglan Han, Anuradha Mathrani, Teo Susnjak

机构 * School of Mathematical and Computational Sciences（数学与计算科学学院）

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

2510.16536 2025-10-21 q-bio.QM cs.AI cs.LG 91%

Few-Label Multimodal Modeling of SNP Variants and ECG Phenotypes Using Large Language Models for Cardiovascular Risk Stratification

Niranjana Arun Menon, Yulong Li, Iqra Farooq, Sara Ahmed, Muhammad Awais, Imran Razzak

机构 * University of New South Wales, Australia（新南威尔士大学，澳大利亚）； University of Surrey, United Kingdom（萨里大学，英国）； Mohamed bin Zayed University of Artificial Intelligence, UAE（穆罕默德·本·扎耶德人工智能大学，阿联酋）

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

2510.16952 2025-10-21 cs.HC cs.CL 90%

Real-Time World Crafting: Generating Structured Game Behaviors from Natural Language with Large Language Models

Austin Drake, Hang Dong

机构 * University of Exeter Department of Computer Science（埃克塞特大学计算机科学系）

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

Comments 16 pages, 11 figures (including appendix). To be presented at the 5th Wordplay @ EMNLP workshop (2025)

2505.06493 2025-10-21 cs.CR cs.AI 90%

System Prompt Poisoning: Persistent Attacks on Large Language Models Beyond User Injection

Zongze Li, Jiawei Guo, Haipeng Cai

机构 * University at Buffalo（布法罗大学）

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

2410.17333 2025-10-21 cs.AI cs.CL cs.CY 90%

Whose Journey Matters? Investigating Identity Biases in Large Language Models (LLMs) for Travel Planning Assistance

Ruiping Ren, Yingwei, Xu, Xing Yao, Shu Cole, Haining Wang

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、cs.AI

2510.16476 2025-10-21 cs.AI 89%

NP-Engine: Empowering Optimization Reasoning in Large Language Models with Verifiable Synthetic NP Problems

Xiaozhe Li, Xinyu Fang, Shengyuan Ding, Linyang Li, Haodong Duan, Qingwen Liu, Kai Chen

机构 * Tongji University（同济大学）； Shanghai AI Lab（上海人工智能实验室）； Zhejiang University（浙江大学）； Fudan University（复旦大学）

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

2510.15974 2025-10-21 cs.AI 89%

Limits of Emergent Reasoning of Large Language Models in Agentic Frameworks for Deterministic Games

Chris Su, Harrison Li, Matheus Marques, George Flint, Kevin Zhu, Sunishchal Dev

机构 * Algoverse AI Research（Algoverse AI研究）

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

2510.09211 2025-10-21 cs.CL cs.AI 89%

DICE: Structured Reasoning in LLMs through SLM-Guided Chain-of-Thought Correction

Yiqi Li, Yusheng Liao, Zhe Chen, Yanfeng Wang, Yu Wang

机构 * Shanghai Jiao Tong University（上海交通大学）； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）

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

Comments This paper was accepted to the EMNLP 2025 main conference

2510.17164 2025-10-21 cs.SE 89%

Software Testing with Large Language Models: An Interview Study with Practitioners

Maria Deolinda Santana, Cleyton Magalhaes, Ronnie de Souza Santos

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

2303.06689 2025-10-21 cs.SE 89%

Self-planning Code Generation with Large Language Models

Xue Jiang, Yihong Dong, Lecheng Wang, Zheng Fang, Qiwei Shang, Ge Li, Zhi Jin, Wenpin Jiao

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

Comments Accepted by TOSEM

2506.00783 2025-10-21 cs.CL cs.AI 88%

KG-TRACES: Enhancing Large Language Models with Knowledge Graph-constrained Trajectory Reasoning and Attribution Supervision

Rong Wu, Pinlong Cai, Jianbiao Mei, Licheng Wen, Tao Hu, Xuemeng Yang, Daocheng Fu, Botian Shi

机构 * Zhejiang University（浙江大学）； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）； University of Science and Technology of China（中国科学技术大学）； Fudan University（复旦大学）

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

Comments 24 pages, 13 figures

2507.00432 2025-10-21 cs.AI cs.CL 88%

Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning

Maggie Huan, Yuetai Li, Tuney Zheng, Xiaoyu Xu, Seungone Kim, Minxin Du, Radha Poovendran, Graham Neubig, Xiang Yue

机构 * Carnegie Mellon University（卡内基梅隆大学）； University of Pennsylvania（宾夕法尼亚大学）； University of Washington（华盛顿大学）； M-A-P ； The Hong Kong Polytechnic University（香港理工大学）

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

2508.02298 2025-10-21 cs.LG cs.AI cs.CL 87%

CAPO: Towards Enhancing LLM Reasoning through Generative Credit Assignment

Guofu Xie, Yunsheng Shi, Hongtao Tian, Ting Yao, Xiao Zhang

机构 * Gaoling School of Artificial Intelligence, Renmin University of China（人工智能学院，中国人民大学）； Tencent Inc（腾讯公司）

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

Comments Work in progress

2510.16924 2025-10-21 cs.CL 86%

Does Visual Grounding Enhance the Understanding of Embodied Knowledge in Large Language Models?

Zhihui Yang, Yupei Wang, Kaijie Mo, Zhe Zhao, Renfen Hu

机构 * Beijing Normal University（北京师范大学）； Tencent AI Lab（腾讯AI实验室）

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

Comments Accepted to EMNLP 2025 (Findings). This version corrects a redundant sentence in the Results section that appeared in the camera-ready version

2510.15979 2025-10-21 cs.LG cs.AI 86%

Cog-Rethinker: Hierarchical Metacognitive Reinforcement Learning for LLM Reasoning

Zexu Sun, Yongcheng Zeng, Erxue Min, Heyang Gao, Bokai Ji, Xu Chen

机构 * Baidu Inc.（百度公司）； Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）； Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学人工智能学院）

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

Comments 22 Pages, 8 figures, 4 tables

2506.10343 2025-10-21 cs.CL cs.AI 86%

Code Execution as Grounded Supervision for LLM Reasoning

Dongwon Jung, Wenxuan Zhou, Muhao Chen

机构 * University of California, Davis（加州大学戴维斯分校）； University of Southern California（南加州大学）

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

Comments EMNLP 2025

2510.17576 2025-10-21 cs.RO cs.AI cs.HC cs.MA 85%

Intent-Driven LLM Ensemble Planning for Flexible Multi-Robot Disassembly: Demonstration on EV Batteries

Cansu Erdogan, Cesar Alan Contreras, Alireza Rastegarpanah, Manolis Chiou, Rustam Stolkin

机构 * 1Extreme Robotics Lab, School of Metallurgy \& Materials, University of Birmingham, Birmingham, UK ； 2Department of Applied Artificial Intelligence ； Robotics, School of Computer Science, Aston University, Birmingham, UK ； 3School of Electronic Engineering ； Computer Science, Queen Mary University of London, London, UK

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

Comments This work is funded by the project called "Research and Development of a Highly Automated and Safe Streamlined Process for Increasing Lithium-ion Battery Repurposing and Recycling" (REBELION) under Grant 101104241, and partially supported by the Ministry of National Education, Republic of Turkey. Submitted to Frontiers for Review

2510.17002 2025-10-21 cs.LG 85%

EEschematic: Multimodal-LLM Based AI Agent for Schematic Generation of Analog Circuit

Chang Liu, Danial Chitnis

机构 * School of Engineering The University of Edinburgh Edinburgh, UK（工程学院苏格兰爱丁堡大学）

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

2510.16933 2025-10-21 cs.DC cs.AI 85%

Tutoring LLM into a Better CUDA Optimizer

Matyáš Brabec, Jiří Klepl, Michal Töpfer, Martin Kruliš

机构 * Charles University（查理大学）

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

Comments This preprint has not undergone peer review or any post-submission improvements or corrections. The Version of Record of this contribution is published in Euro-Par 2025: Parallel Processing, Part II, and is available online at https://doi.org/10.1007/978-3-031-99857-7_18

Journal ref Euro-Par 2025: Parallel Processing. Euro-Par 2025. Lecture Notes in Computer Science, vol 15901. Springer, Cham

2510.16080 2025-10-21 q-bio.QM cs.AI 85%

TriAgent: Automated Biomarker Discovery with Deep Research Grounding for Triage in Acute Care by LLM-Based Multi-Agent Collaboration

Kerem Delikoyun, Qianyu Chen, Win Sen Kuan, John Tshon Yit Soong, Matthew Edward Cove, Oliver Hayden

机构 * Technical University of Munich（慕尼黑技术大学）； National University of Singapore（新加坡国立大学）； National University Hospital（新加坡国立大学医院）

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

2510.06917 2025-10-21 cs.CL eess.AS 85%

SHANKS: Simultaneous Hearing and Thinking for Spoken Language Models

Cheng-Han Chiang, Xiaofei Wang, Linjie Li, Chung-Ching Lin, Kevin Lin, Shujie Liu, Zhendong Wang, Zhengyuan Yang, Hung-yi Lee, Lijuan Wang

机构 * National Taiwan University（台湾大学）； Microsoft（微软）

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

Comments Work in progress

2510.16767 2025-10-21 cs.RO 85%

T3 Planner: A Self-Correcting LLM Framework for Robotic Motion Planning with Temporal Logic

Jia Li, Guoxiang Zhao

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

2504.01005 2025-10-21 cs.CL cs.AI cs.LG 85%

When To Solve, When To Verify: Compute-Optimal Problem Solving and Generative Verification for LLM Reasoning

Nishad Singhi, Hritik Bansal, Arian Hosseini, Aditya Grover, Kai-Wei Chang, Marcus Rohrbach, Anna Rohrbach

机构 * TU Darmstadt（图恩-达姆施塔特技术大学）； UCLA（加州大学洛杉矶分校）； Google Deepmind（谷歌DeepMind）； Mila（蒙特利尔人工智能研究院）

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

Comments COLM 2025

2510.16366 2025-10-21 cs.CY 85%

Integrating LLM and Diffusion-Based Agents for Social Simulation

Xinyi Li, Zhiqiang Guo, Qinglang Guo, Hao Jin, Weizhi Ma, Min Zhang

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

Comments 10 pages, 3 figures, 4 tables

2510.12997 2025-10-21 cs.LG cs.AI cs.CL 85%

Max It or Miss It: Benchmarking LLM On Solving Extremal Problems

Binxin Gao, Jingjun Han

机构 * University of Maryland（马里兰大学）； Fudan University（复旦大学）

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

Comments Our benchmark dataset is available at https://huggingface.co/datasets/binxingao/extrem-bench

2508.12535 2025-10-21 cs.CL cs.AI cs.LG 85%

CorrSteer: Generation-Time LLM Steering via Correlated Sparse Autoencoder Features

Seonglae Cho, Zekun Wu, Adriano Koshiyama

机构 * University College London（伦敦大学学院）

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

Comments 42 pages, 9 tables

2505.08750 2025-10-21 cs.CL 84%

HCR-Reasoner: Synergizing Large Language Models and Theory for Human-like Causal Reasoning

Yanxi Zhang, Xin Cong, Zhong Zhang, Xiao Liu, Dongyan Zhao, Yesai Wu

机构 * Center for Data Science, AAIS, Peking University（数据科学中心，AAIS，北京大学）； Wangxuan Institute of Computer Technology, Peking University（王轩计算机技术研究所，北京大学）； Tsinghua University（清华大学）； State Key Laboratory of General Artificial Intelligence（通用人工智能国家重点实验室）

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

2510.13850 2025-10-21 cs.CL cs.AI 84%

Revisiting the UID Hypothesis in LLM Reasoning Traces

Minju Gwak, Guijin Son, Jaehyung Kim

机构 * Department of Artificial Intelligence（人工智能系）； Yonsei University（延世大学）； OneLine AI

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

Journal ref The 5th Workshop on Mathematical Reasoning and AI, NeurIPS 2025

2510.10252 2025-10-21 cs.CL cs.AI 84%

Audit-of-Understanding: Posterior-Constrained Inference for Mathematical Reasoning in Language Models

Samir Abdaljalil, Erchin Serpedin, Khalid Qaraqe, Hasan Kurban

机构 * Texas A&M University（德克萨斯大学）； Hamad Bin Khalifa University（哈马德·本·哈利法大学）

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

2508.19131 2025-10-21 cs.RO cs.AI cs.CV 83%

ZeST: an LLM-based Zero-Shot Traversability Navigation for Unknown Environments

Shreya Gummadi, Mateus V. Gasparino, Gianluca Capezzuto, Marcelo Becker, Girish Chowdhary

机构 * Field Robotics Engineering and Science Hub (FRESH), Illinois Autonomous Farm, University of Illinois at Urbana-Champaign (UIUC), IL（伊利诺伊大学厄巴纳-香槟分校）； Mobile Robotics Group, São Carlos School of Engineering, University of São Paulo (EESC-USP), São Carlos, SP, Brazil（圣保罗大学）

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

1. 推理与问题求解 75 篇

Evaluating Prompting Strategies and Large Language Models in Systematic Literature Review Screening: Relevance and Task-Stage Classification

Few-Label Multimodal Modeling of SNP Variants and ECG Phenotypes Using Large Language Models for Cardiovascular Risk Stratification

Real-Time World Crafting: Generating Structured Game Behaviors from Natural Language with Large Language Models

System Prompt Poisoning: Persistent Attacks on Large Language Models Beyond User Injection

Whose Journey Matters? Investigating Identity Biases in Large Language Models (LLMs) for Travel Planning Assistance

NP-Engine: Empowering Optimization Reasoning in Large Language Models with Verifiable Synthetic NP Problems

Limits of Emergent Reasoning of Large Language Models in Agentic Frameworks for Deterministic Games

DICE: Structured Reasoning in LLMs through SLM-Guided Chain-of-Thought Correction

Software Testing with Large Language Models: An Interview Study with Practitioners

Self-planning Code Generation with Large Language Models

KG-TRACES: Enhancing Large Language Models with Knowledge Graph-constrained Trajectory Reasoning and Attribution Supervision

Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning

CAPO: Towards Enhancing LLM Reasoning through Generative Credit Assignment

Does Visual Grounding Enhance the Understanding of Embodied Knowledge in Large Language Models?

Cog-Rethinker: Hierarchical Metacognitive Reinforcement Learning for LLM Reasoning

Code Execution as Grounded Supervision for LLM Reasoning

Intent-Driven LLM Ensemble Planning for Flexible Multi-Robot Disassembly: Demonstration on EV Batteries

EEschematic: Multimodal-LLM Based AI Agent for Schematic Generation of Analog Circuit

Tutoring LLM into a Better CUDA Optimizer

TriAgent: Automated Biomarker Discovery with Deep Research Grounding for Triage in Acute Care by LLM-Based Multi-Agent Collaboration

SHANKS: Simultaneous Hearing and Thinking for Spoken Language Models

T3 Planner: A Self-Correcting LLM Framework for Robotic Motion Planning with Temporal Logic

When To Solve, When To Verify: Compute-Optimal Problem Solving and Generative Verification for LLM Reasoning

Integrating LLM and Diffusion-Based Agents for Social Simulation

Max It or Miss It: Benchmarking LLM On Solving Extremal Problems

CorrSteer: Generation-Time LLM Steering via Correlated Sparse Autoencoder Features

HCR-Reasoner: Synergizing Large Language Models and Theory for Human-like Causal Reasoning

Revisiting the UID Hypothesis in LLM Reasoning Traces

Audit-of-Understanding: Posterior-Constrained Inference for Mathematical Reasoning in Language Models

ZeST: an LLM-based Zero-Shot Traversability Navigation for Unknown Environments