语言大模型 / LLM

Inductive reasoning in humans and large language models

Simon J. Han, Keith Ransom, Andrew Perfors, Charles Kemp

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 61 pages, 5 figures

Emergent Analogical Reasoning in Large Language Models

Taylor Webb, Keith J. Holyoak, Hongjing Lu

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 Published at Nature Human Behaviour (2023) https://doi.org/10.1038/s41562-023-01659-w

ARB: Advanced Reasoning Benchmark for Large Language Models

Tomohiro Sawada, Daniel Paleka, Alexander Havrilla, Pranav Tadepalli, Paula Vidas, Alexander Kranias, John J. Nay, Kshitij Gupta, Aran Komatsuzaki

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.LG

Comments Submitted to NeurIPS Datasets and Benchmarks Track

Dynamic Large Language Models on Blockchains

Yuanhao Gong

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

Garbage in, garbage out: Zero-shot detection of crime using Large Language Models

Anj Simmons, Rajesh Vasa

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 5 pages, 4 figures, 1 table

Negated Complementary Commonsense using Large Language Models

Navid Rezaei, Marek Z. Reformat

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 Appeared in Natural Language Reasoning and Structured Explanations Workshop (NLRSE) - ACL 2023

Towards Benchmarking and Improving the Temporal Reasoning Capability of Large Language Models

Qingyu Tan, Hwee Tou Ng, Lidong Bing

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 ACL 2023

Evaluating Large Language Models with NeuBAROCO: Syllogistic Reasoning Ability and Human-like Biases

Risako Ando, Takanobu Morishita, Hirohiko Abe, Koji Mineshima, Mitsuhiro Okada

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 To appear in Proceedings of the 4th Natural Logic Meets Machine Learning Workshop (NALOMA IV)

Large Language Models are In-Context Semantic Reasoners rather than Symbolic Reasoners

Xiaojuan Tang, Zilong Zheng, Jiaqi Li, Fanxu Meng, Song-Chun Zhu, Yitao Liang, Muhan Zhang

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

Distilling Script Knowledge from Large Language Models for Constrained Language Planning

Siyu Yuan, Jiangjie Chen, Ziquan Fu, Xuyang Ge, Soham Shah, Charles Robert Jankowski, Yanghua Xiao, Deqing Yang

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 Accepted to ACL 2023

Towards Reasoning in Large Language Models: A Survey

Jie Huang, Kevin Chen-Chuan Chang

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 ACL 2023 Findings, 15 pages

Making Large Language Models Better Reasoners with Step-Aware Verifier

Yifei Li, Zeqi Lin, Shizhuo Zhang, Qiang Fu, Bei Chen, Jian-Guang Lou, Weizhu Chen

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

Think Outside the Code: Brainstorming Boosts Large Language Models in Code Generation

Xin-Ye Li, Jiang-Tian Xue, Zheng Xie, Ming Li

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 13 pages, 5 figures

Algebra Error Classification with Large Language Models

Hunter McNichols, Mengxue Zhang, Andrew Lan

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

Measuring Progress on Scalable Oversight for Large Language Models

Samuel R. Bowman, Jeeyoon Hyun, Ethan Perez, Edwin Chen, Craig Pettit, Scott Heiner, Kamilė Lukošiūtė, Amanda Askell, Andy Jones, Anna Chen, Anna Goldie, Azalia Mirhoseini, Cameron McKinnon, Christopher Olah, Daniela Amodei, Dario Amodei, Dawn Drain, Dustin Li, Eli Tran-Johnson, Jackson Kernion, Jamie Kerr, Jared Mueller, Jeffrey Ladish, Joshua Landau, Kamal Ndousse, Liane Lovitt, Nelson Elhage, Nicholas Schiefer, Nicholas Joseph, Noemí Mercado, Nova DasSarma, Robin Larson, Sam McCandlish, Sandipan Kundu, Scott Johnston, Shauna Kravec, Sheer El Showk, Stanislav Fort, Timothy Telleen-Lawton, Tom Brown, Tom Henighan, Tristan Hume, Yuntao Bai, Zac Hatfield-Dodds, Ben Mann, Jared Kaplan

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 v2 fixes a few typos from v1

Faithful Reasoning Using Large Language Models

Antonia Creswell, Murray Shanahan

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

Autoformalization with Large Language Models

Yuhuai Wu, Albert Q. Jiang, Wenda Li, Markus N. Rabe, Charles Staats, Mateja Jamnik, Christian Szegedy

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

Comments 44 pages

ManuSearch: Democratizing Deep Search in Large Language Models with a Transparent and Open Multi-Agent Framework

Lisheng Huang, Yichen Liu, Jinhao Jiang, Rongxiang Zhang, Jiahao Yan, Junyi Li, Wayne Xin Zhao

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

Comments LLM, Complex Search Benchmark

StructGPT: A General Framework for Large Language Model to Reason over Structured Data

Jinhao Jiang, Kun Zhou, Zican Dong, Keming Ye, Wayne Xin Zhao, Ji-Rong Wen

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

Comments LLM+Structured Data(KG, Table, DB); EMNLP-23 Camera-ready

Large Language Models as Corporate Lobbyists

John J. Nay

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

Comments Our open-source code available here: https://github.com/JohnNay/llm-lobbyist

OmicSync: Reliability-Aware Spatial Multi-Omics Clustering with Evidence-Constrained LLM Reasoning

OmicSync：结合证据约束大语言模型推理的可靠性感知空间多组学聚类

Rabeya Tus Sadia, Qiang Ye, Qiang Cheng

机构 * University of Kentucky（肯塔基大学） 纠错

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

AI总结 OmicSync是结合证据约束LLM推理的可靠性感知空间多组学聚类框架，集成KAN-GCN骨干等功能，在多组学基准测试中表现优异，OmicSync-R进一步提升了人乳腺癌的聚类性能。

Bounding Hallucinations: Merlin-Arthur Protocols for Mutual-Information Bounds in Language Models

界限幻觉：通过Merlin-Arthur协议为RAG系统提供信息论保证

Björn Deiseroth, Max Henning Höth, Kristian Kersting, Letitia Parcalabescu

机构 * Aleph Alpha Research（Aleph Alpha研究机构） ； Lab1141（Lab1141实验室） 纠错

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

AI总结 通过Merlin-Arthur协议训练RAG系统，提升模型对证据的依赖性，减少幻觉并增强信息论指标。

Comments 45 pages, 30 figures

LLM-Grounded Dynamic Task Planning with Hierarchical Temporal Logic for Human-Aware Multi-Robot Handover

基于分层时序逻辑的LLM引导动态任务规划用于人感知多机器人协作

Shuyuan Hu, Tao Lin, Kai Ye, Tianwei Zhang

机构 * The Shenzhen Institute of Artificial Intelligence and Robotics for Society（深圳人工智能与机器人社会研究院） ； Harbin Institute of Technology（哈尔滨工业大学） ； The Chinese University of Hong Kong-Shenzhen（香港中文大学（深圳）） ； Tsinghua Shenzhen International Graduate School（清华大学深圳国际 Graduate School） 纠错

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

AI总结 本文提出基于分层时序逻辑的神经符号框架，实现动态任务规划以提升多机器人协作的效率和鲁棒性。

Comments Accepted by IROS 2026

Simple Policy Gradients for Reasoning with Diffusion Language Models

为扩散语言模型进行推理的简单策略梯度

Anthony Zhan

机构 * Stanford University（斯坦福大学） 纠错

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

AI总结 本文提出 AGRPO 算法，通过优化 dLLM 的去噪步骤提升推理性能，实现多个任务上的显著增益。

Comments 19 pages. ICML 2026

On the risk of coding before testing: An empirical study on LLM-based test generation workflow

关于测试前编码风险：基于大语言模型的测试生成工作流程的实证研究

Michael Konstantinou, Florian Tambon, Mike Papadakis

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 研究大语言模型在软件工程工作流程中生成代码和测试套件时，生成的代码是否会使后续测试产生偏差，通过实证研究错误传播现象，评估其在多种编程任务和工作流程中的影响。

From Pixels to Concepts: Growing Rich 3D Semantic Scene Graph Forests utilizing Foundation Models

从像素到概念：利用基础模型构建丰富的3D语义场景图森林

David Oberacker, Meike Deitersen, Niklas Spielbauer, Tristan Schnell, Georg Heppner, Arne Roennau

机构 * FZI Research Center for Information Technology（FZI信息技术研究中心） ； Machine Intelligence and Robotics Lab (MaiRo), Karlsruhe Institute for Technology (KIT)（卡尔斯鲁厄理工学院机器智能与机器人实验室） 纠错

专题命中 推理与问题求解 ：LLM(summary_cn,abstract)；foundation model(title,abstract)

AI总结 提出利用基础模型构建具有开放语义关系的3D场景图森林，通过VLM和LLM推理抽象概念节点与关系，提升机器人场景理解与任务执行能力。

Comments To be published in the Proceedings of the IEEE/RSJ International Conference on Intelligent Robots & Systems (IEEE IROS 2026)

Beyond representational alignment with brain-guided language models for robust reasoning

超越表征对齐：基于大脑引导的语言模型实现稳健推理

Mingqing Xiao, Kai Du, Zhouchen Lin

机构 * State Key Lab of General AI, School of Intelligence Science and Technology, Peking University（北京大学通用人工智能国家重点实验室、智能科学与技术学院） ； Department of Psychological and Cognitive Sciences, Tsinghua University（清华大学心理与认知科学系） ； Microsoft Research Asia（微软亚洲研究院） 纠错

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

AI总结 研究通过fMRI信号增强大型语言模型推理能力，提出脑引导框架，在10个模型上实现最高13%的准确率提升。

ProcessThinker: Enhancing Multi-modal Large Language Models Reasoning via Rollout-based Process Reward

ProcessThinker: 通过基于展开的过程奖励增强多模态大语言模型推理

Jingpei Wu, Xiao Han, Weixiang Shen, Boer Zhang, Zifeng Ding, Volker Tresp

机构 * LMU Munich（慕尼黑大学） ； Harvard University（哈佛大学） ； University of Cambridge（剑桥大学） ； Mina AI ； Konrad Zuse School of Excellence in Reliable AI (relAI)（康拉德·楚泽可靠人工智能卓越学校（relAI）） 纠错

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

AI总结 提出ProcessThinker，一种无需显式过程奖励模型的后训练方法，通过步骤标记格式和基于展开的过程奖励，为多步推理提供密集的步骤级奖励，提升多模态推理一致性。

Comments Accepted at ICLR 2026 Workshop on Logical Reasoning of Large Language Models. 7 pages, 1 figure

Beyond Semantic Dominance: Cognitive Affective Reasoning and Empathetic Response Alignment in Audio Language Models

超越语义主导：音频语言模型中的认知情感推理与共情响应对齐

Zhixian Zhao, Shuiyuan Wang, Wenjie Tian, Jingbin Hu, Ziyu Zhang, Lei Xie

机构 * Northwestern Polytechnical University（西北工业大学） 纠错

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

AI总结 提出CogAudio-LLM框架，通过构建LIME-440K数据集实现声学-语义解耦，设计EIPS思维链机制进行心理推理，并采用DR-SAPO优化策略平衡逻辑严谨性与共情质量，解决音频语言模型中的语义主导和情感认知不足问题。

Comments Accepted by Interspeech2026

Self-Consistency from Only Two Samples: CoT-PoT Ensembling for Efficient LLM Reasoning

仅需两个样本的自一致性：CoT-PoT集成实现高效LLM推理

Raman Saparkhan, Majd Hawasly, Md Rizwan Parvez, Mohammad Raza

机构 * Carnegie Mellon University Qatar（卡内基梅隆大学（卡塔尔）） ； Qatar Computing Research Institute（卡塔尔计算研究院） 纠错

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、cs.LG

AI总结 提出一种混合集成方法，结合思维链与程序化推理两种模式，通过仅需两个样本即可实现自一致性，将采样量减少9.3倍，并在78.6%的任务上达到最优。

Comments 9 pages, 3 figures; accepted to Findings of ACL 2026