大模型推理能力

MTMT: Consolidating Multiple Thinking Modes to Form a Thought Tree for Strengthening LLM

Changcheng Li, Xiangyu Wang, Qiuju Chen, Xiren Zhou, Huanhuan Chen

专题命中 复杂问题求解 ：reasoning(abstract)；logical reasoning(abstract)；分类 cs.CL、cs.AI

FinDVer: Explainable Claim Verification over Long and Hybrid-Content Financial Documents

Yilun Zhao, Yitao Long, Yuru Jiang, Chengye Wang, Weiyuan Chen, Hongjun Liu, Yiming Zhang, Xiangru Tang, Chen Zhao, Arman Cohan

专题命中 复杂问题求解 ：reasoning(abstract)；chain-of-thought(abstract)；分类 cs.CL、cs.LG

Comments EMNLP 2024

MetaReflection: Learning Instructions for Language Agents using Past Reflections

Priyanshu Gupta, Shashank Kirtania, Ananya Singha, Sumit Gulwani, Arjun Radhakrishna, Sherry Shi, Gustavo Soares

专题命中 复杂问题求解 ：reasoning(abstract)；logical reasoning(abstract)；分类 cs.CL、cs.AI

Comments We release our experimental code at: https://aka.ms/metareflection-code

E2CL: Exploration-based Error Correction Learning for Embodied Agents

Hanlin Wang, Chak Tou Leong, Jian Wang, Wenjie Li

专题命中 复杂问题求解 ：reasoning(abstract)；self-correction(abstract)；分类 cs.CL、cs.AI

Comments Accepted by EMNLP 2024

HDFlow: Enhancing LLM Complex Problem-Solving with Hybrid Thinking and Dynamic Workflows

Wenlin Yao, Haitao Mi, Dong Yu

专题命中 复杂问题求解 ：reasoning(abstract)；chain-of-thought(abstract)；分类 cs.CL、cs.AI

Comments 27 pages, 5 figures

A Preliminary Study of o1 in Medicine: Are We Closer to an AI Doctor?

Yunfei Xie, Juncheng Wu, Haoqin Tu, Siwei Yang, Bingchen Zhao, Yongshuo Zong, Qiao Jin, Cihang Xie, Yuyin Zhou

专题命中 复杂问题求解 ：reasoning(abstract)；chain-of-thought(abstract)；分类 cs.CL、cs.AI

Comments The first four authors contributed equally, project page available at https://ucsc-vlaa.github.io/o1_medicine/

WavLLM: Towards Robust and Adaptive Speech Large Language Model

Shujie Hu, Long Zhou, Shujie Liu, Sanyuan Chen, Lingwei Meng, Hongkun Hao, Jing Pan, Xunying Liu, Jinyu Li, Sunit Sivasankaran, Linquan Liu, Furu Wei

专题命中 复杂问题求解 ：chain-of-thought(abstract)；CoT(abstract)；分类 cs.CL、cs.AI

Comments accepted by EMNLP2024 findings

Conditional Logical Message Passing Transformer for Complex Query Answering

Chongzhi Zhang, Zhiping Peng, Junhao Zheng, Qianli Ma

专题命中 复杂问题求解 ：reasoning(abstract)；logical reasoning(abstract)；分类 cs.AI、cs.LG

Comments KDD 2024 Research Track

Multi-step Inference over Unstructured Data

Aditya Kalyanpur, Kailash Karthik Saravanakumar, Victor Barres, CJ McFate, Lori Moon, Nati Seifu, Maksim Eremeev, Jose Barrera, Abraham Bautista-Castillo, Eric Brown, David Ferrucci

专题命中 复杂问题求解 ：reasoning(abstract)；planning(abstract)；分类 cs.CL、cs.AI

Large Language Models for Constrained-Based Causal Discovery

Kai-Hendrik Cohrs, Gherardo Varando, Emiliano Diaz, Vasileios Sitokonstantinou, Gustau Camps-Valls

专题命中 复杂问题求解 ：reasoning(abstract)；chain-of-thought(abstract)；分类 cs.CL、cs.AI

Competition-Level Problems are Effective LLM Evaluators

Yiming Huang, Zhenghao Lin, Xiao Liu, Yeyun Gong, Shuai Lu, Fangyu Lei, Yaobo Liang, Yelong Shen, Chen Lin, Nan Duan, Weizhu Chen

专题命中 复杂问题求解 ：reasoning(abstract)；chain-of-thought(abstract)；分类 cs.CL、cs.AI

Comments ACL 2024

Small Language Model Can Self-correct

Haixia Han, Jiaqing Liang, Jie Shi, Qianyu He, Yanghua Xiao

专题命中 复杂问题求解 ：reasoning(abstract)；self-correction(abstract)；分类 cs.CL、cs.AI

Exploring Combinatorial Problem Solving with Large Language Models: A Case Study on the Travelling Salesman Problem Using GPT-3.5 Turbo

Mahmoud Masoud, Ahmed Abdelhay, Mohammed Elhenawy

专题命中 复杂问题求解 ：reasoning(abstract)；CoT(abstract)；分类 cs.CL、cs.AI

Can Language Models Solve Olympiad Programming?

Quan Shi, Michael Tang, Karthik Narasimhan, Shunyu Yao

专题命中 复杂问题求解 ：reasoning(abstract)；chain-of-thought(abstract)；分类 cs.CL、cs.AI

Comments Code and data: https://princeton-nlp.github.io/USACOBench/

All in an Aggregated Image for In-Image Learning

Lei Wang, Wanyu Xu, Zhiqiang Hu, Yihuai Lan, Shan Dong, Hao Wang, Roy Ka-Wei Lee, Ee-Peng Lim

专题命中 复杂问题求解 ：reasoning(abstract)；chain-of-thought(abstract)；分类 cs.CL、cs.AI

Comments Preprint

Can Small Language Models be Good Reasoners for Sequential Recommendation?

Yuling Wang, Changxin Tian, Binbin Hu, Yanhua Yu, Ziqi Liu, Zhiqiang Zhang, Jun Zhou, Liang Pang, Xiao Wang

专题命中 复杂问题求解 ：reasoning(abstract)；CoT(abstract)；分类 cs.CL、cs.LG

Comments Accepted by TheWebConf (WWW) 2024

Transforming Competition into Collaboration: The Revolutionary Role of Multi-Agent Systems and Language Models in Modern Organizations

Carlos Jose Xavier Cruz

专题命中 复杂问题求解 ：reasoning(abstract)；logical reasoning(abstract)；分类 cs.CL、cs.AI

Discriminative Probing and Tuning for Text-to-Image Generation

Leigang Qu, Wenjie Wang, Yongqi Li, Hanwang Zhang, Liqiang Nie, Tat-Seng Chua

专题命中 复杂问题求解 ：planning(abstract)；self-correction(abstract)；分类 cs.CL、cs.AI

Comments CVPR 2024; project page: https://dpt-t2i.github.io/

Can Language Models Solve Graph Problems in Natural Language?

Heng Wang, Shangbin Feng, Tianxing He, Zhaoxuan Tan, Xiaochuang Han, Yulia Tsvetkov

专题命中 复杂问题求解 ：reasoning(abstract)；planning(abstract)；分类 cs.CL、cs.AI

Comments NeurIPS 2023 Spotlight

Large Language Models are Complex Table Parsers

Bowen Zhao, Changkai Ji, Yuejie Zhang, Wen He, Yingwen Wang, Qing Wang, Rui Feng, Xiaobo Zhang

专题命中 复杂问题求解 ：reasoning(abstract)；logical reasoning(abstract)；分类 cs.CL、cs.AI

Comments EMNLP 2023 Main

UPAR: A Kantian-Inspired Prompting Framework for Enhancing Large Language Model Capabilities

Hejia Geng, Boxun Xu, Peng Li

专题命中 复杂问题求解 ：CoT(abstract)；planning(abstract)；分类 cs.CL、cs.AI

Post Hoc Explanations of Language Models Can Improve Language Models

Satyapriya Krishna, Jiaqi Ma, Dylan Slack, Asma Ghandeharioun, Sameer Singh, Himabindu Lakkaraju

专题命中 复杂问题求解 ：reasoning(abstract)；chain-of-thought(abstract)；分类 cs.CL、cs.AI

Large Language Models Are Also Good Prototypical Commonsense Reasoners

Chenin Li, Qianglong Chen, Yin Zhang, Yifei Zhang, Hongxiang Yao

专题命中 复杂问题求解 ：reasoning(abstract)；chain-of-thought(abstract)；分类 cs.CL、cs.AI

LLM Guided Inductive Inference for Solving Compositional Problems

Abhigya Sodani, Lauren Moos, Matthew Mirman

专题命中 复杂问题求解 ：reasoning(abstract)；planning(abstract)；分类 cs.CL、cs.AI

Comments 5 pages, ICML TEACH Workshop

Orca: Progressive Learning from Complex Explanation Traces of GPT-4

Subhabrata Mukherjee, Arindam Mitra, Ganesh Jawahar, Sahaj Agarwal, Hamid Palangi, Ahmed Awadallah

专题命中 复杂问题求解 ：reasoning(abstract)；CoT(abstract)；分类 cs.CL、cs.LG

Quantifying Adaptability in Pre-trained Language Models with 500 Tasks

Belinda Z. Li, Jane Yu, Madian Khabsa, Luke Zettlemoyer, Alon Halevy, Jacob Andreas

专题命中 复杂问题求解 ：reasoning(abstract)；logical reasoning(abstract)；分类 cs.CL、cs.LG

Comments NAACL 2022; 20 pages, 6 figures, 8 tables

Semantics Disentanglement and Composition for Universal Image Coding with Efficiently LLM Reasoning and Generative Diffusion

语义解耦与组合用于具有高效LLM推理和生成扩散的通用图像编码

Jinming Liu, Yuntao Wei, Junyan Lin, Shengyang Zhao, Heming Sun, Zhibo Chen, Wenjun Zeng, Xin Jin

机构 * Shanghai Jiao Tong University（上海交通大学） ； Ningbo Key Laboratory of Spatial Intelligence and Digital Derivative（宁波空间智能与数字衍生关键实验室） ； Ningbo Institute of Digital Twin（宁波数字孪生研究院） ； Eastern Institute of Technology（东部技术研究院） ； University of Science and Technology of China（中国科学技术大学） ； Yokohama National University（Yokohama国立大学） 纠错

专题命中 复杂问题求解 ：reasoning(title)

AI总结 本文提出UniCodec，一种基于语义解耦和组合生成的通用图像编码框架，通过高效LLM推理和生成扩散模型实现人类和机器需求的统一压缩，无需重新训练。

MACAA: Belief-Revision Multi-Agent Reasoning for Code Authorship Verification

MACAA：基于信念修正的多智能体推理用于代码作者身份验证

Jingwei Ye, Zhi Wang, Xin Li, Cong Gao, Chenbin Su, Jieshuai Yang, Jianfei Tang, Ge Chu

专题命中 复杂问题求解 ：reasoning(title)

AI总结 MACAA提出一种无需训练的多智能体框架，通过协调器和四个专家代理分析代码证据，提升代码作者身份验证的准确性和可审计性，实现89.15%的F1分数。

AstroVLM: Expert Multi-agent Collaborative Reasoning for Astronomical Imaging Quality Diagnosis

AstroVLM：专家多智能体协作推理用于天体成像质量诊断

Yaohui Han, Tianshuo Wang, Zixi Zhao, Zhengchun Zhu, Shuo Ren, Yiru Wang, Rongliang Fu, Tinghuan Chen, Tsung-Yi Ho

机构 * The Chinese University of Hong Kong（香港中文大学） ； Central South University（中南大学） ； Huawei Technologies Co., Ltd（华为技术有限公司） ； The Chinese University of Hong Kong, Shenzhen（香港中文大学深圳校区） 纠错

专题命中 复杂问题求解 ：reasoning(title)

AI总结 本文提出AstroVLM，通过多智能体协作推理解决复杂天体成像质量诊断问题，实验表明其在实际任务中优于所有基线模型。

Supporting Reflection and Forward-Looking Reasoning With Data-Driven Questions

通过数据驱动问题支持反思与前瞻性推理

Simon WS Fischer, Hanna Schraffenberger, Serge Thill, Pim Haselager

专题命中 复杂问题求解 ：reasoning(title)

AI总结 本文探讨通过数据驱动问题促进反思与前瞻性推理，提出问题分类法、医疗领域原型及临床反馈、基于大语言模型的问题生成方法及认知参与度测量量表，旨在推动思维工具的设计与评估。

Comments Accepted at CHI2026 Workshop on Tools for Thought, April 16, 2026, in Barcelona, Spain