大模型推理能力

Scientific Hypothesis Generation and Validation: Methods, Datasets, and Future Directions

Adithya Kulkarni, Fatimah Alotaibi, Xinyue Zeng, Longfeng Wu, Tong Zeng, Barry Menglong Yao, Minqian Liu, Shuaicheng Zhang, Lifu Huang, Dawei Zhou

机构 * Virginia Tech（弗吉尼亚理工大学） ； University of California, Davis（加州大学戴维斯分校） 纠错

专题命中 逻辑推理 ：reasoning(abstract)；分类 cs.CL、cs.LG

NSFlow: An End-to-End FPGA Framework with Scalable Dataflow Architecture for Neuro-Symbolic AI

Hanchen Yang, Zishen Wan, Ritik Raj, Joongun Park, Ziwei Li, Ananda Samajdar, Arijit Raychowdhury, Tushar Krishna

机构 * Georgia Institute of Technology（佐治亚理工学院） ； IBM Research（IBM研究院） 纠错

专题命中 逻辑推理 ：reasoning(abstract)；分类 cs.AI、cs.LG

Comments 2025 IEEE/ACM Design Automation Conference (DAC)

Multi-agent Auto-Bidding with Latent Graph Diffusion Models

Dom Huh, Prasant Mohapatra

机构 * Department of Computer Science University of California, Davis（计算机科学系加州大学戴维斯分校） 纠错

专题命中 逻辑推理 ：planning(abstract)；分类 cs.AI、cs.LG

Large Language Model Can Be a Foundation for Hidden Rationale-Based Retrieval

Luo Ji, Feixiang Guo, Teng Chen, Qingqing Gu, Xiaoyu Wang, Ningyuan Xi, Yihong Wang, Peng Yu, Yue Zhao, Hongyang Lei, Zhonglin Jiang, Yong Chen

专题命中 逻辑推理 ：reasoning(abstract)；分类 cs.CL、cs.LG

Comments 10 pages, 3 figures, ECIR 2025

Geo-OLM: Enabling Sustainable Earth Observation Studies with Cost-Efficient Open Language Models & State-Driven Workflows

Dimitrios Stamoulis, Diana Marculescu

专题命中 逻辑推理 ：reasoning(abstract)；分类 cs.AI、cs.LG

Differentially Private Steering for Large Language Model Alignment

Anmol Goel, Yaxi Hu, Iryna Gurevych, Amartya Sanyal

专题命中 逻辑推理 ：reasoning(abstract)；分类 cs.CL、cs.LG

Comments ICLR 2025 Camera Ready; Code: https://github.com/UKPLab/iclr2025-psa

Logic-RAG: Augmenting Large Multimodal Models with Visual-Spatial Knowledge for Road Scene Understanding

Imran Kabir, Md Alimoor Reza, Syed Billah

专题命中 逻辑推理 ：reasoning(abstract)；分类 cs.CL、cs.LG

Cross-Examiner: Evaluating Consistency of Large Language Model-Generated Explanations

Danielle Villa, Maria Chang, Keerthiram Murugesan, Rosario Uceda-Sosa, Karthikeyan Natesan Ramamurthy

专题命中 逻辑推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments 21 pages, 4 figures

Provably Safe Neural Network Controllers via Differential Dynamic Logic

Samuel Teuber, Stefan Mitsch, André Platzer

专题命中 逻辑推理 ：reasoning(abstract)；分类 cs.AI、cs.LG

Comments 39 pages (main paper has 10 pages), 13 figures; Accepted at the Thirty-Eighth Annual Conference on Neural Information Processing Systems (NeurIPS 2024)

Journal ref in Advances in Neural Information Processing Systems, 2024, pp. 1586-1624

Neuro-Symbolic Learning for Galois Groups: Unveiling Probabilistic Trends in Polynomials

Elira Shaska, Tony Shaska

专题命中 逻辑推理 ：reasoning(abstract)；分类 cs.AI、cs.LG

Show, Don't Tell: Evaluating Large Language Models Beyond Textual Understanding with ChildPlay

Gonçalo Hora de Carvalho, Oscar Knap, Robert Pollice

专题命中 逻辑推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

Code-Vision: Evaluating Multimodal LLMs Logic Understanding and Code Generation Capabilities

Hanbin Wang, Xiaoxuan Zhou, Zhipeng Xu, Keyuan Cheng, Yuxin Zuo, Kai Tian, Jingwei Song, Junting Lu, Wenhui Hu, Xueyang Liu

专题命中 逻辑推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments 15 pages

Unlocking the Potential of Generative AI through Neuro-Symbolic Architectures: Benefits and Limitations

Oualid Bougzime, Samir Jabbar, Christophe Cruz, Frédéric Demoly

专题命中 逻辑推理 ：reasoning(abstract)；分类 cs.AI、cs.LG

Comments 54 pages, 7 figures

Stochastic Optimization of Inventory at Large-scale Supply Chains

Zhaoyang Larry Jin, Mehdi Maasoumy, Yimin Liu, Zeshi Zheng, Zizhuo Ren

专题命中 逻辑推理 ：planning(abstract)；分类 cs.AI、cs.LG

Neuro-Conceptual Artificial Intelligence: Integrating OPM with Deep Learning to Enhance Question Answering Quality

Xin Kang, Veronika Shteingardt, Yuhan Wang, Dov Dori

专题命中 逻辑推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments 15 pages, 3 figures,

Journal ref International Conference on Computational Linguistics (COLING), 1-15, Jan. 2025

Neuro-Symbolic Contrastive Learning for Cross-domain Inference

Mingyue Liu, Ryo Ueda, Zhen Wan, Katsumi Inoue, Chris G. Willcocks

专题命中 逻辑推理 ：reasoning(abstract)；分类 cs.CL、cs.LG

Comments In Proceedings ICLP 2024, arXiv:2502.08453

Journal ref EPTCS 416, 2025, pp. 78-94

From Few to Many: Self-Improving Many-Shot Reasoners Through Iterative Optimization and Generation

Xingchen Wan, Han Zhou, Ruoxi Sun, Hootan Nakhost, Ke Jiang, Sercan Ö. Arık

专题命中 逻辑推理 ：reasoning(abstract)；分类 cs.AI、cs.LG

Comments Expanded version of the ICLR 2025 paper

Few-shot Policy (de)composition in Conversational Question Answering

Kyle Erwin, Guy Axelrod, Maria Chang, Achille Fokoue, Maxwell Crouse, Soham Dan, Tian Gao, Rosario Uceda-Sosa, Ndivhuwo Makondo, Naweed Khan, Alexander Gray

专题命中 逻辑推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

Logic Augmented Generation

Aldo Gangemi, Andrea Giovanni Nuzzolese

专题命中 逻辑推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments 10 pages, 2 figures

ActPC-Geom: Towards Scalable Online Neural-Symbolic Learning via Accelerating Active Predictive Coding with Information Geometry & Diverse Cognitive Mechanisms

Ben Goertzel

专题命中 逻辑推理 ：reasoning(abstract)；分类 cs.AI、cs.LG

A Metasemantic-Metapragmatic Framework for Taxonomizing Multimodal Communicative Alignment

Eugene Yu Ji

专题命中 逻辑推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments 34 pages, 1 figure, 3 tables. Draft presented at 2023 ZJU Logic and AI Summit EAI Workshop

Exploiting Hybrid Policy in Reinforcement Learning for Interpretable Temporal Logic Manipulation

Hao Zhang, Hao Wang, Xiucai Huang, Wenrui Chen, Zhen Kan

专题命中 逻辑推理 ：planning(abstract)；分类 cs.AI、cs.LG

Comments Accepted by IROS 2024. Code:https://github.com/Charlie0257/HyTL

Multi-Agent Path Finding in Continuous Spaces with Projected Diffusion Models

Jinhao Liang, Jacob K. Christopher, Sven Koenig, Ferdinando Fioretto

专题命中 逻辑推理 ：planning(abstract)；分类 cs.AI、cs.LG

Large Language Models can Learn Rules

Zhaocheng Zhu, Yuan Xue, Xinyun Chen, Denny Zhou, Jian Tang, Dale Schuurmans, Hanjun Dai

专题命中 逻辑推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

From Unstructured Data to In-Context Learning: Exploring What Tasks Can Be Learned and When

Kevin Christian Wibisono, Yixin Wang

专题命中 逻辑推理 ：reasoning(abstract)；分类 cs.CL、cs.LG

Comments 39 pages

Language Models can Infer Action Semantics for Symbolic Planners from Environment Feedback

Wang Zhu, Ishika Singh, Robin Jia, Jesse Thomason

专题命中 逻辑推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

Infant Agent: A Tool-Integrated, Logic-Driven Agent with Cost-Effective API Usage

Bin Lei, Yuchen Li, Yiming Zeng, Tao Ren, Yi Luo, Tianyu Shi, Zitian Gao, Zeyu Hu, Weitai Kang, Qiuwu Chen

专题命中 逻辑推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

Can Large Language Models Act as Symbolic Reasoners?

Rob Sullivan, Nelly Elsayed

专题命中 逻辑推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments 18 pages, currently under review

Neural Concept Binder

Wolfgang Stammer, Antonia Wüst, David Steinmann, Kristian Kersting

专题命中 逻辑推理 ：reasoning(abstract)；分类 cs.AI、cs.LG

CELI: Controller-Embedded Language Model Interactions

Jan-Samuel Wagner, Dave DeCaprio, Abishek Chiffon Muthu Raja, Jonathan M. Holman, Lauren K. Brady, Sky C. Cheung, Hosein Barzekar, Eric Yang, Mark Anthony Martinez, David Soong, Sriram Sridhar, Han Si, Brandon W. Higgs, Hisham Hamadeh, Scott Ogden

专题命中 逻辑推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments 26 pages, 2 figures