University of Science and Technology of China（中国科学技术大学）；State Key Lab of Processors, Institute of Computing Technolgy, CAS（中国科学院计算技术研究所处理器国家重点实验室）；Cambricon Technologies（寒武纪科技）；Shanghai Innovation Center for Processor Technologies（上海处理器技术创新中心）；Intelligent Software Research Center, Institute of Software, CAS（中国科学院软件研究所智能软件研究中心）；University of Chinese Academy of Sciences（中国科学院大学）
Research on emergent communication between deep-learning-based agents has received extensive attention due to its inspiration for linguistics and artificial intelligence. However, previous attempts have hovered around emerging communication under perception-oriented environmental settings, that forces agents to describe low-level perceptual features intra image or symbol contexts. In this work, inspired by the classic human reasoning test (namely Raven's Progressive Matrix), we propose the Reasoning Game, a cognition-oriented environment that encourages agents to reason and communicate high-level rules, rather than perceived low-level contexts. Moreover, we propose 1) an unbiased dataset (namely rule-RAVEN) as a benchmark to avoid overfitting, 2) and a two-stage curriculum agent training method as a baseline for more stable convergence in the Reasoning Game, where contexts and semantics are bilaterally drifting. Experimental results show that, in the Reasoning Game, a semantically stable and compositional language emerges to solve reasoning problems. The emerged language helps agents apply the extracted rules to the generalization of unseen context attributes, and to the transfer between different context attributes or even tasks.
Lang2Act: Fine-Grained Visual Reasoning through Self-Emergent Linguistic Toolchains
School of Computer Science and Engineering, Northeastern University, Shenyang, China（东北大学计算机科学与工程学院）；Department of Computer Science and Technology, Tsinghua University, Beijing, China（清华大学计算机科学与技术系）；Alibaba Group, Hangzhou, China（阿里巴巴集团）
DIRCR: Dual-Inference Rule-Contrastive Reasoning for Solving RAVENs
School of Computer Science, University of Nottingham Ningbo China, China（诺丁汉大学宁波校区计算机科学学院）；Nottingham Ningbo China Beacons of Excellence Research and Innovation Institute, China（诺丁汉宁波中国卓越研究与创新研究所）；School of Artificial Intelligence, Shenzhen University, China（深圳大学人工智能学院）
Limit Analysis for Symbolic Multi-step Reasoning Tasks with Information Propagation Rules Based on Transformers
Institute of Natural Sciences, MOE-LSC, Shanghai Jiao Tong University（上海交通大学理论科学研究院）；School of Mathematical Sciences, Shanghai Jiao Tong University（上海交通大学数学科学学院）；School of Mathematics and Statistics, Wuhan University（武汉大学数学学院）
针对 Transformers 多步推理机制不明的问题，提出信息传播规则并通过符号任务进行理论分析，给出 L 层注意力模型单次前向推理步数介于 O(3^{L-1}) 与 O(2^{L-1}) 之间的界限。
An Event Calculus Production Rule System for Reasoning in Dynamic and Uncertain Domains
Institute of Computer Science FO.R.T.H.（希腊研究与技术基金会计算机科学研究所）；Lissi Laboratory Paris-Est Créteil Val-de-Marne University (UPEC)（巴黎东大克雷泰伊马恩河谷大学Lissi实验室）
行为语言已经成为动态领域中推理变化和因果关系的知识表示的一个重要领域。本文介绍了Cerbere，一个生产系统，旨在执行在线因果，时间和认知推理的基础上的事件演算。该框架实现了声明性语义的基础逻辑理论在一个向前链接的基于规则的推理系统，耦合的高表达性的形式主义与基于规则的系统的效率。为了说明它的适用性，我们提出了在该领域的基准问题的建模，以及它在智能空间的挑战性领域的利用。已经开发了一种混合框架，该框架将基于逻辑的推理与概率推理相结合，旨在适应智能空间中的活动识别和监控任务。逻辑程序设计理论与实践（Theory and Practice of Logic Programming，TPLP）
Rule Learning for Knowledge Graph Reasoning under Agnostic Distribution Shift
College of Computer Science and Technology, National University of Defense Technology（计算机科学与技术学院，国防科技大学）；Laboratory for Big Data and Decision, National University of Defense Technology（大数据与决策实验室，国防科技大学）；School of Information, Renmin University of China（信息学院，中国人民大学）；National Key Laboratory of Information Systems Engineering, National University of Defense Technology（信息系统工程国家重点实验室，国防科技大学）；Department of Computer Science and Technology, Tsinghua University（计算机科学与技术系，清华大学）；Department of Intelligent Data Science, College of Computer Science and Technology, National University of Defense Technology（智能数据科学系，计算机科学与技术学院，国防科技大学）
Structuring Reasoning for Complex Rules Beyond Flat Representations
Shenzhen Key Laboratory for High Performance Data Mining, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（深圳高性能数据挖掘重点实验室，深圳先进技术研究院，中国科学院）；University of Chinese Academy of Sciences（中国科学院大学）；School of Biomedical Engineering, UNSW Sydney（悉尼大学生物医学工程学院）；University of Queensland（昆士兰大学）；Alibaba Group（阿里巴巴集团）
Structure-Internalized Rule Language Model for Faithful Knowledge Graph Reasoning
Key Laboratory of Knowledge Engineering with Big Data (Hefei University of Technology)（大数据知识工程重点实验室（合肥工业大学））；School of Computer Science and Information Engineering, Hefei University of Technology（合肥工业大学计算机与信息学院）；Nanjing University of Science and Technology（南京理工大学）
Benchmarking Defeasible Reasoning with Large Language Models -- Initial Experiments and Future Directions
School of Computing and Engineering, University of Huddersfield（哈德斯菲尔德大学计算与工程学院）；Hellenic Mediterranean University（希腊地中海大学）；Leeds Beckett University（利兹贝克特大学）
RNNLogic: Learning Logic Rules for Reasoning on Knowledge Graphs
Université de Montréal（蒙特利尔大学）；Mila - Québec AI Institute（米拉 - 魁北克人工智能研究所）；Canadian Institute for Advanced Research (CIFAR)（加拿大高等研究院）；HEC Montréal（蒙特利尔高等商学院）；Tsinghua University（清华大学）
