Learning to Solve Geometry Problems via Simulating Human Dual-Reasoning Process
University of Science and Technology of China(中国科学技术大学);Institute of Artificial Intelligence, Hefei Comprehensive National Science Center(合肥综合性国家科学中心人工智能研究院);iFLYTEK AI Research(讯飞人工智能研究院);State Key Laboratory of Cognitive Intelligence(认知智能国家重点实验室)
几何问题求解(Geometry Problem Solving, GPS)是一项经典且具有挑战性的数学问题,近年来受到广泛关注。它要求求解者全面理解文本和图形,掌握必要的几何知识,并在推理中恰当地加以应用。然而,现有工作遵循神经机器翻译范式,只关注增强编码器能力,忽视了人类几何推理的本质特征。本文受双过程理论启发,提出一种双推理几何求解器(Dual-Reasoning Geometry Solver, DualGeoSolver),用于模拟人类在GPS中的双推理过程。具体而言,我们在DualGeoSolver中构建了两个系统,即知识系统(Knowledge System)和推理系统(Inference System)。知识系统控制隐式推理过程,负责根据推理系统生成的逐步推理目标提供图形信息和几何知识。推理系统执行显式推理过程,明确每一步推理的目标,并应用知识生成用于解决该目标的程序token。两个系统迭代执行上述过程,其表现更符合人类认知。我们在GeoQA和GeoQA+两个基准数据集上进行了大量实验。结果表明,通过显式建模人类推理过程和知识应用,DualGeoSolver在求解准确率和鲁棒性方面均具有优越性。
英文摘要:
Geometry Problem Solving (GPS), which is a classic and challenging math problem, has attracted much attention in recent years. It requires a solver to comprehensively understand both text and diagram, master essential geometry knowledge, and appropriately apply it in reasoning. However, existing works follow a paradigm of neural machine translation and only focus on enhancing the capability of encoders, which neglects the essential characteristics of human geometry reasoning. In this paper, inspired by dual-process theory, we propose a Dual-Reasoning Geometry Solver (DualGeoSolver) to simulate the dual-reasoning process of humans for GPS. Specifically, we construct two systems in DualGeoSolver, namely Knowledge System and Inference System. Knowledge System controls an implicit reasoning process, which is responsible for providing diagram information and geometry knowledge according to a step-wise reasoning goal generated by Inference System. Inference System conducts an explicit reasoning process, which specifies the goal in each reasoning step and applies the knowledge to generate program tokens for resolving it. The two systems carry out the above process iteratively, which behaves more in line with human cognition. We conduct extensive experiments on two benchmark datasets, GeoQA and GeoQA+. The results demonstrate the superiority of DualGeoSolver in both solving accuracy and robustness from explicitly modeling human reasoning process and knowledge application.
DrawSim-PD: Simulating Student Science Drawings to Support NGSS-Aligned Teacher Diagnostic Reasoning
Department of Computer Science, Drexel University(德雷塞尔大学计算机科学系);College of Chemistry, Beijing Normal University(北京师范大学化学学院);Department of Teaching and Learning, Washington State University(华盛顿州立大学教学与学习系)
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)
Optimus-3: Dual-Router Aligned Mixture-of-Experts Agent with Dual-Granularity Reasoning-Aware Policy Optimization
School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen Campus)(计算机科学与技术学院,哈尔滨工业大学(深圳校区));Pengcheng Laboratory(鹏城实验室);School of Information Science and Technology, Harbin Institute of Technology (Shenzhen Campus)(信息科学与技术学院,哈尔滨工业大学(深圳校区));Shenzhen Loop Area Institute(深圳河套学院)
DualVGR: A Dual-Visual Graph Reasoning Unit for Video Question Answering
Nanjing University of Posts and Telecommunications(南京邮电大学);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);University of Chinese Academy of Sciences(中国科学院大学)
AgentCourt: Simulating Court with Adversarial Evolvable Lawyer Agents
Southern University of Science and Technology(南方科技大学);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,深圳先进技术研究所,中国科学院);SIAT-DELI AI and Law Joint Lab(SIAT-DELI人工智能与法律联合实验室);Shenzhen MSU-BIT University(深圳MSU-BIT大学);UNSW Sydney(新南威尔士大学悉尼分校);SUAT(南方科技大学)
DTKG: Dual-Track Knowledge Graph-Verified Reasoning Framework for Multi-Hop QA
School of Computer Science;Engineering, Beihang University, Beijing, China;School of Reliability;Systems Engineering, Beihang University, Beijing, China;State Key Laboratory of Complex \& Critical Software Environment;National Key Laboratory of Reliability;State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences
Beyond Imitation: Learning Key Reasoning Steps from Dual Chain-of-Thoughts in Reasoning Distillation
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络空间安全学院)
VITAL: Visual-Semantic Dual Supervision for Enhanced and Interpretable Latent Reasoning in Medical MLLMs
Zhejiang University(浙江大学);Shanghai AI Laboratory(上海人工智能实验室);Tencent(腾讯);Ningbo Global Innovation Center, Zhejiang University(宁波全球创新中心,浙江大学);Zhejiang Key Laboratory of Digital-Intelligence Service Technology(浙江省数字智能服务技术重点实验室)
Incentivizing Dual Process Thinking for Efficient Large Language Model Reasoning
Gaoling School of Artificial Intelligence, Renmin University of China(中国人民大学人工智能学院);Department of Computer Science, National University of Singapore(新加坡国立大学计算机科学系);Ant Group(蚂蚁集团)
Evolution in Simulation: AI-Agent School with Dual Memory for High-Fidelity Educational Dynamics
Guanghua Law School, Zhejiang University(浙江大学法学院);Faculty of Education, East China Normal University(华东师范大学教育学院);School of Data Science, The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳)数据科学学院);Department of Electrical and Computer Engineering, University of California San Diego(加州大学圣地亚哥分校电子与计算机工程系);Institute of Systems Science, National University of Singapore(新加坡国立大学系统科学研究所)
Relational Temporal Graph Reasoning for Dual-task Dialogue Language Understanding
Australian Artificial Intelligence Institute (AAII)(澳大利亚人工智能研究所);University of Technology Sydney(悉尼科技大学);Centre for Frontier AI Research, A*STAR(新加坡科技研究局前沿人工智能研究中心)
DuetGraph: Coarse-to-Fine Knowledge Graph Reasoning with Dual-Pathway Global-Local Fusion
School of Biomedical Engineering, University of Science and Technology of China(生物医学工程学院,中国科学技术大学);School of Artificial Intelligence and Data Science, USTC(人工智能与数据科学学院,中国科学技术大学);Data Darkness Lab, Suzhou Institute for Advanced Research, USTC(数据黑暗实验室,苏州先进研究院)
Backtracking When It Strays: Mitigating Dual Exposure Biases in LLM Reasoning Distillation
College of Computer Science and Technology, Jilin University(吉林大学计算机科学与技术学院);Key Laboratory of Symbolic Computation and Knowledge Engineering, MoE, Jilin University(吉林大学符号计算与知识工程重点实验室);Tongyi Lab, Alibaba Group(阿里集团通义实验室);College of Computer Science and Technology, Zhejiang University(浙江大学计算机科学与技术学院);School of Artificial Intelligence, Jilin University(吉林大学人工智能学院)
AudioRouter: Data Efficient Audio Understanding via RL based Dual Reasoning
University of California, Los Angeles(加利福尼亚大学洛杉矶分校);The University of Queensland(昆士兰大学);vivo Mobile Communication Co., Ltd.(维沃移动通信有限公司);University of California, Merced(加利福尼亚大学美熹德分校)