We introduce the concept and a default implementation of Guided Reasoning. A multi-agent system is a Guided Reasoning system iff one agent (the guide) primarily interacts with other agents in order to improve reasoning quality. We describe Logikon's default implementation of Guided Reasoning in non-technical terms. This is a living document we'll gradually enrich with more detailed information and examples.
Code: https://github.com/logikon-ai/logikon
Partial Reasoning in Language Models: Search and Refinement Guided by Uncertainty
Advanced Knowledge Center for Immersive Technologies (AKCIT)（沉浸式技术高级知识中心）；Federal University of Goiás, Brazil（巴西戈亚斯联邦大学）；OATML, University of Oxford（牛津大学OATML）
Massachusetts Institute of Technology（麻省理工学院）；Raytheon BBN Technologies（雷神BBN技术公司）；Boston University（波士顿大学）；Princeton University（普林斯顿大学）
One of the challenges facing artificial intelligence research today is designing systems capable of utilizing systematic reasoning to generalize to new tasks. The Abstraction and Reasoning Corpus (ARC) measures such a capability through a set of visual reasoning tasks. In this paper we report incremental progress on ARC and lay the foundations for two approaches to abstraction and reasoning not based in brute-force search. We first apply an existing program synthesis system called DreamCoder to create symbolic abstractions out of tasks solved so far, and show how it enables solving of progress…
Lung-R1: A Knowledge Graph-Guided LLM for Pulmonary Diagnostic Reasoning
School of Computer Science, Chongqing University（重庆大学计算机学院）；AI Research Institution, Mashang Financial Institution（马上金融人工智能研究院）；Department of Information, Third Military Medical University（陆军军医大学信息系）
Think Before You Act: Intention-Guided Reasoning for LLM-Based Location Prediction
The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Shanghai Jiao Tong University（上海交通大学）；The Hong Kong University of Science and Technology（香港科技大学）；Fudan University（复旦大学）；Shanghai Innovation Institute（上海创新研究院）
MiRAGE: Misconception Detection with Retrieval-Guided Multi-Stage Reasoning and Ensemble Fusion
Hanoi University of Science and Technology（河内科学技术大学）；School of Computing, Phenikaa University（现象学大学计算机学院）；Faculty of Interdisciplinary Digital Technology, Phenikaa University（现象学大学跨学科数字技术学院）
Zhejiang University（浙江大学）；AZFT Joint Lab for Knowledge Engine（AZFT知识引擎联合实验室）；Hangzhou Innovation Center, Zhejiang University（浙江大学杭州创新中心）；Alibaba Group（阿里巴巴集团）
Recent years have witnessed the prosperity of legal artificial intelligence with the development of technologies. In this paper, we propose a novel legal application of legal provision prediction (LPP), which aims to predict the related legal provisions of affairs. We formulate this task as a challenging knowledge graph completion problem, which requires not only text understanding but also graph reasoning. To this end, we propose a novel text-guided graph reasoning approach. We collect amounts of real-world legal provision data from the Guangdong government service website and construct a leg…
MARGE: Improving Math Reasoning for LLMs with Guided Exploration
Institute for Interdisciplinary Information Sciences, Tsinghua University, Beijing, China（清华大学交叉信息学院）；Alibaba Group（阿里巴巴集团）；Shanghai Qi Zhi Institute, Shanghai, China（上海启智研究院）
Reasoning on Time-Series for Financial Technical Analysis
National University of Singapore（国立新加坡大学）；Technical University of Munich（慕尼黑技术大学）；Singapore Management University（新加坡管理学院）；City University of Hong Kong（香港城市大学）
Carney Institute for Brain Science（卡尼脑科学研究所）；Brown University（布朗大学）；Centre de Recherche Cerveau et Cognition（脑与认知研究中心）；CNRS（法国国家科学研究中心）；Université de Toulouse（图卢兹大学）；Artificial and Natural Intelligence Toulouse Institute（图卢兹人工智能与自然智能研究所）
Humans continue to outperform modern AI systems in their ability to flexibly parse and understand complex visual scenes. Here, we present a novel module for visual reasoning, the Guided Attention Model for (visual) Reasoning (GAMR), which instantiates an active vision theory -- positing that the brain solves complex visual reasoning problems dynamically -- via sequences of attention shifts to select and route task-relevant visual information into memory. Experiments on an array of visual reasoning tasks and datasets demonstrate GAMR's ability to learn visual routines in a robust and sample-eff…
Shandong University（山东大学）；National University of Singapore（新加坡国立大学）
Logical reasoning is of vital importance to natural language understanding. Previous studies either employ graph-based models to incorporate prior knowledge about logical relations, or introduce symbolic logic into neural models through data augmentation. These methods, however, heavily depend on annotated training data, and thus suffer from over-fitting and poor generalization problems due to the dataset sparsity. To address these two problems, in this paper, we propose MERIt, a MEta-path guided contrastive learning method for logical ReasonIng of text, to perform self-supervised pre-training…
Learning More by Training Less: Uncertainty-Guided Progressive Contraction for Efficient Reasoning Post-Training
National University of Singapore（新加坡国立大学）；Nanjing University（南京大学）；Fudan University（复旦大学）；The University of Sydney（悉尼大学）；The Chinese University of Hong Kong（香港中文大学）；Nanyang Technological University（南洋理工大学）
Evo-PI: Aligning Medical Reasoning via Evolving Principle-Guided Supervision
School of Computer Science, University of Auckland（奥克兰大学计算机科学学院）；Beijing University of Posts and Telecommunications（北京邮电大学）；Renyixun Health Technology Co., Ltd.（仁医讯健康科技有限公司）；National Yang Ming Chiao Tung University（国立阳明交通大学）；Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））
