Efficiently tackling combinatorial reasoning problems, particularly the notorious NP-hard tasks, remains a significant challenge for AI research. Recent efforts have sought to enhance planning by incorporating hierarchical high-level search strategies, known as subgoal methods. While promising, their performance against traditional low-level planners is inconsistent, raising questions about their application contexts. In this study, we conduct an in-depth exploration of subgoal-planning methods for combinatorial reasoning. We identify the attributes pivotal for leveraging the advantages of high-level search: hard-to-learn value functions, complex action spaces, presence of dead ends in the environment, or using data collected from diverse experts. We propose a consistent evaluation methodology to achieve meaningful comparisons between methods and reevaluate the state-of-the-art algorithms.
GraphThought: Graph Combinatorial Optimization with Thought Generation
East China Normal University（东华大学）；Tongji University（同济大学）；Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University（上海智能自主系统研究院，同济大学）；Key Laboratory of Mathematics and Engineering Applications, MoE, East China Normal University（数学与工程应用重点实验室，教育部，东华大学）
The ability to reason with multiple hierarchical structures is an attractive and desirable property of sequential inductive biases for natural language processing. Do the state-of-the-art Transformers and LSTM architectures implicitly encode for these biases? To answer this, we propose ORCHARD, a diagnostic dataset for systematically evaluating hierarchical reasoning in state-of-the-art neural sequence models. While there have been prior evaluation frameworks such as ListOps or Logical Inference, our work presents a novel and more natural setting where our models learn to reason with multiple …
Yale University（耶鲁大学）；The Chinese University of Hong Kong（香港中文大学）；Northeastern University（东北大学）；Penn State University（宾夕法尼亚州立大学）
Numerical reasoning over hybrid data containing both textual and tabular content (e.g., financial reports) has recently attracted much attention in the NLP community. However, existing question answering (QA) benchmarks over hybrid data only include a single flat table in each document and thus lack examples of multi-step numerical reasoning across multiple hierarchical tables. To facilitate data analytical progress, we construct a new large-scale benchmark, MultiHiertt, with QA pairs over Multi Hierarchical Tabular and Textual data. MultiHiertt is built from a wealth of financial reports and …
UC Berkeley（加州大学伯克利分校）；Meta AI Research（Meta人工智能研究院）；Princeton University（普林斯顿大学）；UT Austin（德克萨斯大学奥斯汀分校）
Object rearrangement is a challenge for embodied agents because solving these tasks requires generalizing across a combinatorially large set of configurations of entities and their locations. Worse, the representations of these entities are unknown and must be inferred from sensory percepts. We present a hierarchical abstraction approach to uncover these underlying entities and achieve combinatorial generalization from unstructured visual inputs. By constructing a factorized transition graph over clusters of entity representations inferred from pixels, we show how to learn a correspondence bet…
Combinatorial Reasoning: Selecting Reasons in Generative AI Pipelines via Combinatorial Optimization
Icosa Computing Inc.（伊科萨计算公司）；NASA ARC（美国国家航空航天局艾姆斯研究中心）；USRA Research Institute for Advanced Computer Science (RIACS)（美国大学空间研究协会高级计算机科学研究所）；Hewlett Packard Labs（惠普实验室）；DataStax（DataStax公司）
本文提出完全自动化的组合推理框架 CR，将 LLM 流水线采样的理由建模为 QUBO 问题并选择子集构建思维链提示，实验表明组合优化可增强生成式 AI 推理。
Hierarchical Reasoning Models: Perspectives and Misconceptions
Center for Brains, Minds, and Machines（大脑、心智与机器中心）；K. Lisa Yang Integrative Computational Neuroscience (ICoN) Center（K. Lisa Yang整合计算神经科学中心）；McGovern Institute for Brain Research（麦戈文脑科学研究所）；Department of Brain and Cognitive Sciences（脑科学与认知科学系）
Reasoning about the behaviour of physical objects is a key capability of agents operating in physical worlds. Humans are very experienced in physical reasoning while it remains a major challenge for AI. To facilitate research addressing this problem, several benchmarks have been proposed recently. However, these benchmarks do not enable us to measure an agent's granular physical reasoning capabilities when solving a complex reasoning task. In this paper, we propose a new benchmark for physical reasoning that allows us to test individual physical reasoning capabilities. Inspired by how humans a…
Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））
We address the task of automatically scoring the competency of candidates based on textual features, from the automatic speech recognition (ASR) transcriptions in the asynchronous video job interview (AVI). The key challenge is how to construct the dependency relation between questions and answers, and conduct the semantic level interaction for each question-answer (QA) pair. However, most of the recent studies in AVI focus on how to represent questions and answers better, but ignore the dependency information and interaction between them, which is critical for QA evaluation. In this work, we …
HiPO: Hierarchical Preference Optimization for Adaptive Reasoning in LLMs
Vellore Institute of Technology（维洛雷理工学院）；University of Massachusetts Amherst（马萨诸塞大学阿姆赫斯特分校）；Northwestern University（西北大学）；Yale University（耶鲁大学）；Algoverse AI Research（Algoverse AI研究）
Cog-Rethinker: Hierarchical Metacognitive Reinforcement Learning for LLM Reasoning
Baidu Inc.（百度公司）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学人工智能学院）
Dynamical Systems Theory Behind a Hierarchical Reasoning Model
Department of Radiophysics, University of Nizhny Novgorod（尼日尼诺夫戈罗德大学无线电物理系）；Huawei Nizhny Novgorod Research Center（华为尼日尼诺夫戈罗德研究中心）；Skolkovo Institute of Science and Technology（斯克洛科夫科学与技术研究院）
CHARMS: A Cognitive Hierarchical Agent for Reasoning and Motion Stylization in Autonomous Driving
School of Mechanical and Electronic Engineering, Wuhan University of Technology（武汉理工大学机械与电子工程学院）；Intelligent Transportation Systems Research Center, Wuhan University of Technology（武汉理工大学智能交通系统研究所）；Department of Data and Systems Engineering, The University of Hong Kong（香港大学数据与系统工程系）；School of Computer Science and Artificial Intelligence, Wuhan University of Technology（武汉理工大学计算机科学与人工智能学院）；School of Mechanical Engineering, Southeast University（东南大学机械工程学院）
Dental-TriageBench: Benchmarking Multimodal Reasoning for Hierarchical Dental Triage
School of Computing and Data Science, The University of Hong Kong（香港大学计算与数据科学学院）；Faculty of Dentistry, The University of Hong Kong（香港大学牙科学院）；The Prince Philip Dental Hospital（菲利普王子牙科医院）；Li Ka Shing Faculty of Medicine, The University of Hong Kong（香港大学利滋医学学院）；The Hong Kong University of Science and Technology（香港科学与技术大学）
University of Toronto（多伦多大学）；Vector Institute（向量研究所）；Pontificia Universidad Católica de Chile（智利天主教大学）；Centro Nacional de Inteligencia Artificial（国家人工智能中心）；Schwartz Reisman Institute（施瓦茨·赖斯曼研究所）
Deep reinforcement learning has shown promise in discrete domains requiring complex reasoning, including games such as Chess, Go, and Hanabi. However, this type of reasoning is less often observed in long-horizon, continuous domains with high-dimensional observations, where instead RL research has predominantly focused on problems with simple high-level structure (e.g. opening a drawer or moving a robot as fast as possible). Inspired by combinatorially hard optimization problems, we propose a set of robotics tasks which admit many distinct solutions at the high-level, but require reasoning abo…
