Puzzle

Ask about this topic

Momentum

7 papers in the last four weeks, with none the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 42

All topics
CardsList

  1. Solving Multi-Agent Sokoban via LaCAM

    Sep 30, 2026Keisuke OkumuraMulti-Agent Path FindingMulti-Agent Planning

    National Institute of Advanced Industrial Science and Technology (AIST), Japan

  2. The Row Normalization Puzzle in Muon

    Sep 30, 2026Jiayu Zhang, Tianyi LinMuonNormalization

    Department of Industrial Engineering and Operations Research Columbia University

  3. LongPuzzleBench: Evaluating GUI Agents on Long-Horizon Visual Puzzles

    Sep 28, 2026Bingo Zhang, Haochuan Lu, Zongjie Li +3PuzzleGraphical User Interface Agents

    Vera Praxis · Tencent · The Hong Kong University of Science and Technology +2

  4. Codoku: Renewable Program-Reasoning Challenges for Frontier Coding Agents

    Sep 28, 2026Cong Li, Hao Sun, Zenan Li +1Coding AgentsPuzzle

    ETH Zurich

  5. FINGR: Learning Dexterous Hand Control for Real-World Rubik's Cube Solving

    Sep 27, 2026Yutong Liang, Quanquan Peng, Matthew Kim +1Dexterous ManipulationPuzzle

    University of California San Diego

  6. Clueing up LLMs with Tool-Augmented Deductive Reasoning

    Sep 16, 2026Rebecca Ansell, Autumn Toney-WailsDeductionStrategic Reasoning

    Georgetown University · Syntheos, Corp · UNU-MERIT

  7. TDDN: Text-aligned Diffused DINO Network for Puzzle Understanding

    Sep 7, 2026Harsha Patnala, Debopriyo Banerjee, Ayush Sunil Munot +1Fine-Grained PerceptionSelf-Supervised Vision Transformers

    Eightfold AI · Inception42 · Indian Institute of Technology Kharagpur

  8. MathShikkha: A Controlled Study of Answer-Only and Chain-of-Thought Supervision for Bangla Mathematical Reasoning in Small Language Models

    Aug 9, 2026Rahma Simin Ali, Jawad HossainBanglaProcess-Level Supervision

    Independent Researcher · University at Albany

  9. Transformers Struggle to Use Their Emergent World Models: Revisiting the Tower of Hanoi, and the Illusion of Thinking

    Aug 7, 2026Devin Pereira, Willem ZuidemaLLM Reasoning StrategiesPuzzle

    1Artificial Intelligence Program, University of Amsterdam · ELLIS Unit Amsterdam · Institute for Logic Language and Computation, University of Amsterdam

  10. JigShape: Evaluating Visual-Geometric Reasoning in VLMs through Jigsaw Puzzles

    Jul 30, 2026Shawn Li, Wei Yang, Jike Zhong +11PuzzleShapes Constraint Language

    University of Southern California · National University of Singapore · Adobe Research +3

  11. SymStep: Symbolic Step Verification for Logical Reasoning

    Jul 25, 2026Aida Usmanova, Rui Gao, Dilshod Azizov +2Constraint SatisfactionSymbol-

    Leuphana University of Lüneburg · Mohamed bin Zayed University of Artificial Intelligence

  12. Chess_db: A framework for working with large chess game datasets

    Jul 23, 2026Nicos Angelopoulos, Jan WielemakerChessLarge Databases

    University College & Imperial College, London UK · University College & Imperial College London, UK · SWI-Prolog solutions +1

  13. Anatomy of a Sound Neural Reasoner: One-Shot Amortization, First-Pass Poisoning, and Search Inertness in Clue-Rich Completion

    Jul 22, 2026Aleksey KomissarovPuzzleNeural Solvers

    Neapolis University, Pafos, Cyprus

  14. Graph Coloring Approach to Solving Sudoku with Oscillatory Neural Networks

    Jul 17, 2026Filip Sabo, Aida Todri-SanialNeural SolversNeural Network

    NanoComputing Research Lab, Electrical Engineering Department Eindhoven University of Technology Eindhoven, the Netherlands

  15. CayleyR: Solving the TopSpin puzzle via cycle intersection

    Jul 14, 2026Yuri BaramykovPermutationAcyclic Graphs

  16. MaxSAT-Based Feedback for Guiding Vision-Language Models in Sudoku

    Jul 14, 2026Pedro Orvalho, Guillem Alenyà, Felip ManyàSatisfiabilityRecent Vision-Language Models

    Artificial Intelligence Research Institute (IIIA), Consejo Superior de Investigaciones Científicas (CSIC), Barcelona, Catalonia, Spain · Institut de Robòtica i Informàtica Industrial (IRI-CSIC-UPC), Barcelona, Spain

  17. Comparative Analysis of GAT and BERT for Human-Like Playtesting

    Jul 13, 2026Kleio Fragkedaki, Theodoros Panagiotakopoulos, Matteo Biasielli +1PuzzleComparison

    AI Center of Excellence King Stockholm, Sweden

  18. ClassicLogic: A Knowledge-Driven Benchmark of Classic Puzzle Games for Evaluating Compositional Generalization

    Jul 6, 2026Mahnoor Shahid, Hannes RothePuzzleReasoning Benchmark

    Universität Duisburg-Essen Germany

  19. A Verifiable Search Is Not a Learnable Chain-of-Thought

    Jun 20, 2026Harsh PatelChain-of-Thought ReasoningReasoning Skills

    Independent Researcher

  20. History of the Muddy Children Puzzle

    Jun 8, 2026Hans van DitmarschPuzzleHistory

    CNRS, France · IIT Kanpur, India

  21. PhyRoGen: Synthetic Generation of Physical Robot Manipulation Puzzles Using Procedural Content Generation

    Jun 4, 2026Lennart Julian Droß, Andreas Orthey, Marc ToussaintMotion GenerationRobotic Manipulation

    Technical University of Berlin, Germany · Robotics Institute Germany

  22. Tangram: Unlocking Non-Uniform KV Cache Compression for Efficient Multi-turn LLM Serving

    Jun 4, 2026Hyungmin Kim, Minsoo Kim, Hongseok Kim +1Large Language Model ServingKey-Value Cache Compression

  23. DeliChess: A Multi-party Dialogue Dataset for Deliberation in Chess Puzzle Solving

    Jun 3, 2026Xiaochen Zhu, Georgi Karadzhov, Tom Stafford +1ChessDeliberation

    University of Cambridge · University of Sheffield

  24. Learning Empirically Admissible Neural Heuristics for Combinatorial Search

    Jun 3, 2026Siddharth SahayHeuristicsNeural Combinatorial Optimization

    Independent Researcher, India

  25. DiBS: Diffusion-Informed Branch Selection

    Jun 2, 2026Bo Liu, Yuan Xie, Yuan Gao +4Puzzle

    1Jilin University · 2The Chinese University of Hong Kong, Shenzhen · 3Southwest University +3

  26. Learning Permutation from Structure Without Supervision

    May 25, 2026Ran Eisenberg, Ofir LindenbaumPermutationEquivariant Learning

    Faculty of Engineering, Bar-Ilan University, Ramat Gan, Israel. · Faculty of Engineering, Bar-Ilan

  27. Tetris: Tile-level Sampling for Efficient and High-Fidelity Video Object Tracking

    May 25, 2026Chanwut Kittivorawong, Alena Chao, Charlie Si +1Multi-Object TrackingVideo Dataset

    U. of California, Berkeley Berkeley, California, USA

  28. Puzzled By ChatGPT? No more! A Jigsaw Puzzle to Promote AI Literacy and Awareness

    May 19, 2026Francesca Padovani, Malvina NissimArtificial Intelligence LiteracyGenerative Artificial Intelligence

    Center for Language and Cognition (CLCG)

  29. The Missing GAP: From Solving Square Jigsaw Puzzles to Handling Real World Archaeological Fragments

    May 12, 2026Ofir Itzhak Shahar, Gur Elkin, Ohad Ben-ShaharPuzzleComputer Vision

    Stein Faculty of Computer and Information Science Ben-Gurion University of the Negev, Israel

  30. Do Vision-Language-Models show human-like logical problem-solving capability in point and click puzzle games?

    May 11, 2026Maximilian Triebel, Marco Menner, Dominik HelfensteinPuzzleWeak Visual Grounding

    Institute of Artificial Intelligence, University of Stuttgart, Stuttgart, Germany.

  31. Do multimodal models imagine electric sheep?

    May 10, 2026Santhosh Kumar Ramakrishnan, Carl Vondrick, Raja Giryes +2Visual ReasoningMultimodal Model

    Apple

  32. TriP: A Triangle Puzzle Approach to Robust Translation Averaging

    May 8, 2026Zhekai Fan, Wanze Li, Jinxin Wang +1Structure-From-MotionJourney

    UC Davis · University of Chicago

  33. Neuromorphic Control for 3D Navigation in Minecraft Using Genetic Algorithms

    May 4, 2026Eric ZiporPath PlanningMaze Task

    Department of Electrical and Computer Engineering George Mason University, Fairfax, VA, USA

  34. Multi-Perspective Transformers in ARC-AGI-2 Challenge

    May 1, 2026Caleb Talley, Vedant Tibrewal, Seun Adekunle +3PuzzleModel Fine-Tuning

  35. IceBreaker for Conversational Agents: Breaking the First-Message Barrier with Personalized Starters

    Apr 20, 2026Hongwei Zheng, Weiqi Wu, Zhengjia Wang +6Conversational Artificial IntelligenceArtificial Intelligence Assistants

    ByteDance

  36. Recurrent Reasoning on Symbolic Puzzles with Sequence Models

    Apr 19, 2026Gowrav Mannem, Chowdhury Marzia Mahjabin, Jason Chen +2PuzzleReasoning Benchmark

    Algoverse AI Research · Cornell University

  37. Placing Puzzle Pieces Where They Matter: A Question Augmentation Framework for Reinforcement Learning

    Apr 17, 2026Yangyi Fang, Jiaye Lin, Xiaoliang Fu +2PuzzleQuestion

    Tsinghua University · Fudan University · Peking University

  38. CAPTCHA Solving for Native GUI Agents: Automated Reasoning-Action Data Generation and Self-Corrective Training

    Mar 23, 2026Yuxi Chen, Haoyu Zhai, Chenkai Wang +4CaptchaGraphical User Interface Agents

    University of Illinois Urbana-Champaign.

  39. Evaluating Implicit Biases in LLM Reasoning through Logic Grid Puzzles

    Nov 8, 2025Fatima Jahara, Mark Dredze, Sharon LevyLarge Language Model BiasLLM Reasoning Strategies

    Rutgers University · Johns Hopkins University

  40. PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference

    Nov 6, 2025Yushu Zhao, Zheng Wang, Minjia ZhangMixture-Of-Expert InferenceMixture-Of-Experts

    1Tsinghua University · †Work done while intern at UIUC. · University of Illinois Urbana-Champaign.

  41. MultiZebraLogic: A Multilingual Logical Reasoning Benchmark

    Nov 5, 2025Sofie Helene Bruun, Dan Saattrup SmartReasoning BenchmarkPuzzle

    The Alexandra Institute Rued Langgaards Vej 7, 5D, 2300 Copenhagen S, Denmark

  42. Communication and Verification in LLM Agents towards Collaboration under Information Asymmetry

    Oct 29, 2025Run Peng, Ziqiao Ma, Amy Pang +5Large Language Model AgentsCollaboration

    University of Michigan · UNC, Chapel Hill · Georgia Tech +2