Constraint Satisfaction

Follow this topic Ask about this topic

Momentum

8 papers in the last four weeks, up 100% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 66

All topics

Blackboard Intelligence Can Surpass Autoregressive on Globally Constrained Problems
Sep 30, 2026Woosang Jeon, Jaeyeon Kim, Sham Kakade +6Constraint Satisfaction Next-Token Prediction
Seoul National University · Harvard University · University of Central Florida
TACIT: Optimization Models that Learn from Their Mistakes
Sep 29, 2026Maxime Bouscary, Marco Molinaro, Sirui Li +3Optimization Modeling Constraint Satisfaction
Massachusetts Institute of Technology, Cambridge, MA, USA · Microsoft Research, Redmond, WA, USA
ConCAD: Constraint-Aware Image-to-CAD Generation with Dual-Granularity Rewards
Sep 28, 2026Chenxi Zhai, Xi Cheng, Hang Cheng +5Image-To-Cad Generation Constraint Satisfaction
Tsinghua University, Shenzhen International Graduate School
Org-Agent: Beyond Personal Assistants Towards Organizational Agents
Sep 28, 2026Luyao Zhuang, Yujing Zhang, Zijin Hong +2Multi-Agent Orchestration Cp-Agent
The Department of Computing, The Hong Kong Polytechnic University, Hong Kong SAR
Ontology-Mediated Neurosymbolic Constraint Acquisition from Multiple Stakeholders
Sep 24, 2026Stefan Bischof, Juliana Kainz, Danilo ValerioNeuro-Symbolic Framework Ontology
Siemens AG Österreich, Vienna, Austria
Learning Symbolic Constraint Representations from Examples: A Neuro-Symbolic Approach
Sep 14, 2026Nassim Belmecheri, Arnaud Gotlieb, Nadjib Lazaar +1Neuro-Symbolic Framework Constraint Satisfaction
Simula Research Laboratory, Oslo, Norway · Microsoft, Norway · LISN, CNRS, Paris-Saclay University, France
Fast Constraint Extraction for Corrective Control under STL Specifications via Logical Dependency Tracking
Sep 8, 2026Antoine Besset, Joris Tillet, Chuchu Fan +1Signal Temporal Logic Reachability
u2IS, ENSTA, Institut Polytechnique de Paris, France · Univ. Grenoble Alpes, CNRS, Grenoble INP, VERIMAG, France · REALM, AeroAstro, Massachusetts Institute of Technology, Cambridge, USA
Proactive Context-Forecasted Safety Constraints for Nonstationary Reinforcement Learning
Sep 8, 2026Tim TomashevskiySafety Constraints Non-Stationarity
Department of Computing and Software McMaster University Hamilton, Ontario, Canada
Beyond Surface Forms: Symbolic Edits as a Test for Logical Reasoning with LLMs
Aug 31, 2026Ramya Keerthy Thatikonda, Wray Buntine, Ehsan ShareghiLLM Reasoning Strategies Reasoning Skills
Department of Data Science & AI, Monash University · ∃Department of Computer Science, University College London
Capability Sheaves for Compositional Agent-Harness Repair: Controlled Quotients and a Real-Repository Stress Test
Aug 13, 2026Saveliy BatruinRepair Automated Program Repair
Independent researcher
Large Language Models Can Follow Instructions, But Not Many at Once: Phase Transitions in Compositional Constraint Satisfaction
Aug 12, 2026Mariya I. VasilevaLarge Language Models Fail Constraint Satisfaction
Work done while at Meta Superintelligence Labs.
Enhanced Filtering Algorithms for the Euclidean Traveling Salesperson Problem and its variants in Constraint Logic Programming
Aug 11, 2026Alessandro Bertagnon, Marco GavanelliSalesman Problem Constraint Satisfaction
Department of Environmental and Prevention Sciences, University of Ferrara, Italy · Department of Engineering, University of Ferrara, Italy
Improving Constraint Models with LLM Agents
Aug 8, 2026Florentina Voboril, Stefan SzeiderConstraint Satisfaction Structural Constraints
Algorithms and Complexity Group TU Wien, Vienna, Austria
KNOWPLAN: Knowledge-Driven AI Agents for Smart Degree Pathway Planning
Aug 6, 2026Shuheng Cao, Weijia Zhang, Jiaqi Wu +4Scholar Information Database Curriculum
University of California, San Diego · Yale University · University of North Carolina, Chapel Hill
Constraint-First Reasoning: A Training-Free Protocol for Exploiting Answer-Space Constraints in Mathematical Problem Solving
Aug 5, 2026Hongbo Ma, Bangji Yang, Yunqian Selina Cheng +3Constraint Satisfaction Structural Constraints
1Tsinghua University · University of Illinois Urbana-Champaign
OmniRouting: A Semantic-Coupled Multimodal Benchmark for Constraint-Aware Spatial Reasoning in PCB Routing
Aug 5, 2026Taiting Lu, Kaiyuan Lin, Ziwei Dong +18Electronic Design Automation Large Language Model Routing
1Pennsylvania State University · 2Independent Researcher · 3Shanghai Jiao Tong University +3
LLM-Guided Evolutionary Search for Constraint Model Reformulation to Improve Solver Efficiency
Jul 30, 2026Kostis Michailidis, Dimos Tsouros, Nguyen Dang +1Evolutionary Search Automated Heuristic Design
1DTAI, KU Leuven, Belgium · University of Western Macedonia, Greece · University of St Andrews, United Kingdom
SymStep: Symbolic Step Verification for Logical Reasoning
Jul 25, 2026Aida Usmanova, Rui Gao, Dilshod Azizov +2Constraint Satisfaction Symbol-
Leuphana University of Lüneburg · Mohamed bin Zayed University of Artificial Intelligence
Global Difference Constraint Propagation for Constraint Programming
Jul 22, 2026Lucas Kletzander, Jip J. Dekker, Andreas Schutt +1Constraint Satisfaction Satisfiability
1Databases and Artificial Intelligence Group, TU Wien, Karlsplatz 13, Wien, 1040, Austria. · Department of Data Science and Artificial Intelligence, Monash University, Clayton, 3168, Victoria, Australia. · 3ARC Training Centre in Optimisation Technologies, Integrated Methodologies, and Applications (OPTIMA), Melbourne, Victoria, Australia. +1
Constrained Path Reasoning: Measuring When Committed Stages Earn Their Cost
Jul 19, 2026Honglin LiReasoning Paths Constraint Satisfaction
ShanghaiTech University
Constraint-Anchored Reasoning Traces
Jul 18, 2026Zehua Cheng, Wei Dai, Jiahao SunLLM Reasoning Strategies Multimodal Large Language Models
Department of Computer Science University of Oxford United Kingdom · FLock.io United Kingdom
SEER: Supervised Learning to Control Energetic Reasoning
Jul 17, 2026Sascha Van Cauwelaert, Michele Lombardi, Pierre SchausConstraint Satisfaction Recursive Reasoner
Universit´e Catholique de Louvain · Universit`a di Bologna
Hard Rules, Soft Preferences: Bridging Reasoning, Learning, and Optimization for Personalized Packing Checklist Generation
Jul 17, 2026Himel Dev, Madhusudan Basak, Tanmoy Sen +2Journey Constraint Satisfaction
Tech LLC · University of Massachusetts Amherst · University of Virginia
Canopy: A Heterograph Foundation Model for Metabolic Engineering
Jul 7, 2026Jake Bowden, Laurence Legon, Satnam SuraeMetabolic Biomedical Knowledge Graph
Twig Bio, London, United Kingdom
GPU-Parallel Linearization Error Bounds for Real-Time Robust Optimal Control of Nonlinear and Neural Network Dynamics
Jul 1, 2026Jeffrey Fang, Keyi Shen, Anutam Srinivasan +1Nonlinear Dynamics Neural Dynamics
Geometry-Aware MCTS for Extremal Problems in Combinatorial Geometry
Jun 24, 2026Luoning Zhang, Xu Zhuang, Tianhao Wang +1Monte Carlo Tree Search Geometric Constraints
Department of Mathematics, University of California, Irvine
AIChilles: Automatically Uncovering Hidden Weaknesses in AI-Evolved Systems
Jun 14, 2026Yajie Zhou, Ao Li, Ashwin Silla +2Self-Evolving Agents Self-Evolution
University of Maryland, College Park · Carnegie Mellon University
Multi-ResNets for Subspace Preconditioning in Constrained Optimization
Jun 4, 2026Merve Karakas, Christopher J. Williams, Emmanuel O. Balogun +3Constrained Optimization Residual Networks
UCLA · University of Oxford · Sunrun† +1
Beyond Objective Equivalence: Constraint Injection for LLM-Based Optimization Modeling on Vehicle Routing Problems
Jun 3, 2026Xizi Luo, Changhong He, Dongdong Geng +2Optimization Modeling Vehicle Routing Problem
Beihang University, Beijing, China · Baidu Inc., Beijing, China
Constrained Multi-Objective Reinforcement Learning with Max-Min Criterion
May 29, 2026Giseung Park, Hyunyoung Nam, Woohyeon Byeon +2Multi-Objective Reinforcement Learning Constraint Satisfaction
Robotics Institute, University of Toronto, 55 St George St, Toronto, Canada. · School of Electical Engineering, KAIST, Daejeon 34141, Republic of Korea. · Faculty of Engineering, Bar-Ilan University, Ramat Gan 52900, Israel.
Constrained Flow Optimization via Sequential Fine Tuning for Molecular Design
May 28, 2026Sven Gutjahr, Riccardo De Santi, Luca Schaufelberger +2Molecular Design Generative Flow Networks
Department of Computer Science, ETH Zurich · ETH AI Center · NCCR Catalysis, Switzerland +1
PhyDrawGen: Physically Grounded Diagram Generation from Natural Language
May 28, 2026Nafiul Haque, Syed Nazmus Sakib, Shifat E ArmanDiagrams Visual Generation
Department of Robotics and Mechatronics Engineering, University of Dhaka
Simulation-Informed Diffusion for Decentralized Multi-robot Motion Planning
May 26, 2026Jinhao Liang, Sven Koenig, Ferdinando FiorettoMulti-Robot Motion Planning Collision-Free Trajectories
University of Virginia · University of California, Irvine
Blocked Gibbs meets Diffusion Transformers: Unsupervised Learning for Constraint Optimization
May 24, 2026Yudong W. Xu, Wenhao Li, Xiaoyu Wang +2Constraint Satisfaction Diffusion Transformers
University of Toronto · Vector Institute
Hypothesis Generation and Inductive Inference in Children and Language Models
May 23, 2026Jeffrey Qin, Wasu Top Piriyakulkij, Zhuangfei Gao +4Induction LLM Reasoning Strategies
Computer Science University of Waterloo · Department of Computer Science Cornell University · Department of Computer Science Dalhousie University +1
CAffNet: Hard Constraint-Affine Neural Networks
May 23, 2026Yang Zhao, Jungeun Lee, Jeong hwan Jeon +1Neural Network Constraint Satisfaction
Department of Mechanical and Industrial Engineering, Northeastern University, Boston, MA 02115 USA · Department of Electrical Engineering, Ulsan National Institute of Science and Technology, Ulsan 44919, Republic of Korea
Streamlined Constraint Reasoning via CNN Pattern Recognition on Enumerated Solutions
May 19, 2026Patrick SpracklenConstraint Satisfaction Convolutional Neural Networks
Transforming Constraint Programs to Input for Local Search
May 19, 2026Jo Devriendt, Patrick De Causmaecker, Marc DeneckerLarge Neighborhood Search Constraint Satisfaction
University of Leuven
Inference-Time Scaling in Diffusion Models through Iterative Partial Refinement
May 19, 2026Taegu Kang, Jaesik Yoon, Sungjin AhnDiffusion Models Inference-Time
KAIST · KAIST & SAP · KAIST & NYU
Constrained Code Generation with Discrete Diffusion
May 16, 2026Lize Shao, Michael Cardei, Zichen Xie +2Code Generation Constraint Satisfaction
University of Virginia
Learning Local Constraints for Reinforcement-Learned Content Generators
May 13, 2026Debosmita Bhaumik, Julian Togelius, Georgios N. Yannakakis +1Motion Generation Constraint Satisfaction
Institute of Digital Games, Msida, Malta · Game Innovation Lab, New York, New York, USA
Controlling Logical Collapse in LLMs via Algebraic Ontology Projection over F2
May 13, 2026Hisashi Miyashita, Mgnite IncOntology Collapse
Mgnite Inc.
Formalize, Don't Optimize: The Heuristic Trap in LLM-Generated Combinatorial Solvers
May 12, 2026Haoyu Wang, Yuliang Song, Tao Li +5Functional Code Solvers Solvers
University of Pennsylvania · University of Toronto · Google DeepMind +1
The Polynomial Counting Capabilities of Message Passing Neural Networks
May 11, 2026Marco Sälzer, Pascal Bergsträßer, Anthony W. LinMessage Passing Neural Networks Logic
1RPTU University Kaiserslautern-Landau · 2Max Planck Institute for Software Systems (MPI-SWS)
Adaptive Data Harvesting for Efficient Neural Network Learning with Universal Constraints
May 10, 2026Siteng Kang, Xinhua ZhangParametric Physics-Informed Neural Network Lyapunov Function
University of Illinois Chicago
Agentic MIP Research: Accelerated Constraint Handler Generation
May 9, 2026Liding Xu, Yugeng Zhou, Sebastian PokuttaMixed-Integer Programming Constraint Satisfaction
Zuse Institute Berlin, Berlin, Germany. · Independent Researcher. · Zuse Institute Berlin +1
Where Larger Models Excel: The Primacy of Constraint-Guided Reasoning
May 9, 2026Guan-Yi Lin, Hen-Hsen HuangReasoning Benchmark Model Size
National Chengchi University Taipei, Taiwan · Academia Sinica Taipei, Taiwan
Narrative Landscape: Mapping Narrative Dispositions Across LLMs
May 9, 2026Donghoon Jung, Jiwoo Choi, Songeun Chae +1Narratives Frontier Models
School of Digital Humanities and Computational Social Sciences, KAIST, South Korea
MathConstraint: Automated Generation of Verified Combinatorial Reasoning Instances for LLMs
May 8, 2026Viresh Pati, Zhengyu Li, Piyush Jha +3Combinations Constraint Satisfaction
Georgia Institute of Technology, USA · KNOWIDEA Technologies
Traffic Scenario Orchestration from Language via Constraint Satisfaction
May 7, 2026Frieda Rong, Chris Zhang, Kelvin Wong +1Autonomous Driving Simulation Scenario Generation
University of Toronto · 2Waabi
Multi-Objective Constraint Inference using Inverse reinforcement learning
May 7, 2026Syed Ihtesham Hussain Shah, Floris den Hengst, Aneta Lisowska +1Multi-Objective Reinforcement Learning Constraint Satisfaction
Faculty of Sciences Vrije Universiteit Amsterdam
Logical Consistency as a Bridge: Improving LLM Hallucination Detection via Label Constraint Modeling between Responses and Self-Judgments
May 5, 2026Hao Mi, Qiang Sheng, Shaofei Wang +7Large Language Model Hallucination Hallucination Detection
Institute of Computing Technology, Chinese Academy of Sciences · University of Chinese Academy of Sciences
CP-SynC: Multi-Agent Zero-Shot Constraint Modeling in MiniZinc with Synthesized Checkers
May 3, 2026Yuliang Song, Eldan CohenConstraint Satisfaction Chess
Department of Mechanical and Industrial Engineering, University of Toronto, Toronto, Canada
Residual Drift Dominates Contradiction in Multi-Turn Constraint Reasoning
Apr 28, 2026Sebastien KawadaConstraint Satisfaction Contradiction
Kaons Los Angeles, United States
VISION-SLS: Safe Perception-Based Control from Learned Visual Representations via System Level Synthesis
Apr 27, 2026Antoine P. Leeman, Shuyu Zhan, Melanie N. Zeilinger +1Visual Servoing Visuomotor Control
Institute for Dynamic Systems and Control, ETH Zürich · Georgia Institute of Technology, Schools of 2Interactive Computing, 3Aerospace Engineering
Constraint-Based Analysis of Reasoning Shortcuts in Neurosymbolic Learning
Apr 25, 2026Akihiro Takemura, Katsumi Inoue, Masaaki NishinoNeuro-Symbolic Framework Constraint Satisfaction
National Institute of Informatics, Tokyo, Japan · Communication Science Laboratories, NTT, Inc., Japan
Bridging Reasoning and Action: Hybrid LLM-RL Framework for Efficient Cross-Domain Task-Oriented Dialogue
Apr 25, 2026Yangyang Zhao, Linfan Dai, Li Cai +2Large Language Model Reinforcement Learning LLM Reasoning Strategies
School of Computer Science and Technology, Changsha University of Science and Technology · School of Computer Science and Engineering, Central South University · Text Computing and Cognitive Intelligence MOE Engineering Research Center, Guizhou University +2
No Certificate, No Categorical Speech Act: A Brouwerian Assertibility Constraint for Public Reason
Mar 4, 2026Michael JülichEpistemology Certificates
aihorizon R&D, Munich, Germany.
How Transformers Reject Wrong Answers: Rotational Dynamics of Factual Constraint Processing
Feb 25, 2026Javier MarínTransformer Encoder Transformer Architectures
Groundlens-dev
Robustness of Constraint Automata for Description Logics with Concrete Domains
Jan 27, 2026Stéphane Demri, Tianwen GuConstraint Satisfaction Automata
Universit´e Paris-Saclay, CNRS, ENS Paris-Saclay, Laboratoire M´ethodes Formelles, 91190 Gif-sur-Yvette, France

Sep 30, 2026, cs.LGJ/K move · Enter open · S save

Blackboard Intelligence Can Surpass Autoregressive on Globally Constrained Problems

Woosang Jeon, Jaeyeon Kim, Sham Kakade, Yilun Du+5

Seoul National University · Harvard University · University of Central Florida

Constraint Satisfaction Next-Token Prediction Autoregressive Model Diffusion Language Models

Open paper AskPDF arXiv

Next-token prediction has driven remarkable progress in large language models, yet a growing body of evidence suggests that they can struggle on problems governed by complex global constraints. In this work, we focus on this regime and ask whether some of these limitations arise from the inference interface induced by next-token prediction itself. We study this question through blackboard intelligence: an inference-time perspective in which a model works on a fixed, revisable canvas and searches over candidate solution states rather than committing to a causal, left-to-right trajectory. We instantiate this idea with diffusion language models, whose any-order prediction interface naturally exposes predictions over partially filled solution states. Our key observation is that mean confidence, a simple model-internal quantity available from the standard masked diffusion objective, provides a useful proxy for global coherence and can guide inference-time search and revision. Empirically, across ZebraLogic, Nurse Rostering, and Job-Shop Scheduling, Blackboard consistently improves inference while holding the fine-tuned LLaDA-8B-Instruct checkpoint fixed and substantially outperforms same-scale autoregressive baselines, reaching 90.4% accuracy on ZebraLogic-Hard, 76.4% exact feasibility on Nurse Rostering, and 80.2% optimality on JSSP. Stronger autoregressive search and refinement also fail to close the gap on ZebraLogic-Hard, while Blackboard surpasses tested frontier LLMs there and on JSSP despite their substantially greater scale and strong test-time reasoning. We open-source our codebase at https://github.com/jwoosang1/blackboard-intelligence.

Momentum

Related topics

Latest papers 66