mlsanityData to 7 Oct 2026

CP-SynC: Multi-Agent Zero-Shot Constraint Modeling in MiniZinc with Synthesized Checkers

arXiv 2605.01675 ↗First posted 3 May 2026cs.AI cs.CLcited by 2

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

Constraint Programming (CP) is a powerful paradigm for solving combinatorial problems, yet translating natural language problem descriptions into executable models remains a significant bottleneck. While Large Language Models (LLMs) show promise in automating this translation, they often struggle with subtle semantic errors in the absence of oracle validation at test time. To address this, we introduce CP-SynC (Constraint Programming modeling with Synthesized Checkers), a multi-agent workflow for zero-shot constraint modeling in MiniZinc. CP-SynC coordinates modeling agents that generate and refine candidate models and validation agents that synthesize semantic checkers to provide feedback on semantic correctness. To mitigate noise inherent in individual LLM outputs, CP-SynC explores multiple modeling trajectories in parallel and employs selection agents to select the final model via multi-agent evidence aggregation. Extensive experiments on a benchmark of 100 CP problems show that CP-SynC substantially outperforms existing baselines in MiniZinc modeling.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 14 of its 28 references that are in the map. First posted on arXiv 3 May 2026.

Builds on

14 of 28 references.

References · 14

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,655
  3. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  4. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  5. 2023Large Language Models Cannot Self-Correct Reasoning Yetcited by 965
  6. 2023Teaching Large Language Models to Self-Debugcited by 963
  7. 2025Large Language Models as End-to-end Combinatorial Optimization Solverscited by 27
  8. 2025Revisit Self-Debugging with Self-Generated Tests for Code Generationcited by 21
  9. 2024Generating Streamlining Constraints with Large Language Modelscited by 7
  10. 2025Text2Zinc: A Cross-Domain Dataset for Modeling Optimization and Satisfaction Problems in MiniZinccited by 7
  11. 2023Operational Research: Methods and Applicationscited by 6
  12. 2025Pragmatic Reasoning improves LLM Code Generationcited by 6
2 more
  1. 2025CP-Agent: Agentic Constraint Programmingcited by 6
  2. 2025Variational Prefix Tuning for Diverse and Accurate Code Summarization Using Pre-trained Language Modelscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Formalize, Don't Optimize: The Heuristic Trap in LLM-Generated Combinatorial Solverscited by 2
  2. 2026OR for AI That Does OR: Routing LLMs up the Escalator inside the OSCAR Frameworkcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Improving Constraint Models with LLM Agents
  2. 2025Gala: Global LLM Agents for Text-to-Model Translation
  3. 2025CO-Bench: Benchmarking Language Model Agents in Algorithm Search for Combinatorial Optimization
  4. 2026Multi-Agent Constraint Factorization Reveals Latent Invariant Solution Structure
  5. 2026OptiLoop: Coordination-in-the-Loop Verification and Repair for LLM-Generated Optimization Agents
  6. 2026CP-Agent: A Calibrated Risk-Controlled Agent for Feedback-Driven Competitive Programming
  7. 2024Testing and Understanding Erroneous Planning in LLM Agents through Synthesized User Inputs
  8. 2026Agentic Proposing: Enhancing Large Language Model Reasoning via Compositional Skill Synthesis