# CP-Agent: Agentic Constraint Programming

arXiv: https://arxiv.org/abs/2508.07468 · HTML: https://mlsanity.com/paper/2508.07468/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 15 of its 37 references that are in the map.
- First posted on arXiv 10 Aug 2025.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 15 of 15)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation](https://mlsanity.com/paper/2305.01210/) (2023)
- [Executable Code Actions Elicit Better LLM Agents](https://mlsanity.com/paper/2402.01030/) (2024)
- [Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models](https://mlsanity.com/paper/2305.04091/) (2023)
- [LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression](https://mlsanity.com/paper/2310.06839/) (2023)
- [Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directions](https://mlsanity.com/paper/2503.23278/) (2025)
- [RepairAgent: An Autonomous, LLM-Based Agent for Program Repair](https://mlsanity.com/paper/2403.17134/) (2024)
- [NL4Opt Competition: Formulating Optimization Problems Based on Their Natural Language Descriptions](https://mlsanity.com/paper/2303.08233/) (2023)
- [Keep the Conversation Going: Fixing 162 out of 337 bugs for 0.42 each using ChatGPT](https://mlsanity.com/paper/2304.00385/) (2023)
- [Holy Grail 2.0: From Natural Language to Constraint Models](https://mlsanity.com/paper/2308.01589/) (2023)
- [Step-by-Step Reasoning to Solve Grid Puzzles: Where do LLMs Falter?](https://mlsanity.com/paper/2407.14790/) (2024)
- [Combining Constraint Programming Reasoning with Large Language Model Predictions](https://mlsanity.com/paper/2407.13490/) (2024)

## Built on by (most cited first, 6 of 6)

- [Code as Agent Harness](https://mlsanity.com/paper/2605.18747/) (2026)
- [Gala: Global LLM Agents for Text-to-Model Translation](https://mlsanity.com/paper/2509.08970/) (2025)
- [CP-SynC: Multi-Agent Zero-Shot Constraint Modeling in MiniZinc with Synthesized Checkers](https://mlsanity.com/paper/2605.01675/) (2026)
- [ASP-Bench: From Natural Language to Logic Programs](https://mlsanity.com/paper/2602.01171/) (2026)
- [Improving Constraint Models with LLM Agents](https://mlsanity.com/paper/2608.08127/) (2026)
- [Agentic AI-Assisted Modeling for Production Scheduling: Assessment in Constraint Programming](https://mlsanity.com/paper/2610.10184/) (2026)

## Abstract (arXiv)

The translation of natural language to formal constraint models requires expertise in the problem domain and modeling frameworks. To explore the effectiveness of agentic workflows, we propose CP-Agent, a Python coding agent that uses the ReAct framework with a persistent IPython kernel. We provide the relevant domain knowledge as a project prompt of under 50 lines. The algorithm works by iteratively executing code, observing the solver's feedback, and refining constraint models based on execution results. We evaluate CP-Agent on 101 constraint programming problems from CP-Bench. We made minor changes to the benchmark to address systematic ambiguities in the problem specifications and errors in the ground-truth models. On the clarified benchmark, CP-Agent achieves perfect accuracy on all 101 problems. Our experiments show that minimal guidance outperforms detailed procedural scaffolding. Our experiments also show that explicit task management tools can have both positive and negative effects on focused modeling tasks.