Work

CP-Agent: Agentic Constraint Programming

Year: 2026

Type: conference-paper

Abstract: 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.

Source: International Workshop on Large Language Models for Code (LLM4Code)

DOI: 10.1145/3786181.3788711

Author: Stefan Szeider

Institution: TU Wien

Language: English

Topic: Constraint Satisfaction and Optimization

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funder: Austrian Science Fund

Award: Structure Identification with SAT (STRIDES)