MiniZinc
PulseAugur coverage of MiniZinc — every cluster mentioning MiniZinc across labs, papers, and developer communities, ranked by signal.
-
AI agents automate feature extractor creation for complex problems
Researchers have developed agentic approaches to automate the creation of feature extractors for constraint satisfaction problems. One method uses Large Language Models (LLMs) in a check-fix-verify loop to generate Pyth…
-
LLM generates graphs for constraint optimization, outperforming Gurobi baseline
Researchers have developed a novel pipeline that uses Large Language Models (LLMs) to generate problem-agnostic graphs for constraint optimization problems. By prompting an LLM with semantic guidelines, the system creat…
-
New Text2Model copilots translate natural language to formal models
Researchers have introduced Text2Model, a suite of copilots designed to translate natural language into formal models for optimization and satisfaction problems. This work also presents Text2Zinc, a novel dataset and in…
-
LLM-generated solvers fall into 'heuristic trap' on combinatorial problems
Researchers have developed a new benchmark, CP-SynC-XL, comprising 100 combinatorial problems to evaluate how Large Language Models (LLMs) synthesize executable solvers. Their findings indicate that using LLMs to formal…
-
CP-SynC system uses multi-agent approach for zero-shot constraint modeling
Researchers have developed CP-SynC, a novel multi-agent system designed to automate the translation of natural language problem descriptions into executable Constraint Programming (CP) models for MiniZinc. This system u…