{"paper":{"title":"Text2Model: Modeling Copilots for Text-to-Model Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"LLM copilots translate natural language into solver-agnostic MiniZinc models for both satisfaction and optimization problems.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Akash Singirikonda, Karthik Uppuluri, Serdar Kadioglu","submitted_at":"2026-04-14T16:51:29Z","abstract_excerpt":"There is growing interest in leveraging large language models (LLMs) for text-to-model translation and optimization tasks. This paper aims to advance this line of research by introducing \\textsc{Text2Model} and \\textsc{Text2Zinc}. \\textsc{Text2Model} is a suite of copilots based on several LLM strategies with varying complexity, along with an online leaderboard. \\textsc{Text2Zinc} is a cross-domain dataset for capturing optimization and satisfaction problems specified in natural language, along with an interactive editor with built-in AI assistant. While there is an emerging literature on usin"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"our work is the first attempt to integrate both satisfaction and optimization problems within a unified architecture and dataset. Moreover, our approach is solver-agnostic unlike existing work that focuses on translation to a solver-specific model.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That LLM-generated MiniZinc models will be syntactically correct and semantically faithful to the natural-language specification for realistic combinatorial problems without requiring substantial human correction or solver-specific tuning.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Text2Model copilots and Text2Zinc dataset enable unified, solver-agnostic text-to-MiniZinc translation for both satisfaction and optimization problems using multiple LLM strategies.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"LLM copilots translate natural language into solver-agnostic MiniZinc models for both satisfaction and optimization problems.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"652a79c2e3797db36dc774543fdd8c50ff5b9f8abc7f71e48adbb3bf9f670411"},"source":{"id":"2604.12955","kind":"arxiv","version":3},"verdict":{"id":"eeef7cae-7a63-4e6f-9a05-3bd80edf0a3b","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T15:19:18.910599Z","strongest_claim":"our work is the first attempt to integrate both satisfaction and optimization problems within a unified architecture and dataset. Moreover, our approach is solver-agnostic unlike existing work that focuses on translation to a solver-specific model.","one_line_summary":"Text2Model copilots and Text2Zinc dataset enable unified, solver-agnostic text-to-MiniZinc translation for both satisfaction and optimization problems using multiple LLM strategies.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That LLM-generated MiniZinc models will be syntactically correct and semantically faithful to the natural-language specification for realistic combinatorial problems without requiring substantial human correction or solver-specific tuning.","pith_extraction_headline":"LLM copilots translate natural language into solver-agnostic MiniZinc models for both satisfaction and optimization problems."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.12955/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}