# Contract2Plan: Verified Contract-Grounded Retrieval-Augmented Optimization for BOM-Aware Procurement and Multi-Echelon Inventory Planning

arXiv: https://arxiv.org/abs/2601.06164 · HTML: https://mlsanity.com/paper/2601.06164/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 19 references that are in the map.
- First posted on arXiv 7 Jan 2026.

## Builds on (most cited first, 6 of 6)

- [CUAD: An Expert-Annotated NLP Dataset for Legal Contract Review](https://mlsanity.com/paper/2103.06268/) (2021)
- [ContractNLI: A Dataset for Document-level Natural Language Inference for Contracts](https://mlsanity.com/paper/2110.01799/) (2021)
- [OptiBench Meets ReSocratic: Measure and Improve LLMs for Optimization Modeling](https://mlsanity.com/paper/2407.09887/) (2024)
- [Towards Foundation Models for Mixed Integer Linear Programming](https://mlsanity.com/paper/2410.08288/) (2024)
- [InvAgent: A Large Language Model based Multi-Agent System for Inventory Management in Supply Chains](https://mlsanity.com/paper/2407.11384/) (2024)
- [ACORD: An Expert-Annotated Retrieval Dataset for Legal Contract Drafting](https://mlsanity.com/paper/2501.06582/) (2025)

## Built on by (most cited first, 1 of 1)

- [Recall Isn't Enough: Bounding Commitments in Personalized Language Systems](https://mlsanity.com/paper/2605.16712/) (2026)

## Abstract (arXiv)

Procurement and inventory planning is governed not only by demand forecasts and bills of materials (BOMs), but also by operational terms in contracts and supplier documents (e.g., MOQs, lead times, price tiers, allocation caps, substitution approvals). LLM-based extraction can speed up structuring these terms, but extraction-only or LLM-only decision pipelines are brittle: missed clauses, unit errors, and unresolved conflicts can yield infeasible plans or silent contract violations, amplified by BOM coupling. We introduce Contract2Plan, a verified GenAI-to-optimizer pipeline that inserts a solver-based compliance gate before plans are emitted. The system retrieves clause evidence with provenance, extracts a typed constraint schema with evidence spans, compiles constraints into a BOM-aware MILP, and verifies grounding, eligibility, consistency, and feasibility using solver diagnostics, triggering targeted repair or abstention when automation is unsafe. We formalize which clause classes admit conservative repair with contract-safe feasibility guarantees and which require human confirmation. A self-contained synthetic micro-benchmark (500 instances; T=5) computed by exact enumeration under an execution model with MOQ uplift and emergency purchases shows heavy-tailed regret and nontrivial MOQ-violation incidence for extraction-only planning, motivating verification as a first-class component of contract-grounded planning systems.