# InvEvolve: Evolving White-Box Inventory Policies via Large Language Models with Performance Guarantees

arXiv: https://arxiv.org/abs/2605.00369 · HTML: https://mlsanity.com/paper/2605.00369/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 39 references that are in the map.
- First posted on arXiv 1 May 2026.

## Builds on (most cited first, 9 of 9)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [AlphaEvolve: A coding agent for scientific and algorithmic discovery](https://mlsanity.com/paper/2506.13131/) (2025)
- [Large Language Models for Supply Chain Optimization](https://mlsanity.com/paper/2307.03875/) (2023)
- [InvAgent: A Large Language Model based Multi-Agent System for Inventory Management in Supply Chains](https://mlsanity.com/paper/2407.11384/) (2024)
- [HeurAgenix: Leveraging LLMs for Solving Complex Combinatorial Optimization Challenges](https://mlsanity.com/paper/2506.15196/) (2025)
- [Bandits with many optimal arms](https://mlsanity.com/paper/2103.12452/) (2021)
- [Large-Scale Optimization Model Auto-Formulation: Harnessing LLM Flexibility via Structured Workflow](https://mlsanity.com/paper/2601.09635/) (2026)
- [DeepStock: Reinforcement Learning with Policy Regularizations for Inventory Management](https://mlsanity.com/paper/2603.19621/) (2026)
- [Learning Virtual Machine Scheduling in Cloud Computing through Language Agents](https://mlsanity.com/paper/2505.10117/) (2025)

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

- [OR-Space: A Full-Lifecycle Workspace Benchmark for Industrial Optimization Agents](https://mlsanity.com/paper/2605.28158/) (2026)

## Abstract (arXiv)

We study how large language models can be used to generate inventory policies in online settings with non-stationary demand. Our work is motivated by recent advances in LLM-based evolutionary search, such as AlphaEvolve, which demonstrates strong performance on static and highly structured problems such as mathematical discovery, but is not directly suited to dynamic inventory settings with online updates. We propose InvEvolve, an end-to-end inventory policy evolution and inference framework grounded in confidence-interval-based certification. Built on a large language model trained via reinforcement learning, InvEvolve can process demand data together with additional numerical and textual features, and generates white-box inventory policies with statistical safety guarantees for future deployment. We further introduce a unified framework with theoretical guarantees that connects training, inference, and deployment. This allows us to derive a lower bound on the probability that InvEvolve evolves a statistically safe and improved policy, and to characterize the multi-period performance gap relative to the oracle-safe benchmark. Tested on both synthetic data and real-world retail data, InvEvolve outperforms classical inventory policies and deep-learning-based methods. In canonical inventory settings, it generates new policies that outperform existing benchmarks.