# Ask, Clarify, Optimize: Human-LLM Agent Collaboration for Smarter Inventory Control

arXiv: https://arxiv.org/abs/2601.00121 · HTML: https://mlsanity.com/paper/2601.00121/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use.
- Builds on 12 of its 43 references that are in the map.
- First posted on arXiv 31 Dec 2025.

## Placed in

- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 12 of 12)

- [How to Build User Simulators to Train RL-based Dialog Systems](https://mlsanity.com/paper/1909.01388/) (2019)
- [Neural User Simulation for Corpus-based Policy Optimisation for Spoken Dialogue Systems](https://mlsanity.com/paper/1805.06966/) (2018)
- [OptiMUS: Optimization Modeling Using MIP Solvers and large language models](https://mlsanity.com/paper/2310.06116/) (2023)
- [OptiMUS-0.3: Using Large Language Models to Model and Solve Optimization Problems at Scale](https://mlsanity.com/paper/2407.19633/) (2024)
- [Large Language Models for Manufacturing](https://mlsanity.com/paper/2410.21418/) (2024)
- [Deep Inventory Management](https://mlsanity.com/paper/2210.03137/) (2022)
- [InvAgent: A Large Language Model based Multi-Agent System for Inventory Management in Supply Chains](https://mlsanity.com/paper/2407.11384/) (2024)
- [Auto-Formulating Dynamic Programming Problems with Large Language Models](https://mlsanity.com/paper/2507.11737/) (2025)
- [Reinforcement Learning for Multi-Product Multi-Node Inventory Management in Supply Chains](https://mlsanity.com/paper/2006.04037/) (2020)
- [Deep Reinforcement Learning for Inventory Networks: Toward Reliable Policy Optimization](https://mlsanity.com/paper/2306.11246/) (2023)
- [Rethinking Supply Chain Planning: A Generative Paradigm](https://mlsanity.com/paper/2509.03811/) (2025)
- [Reinforcement Learning with Intrinsically Motivated Feedback Graph for Lost-sales Inventory Control](https://mlsanity.com/paper/2406.18351/) (2024)

## Built on by (most cited first, 5 of 5)

- [AI Agents for Inventory Control: Human-LLM-OR Complementarity](https://mlsanity.com/paper/2602.12631/) (2026)
- [LLM-SAA: LLM-persona Generated Distributions for Decision-making](https://mlsanity.com/paper/2602.06357/) (2026)
- [The Value of Information in Resource-Constrained Pricing](https://mlsanity.com/paper/2603.24974/) (2026)
- [LLM Biases](https://mlsanity.com/paper/2604.26960/) (2026)
- [LLM-Powered Virtual Population for Demand Simulation and Pricing](https://mlsanity.com/paper/2606.16183/) (2026)

## Abstract (arXiv)

Inventory management remains a challenge for many small and medium-sized businesses that lack the expertise to deploy advanced optimization methods. This paper investigates whether Large Language Models (LLMs) can help bridge this gap. We show that employing LLMs as direct, end-to-end solvers incurs a significant "hallucination tax": a performance gap arising from the model's inability to perform grounded stochastic reasoning. To address this, we propose a hybrid agentic framework that strictly decouples semantic reasoning from mathematical calculation. In this architecture, the LLM functions as an intelligent interface, eliciting parameters from natural language and interpreting results while automatically calling rigorous algorithms to build the optimization engine. To evaluate this interactive system against the ambiguity and inconsistency of real-world managerial dialogue, we introduce the Human Imitator, a fine-tuned "digital twin" of a boundedly rational manager that enables scalable, reproducible stress-testing. Our empirical analysis reveals that the hybrid agentic framework reduces total inventory costs by 32.1% relative to an interactive baseline using GPT-4o as an end-to-end solver. Moreover, we find that providing perfect ground-truth information alone is insufficient to improve GPT-4o's performance, confirming that the bottleneck is fundamentally computational rather than informational. Our results position LLMs not as replacements for operations research, but as natural-language interfaces that make rigorous, solver-based policies accessible to non-experts.