Foundation Models for Logistics: Toward Certifiable, Conversational Planning Interfaces

2025/07/15 by Yunhao Yang, Yang, Yunhao, Neel P. Bhatt +10
Business, Management and Accounting · Computer Science · Social Sciences · #Artificial Intelligence (cs.AI) #Business Process Modeling and Analysis #FOS: Computer and information sciences #Formal Languages and Automata Theory (cs.FL) #Information Systems Theories and Implementation #Multi-Agent Systems and Negotiation

paper · pdf · doi:10.48550/arxiv.2507.11352

openalex publication_date 2025/07/15 · openalex created_date 2025/10/08 · openalex updated_date 2026/07/28

Abstract

Logistics operators, from battlefield coordinators re-routing airlifts ahead of a storm to warehouse managers juggling late trucks, need to make mission-critical decisions. Prevailing methods for logistics planning such as integer programming yield plans that satisfy user-defined logical constraints, assuming an idealized mathematical model of the environment. On the other hand, foundation models lower the intermediate processing barrier by translating natural-language user utterances into executable plans, yet they remain prone to misinterpretations and hallucinations that jeopardize safety and cost. We introduce a Vision-Language Logistics (VLL) agent, built on a neurosymbolic framework that pairs the accessibility of natural-language dialogue with verifiable guarantees on user-objective interpretation. The agent interprets user requests and converts them into structured planning specifications, quantifies the uncertainty of the interpretation, and invokes an interactive clarification loop when the uncertainty exceeds an adaptive threshold. Drawing on a lightweight airlift logistics planning use case as an illustrative case study, we highlight a practical path toward certifiable and user-aligned decision-making for complex logistics. Our lightweight model, fine-tuned on just 100 training samples, surpasses the zero-shot performance of 20x larger models in logistic planning tasks while cutting inference latency by nearly 50%.

Citations

• Learning Safety Constraints for Large Language Models
• Know Where You're Uncertain When Planning with Multimodal Foundation Models: A Formal Framework
• Planning Anything with Rigor: General-Purpose Zero-Shot Planning with LLM-based Formalized Programming
• Uncertainty-Guided Enhancement on Driving Perception System via Foundation Models
• Airlift Challenge: A Competition for Optimizing Cargo Delivery
• Language Model Cascades: Token-level uncertainty and beyond
• Formal-LLM: Integrating Formal Language and Natural Language for Controllable LLM-based Agents
• Fine-Tuning Language Models Using Formal Methods Feedback
• Direct Preference Optimization: Your Language Model is Secretly a Reward Model
• Inner Monologue: Embodied Reasoning through Planning with Language Models
• LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Action
• Do As I Can, Not As I Say: Grounding Language in Robotic Affordances

Related

• Model-Driven Requirements Configuration with Three-Valued Uncertainty Scoring
• Robots That Ask For Help: Uncertainty Alignment for Large Language Model Planners
• Integrating Large Language Models with Network Optimization for Interactive and Explainable Supply Chain Planning: A Real-World Case Study
• CoT-TL: Low-Resource Temporal Knowledge Representation of Planning Instructions Using Chain-of-Thought Reasoning
• LLMs Can Plan Only If We Tell Them