Current Position
Assistant Professor of MS&E and, by courtesy, of Electrical Engineering
Project Intersection
Overview
Professor Madeleine Udell’s research offers an essential technical and sociotechnical bridge to the agricultural chatbot management project, especially regarding democratizing access to complex optimization tools. Her work addresses both the development of artificial intelligence systems capable of translating natural language into rigorous mathematical models and understanding the adoption barriers these tools face among non-specialist users. In the context of the project, Udell’s work validates the choice of a conversational interface (WhatsApp) to handle real-world data (“messy data”) and transform the informal routine of the rural producer into optimized and reliable management decisions.
”OptiMUS: Scalable Optimization Modeling with (MI)LP Solvers and Large Language Models” (2024)
This research introduces OptiMUS, a Large Language Model (LLM)-based agent that automates formulation and solving of optimization problems from natural language descriptions. The system uses an agent-based framework (Manager, Formulator, Programmer, Evaluator) to overcome limitations of common AI models, such as processing long contexts and complex data. The term (MI)LP refers to (Mixed Integer) Linear Programming, a mathematical technique used to find the best solution among several alternatives, such as route optimization or input use optimization
Translation of Natural Language to Action
- “OptiMUS, a Large Language Model (LLM)-based agent designed to formulate and solve (mixed integer) linear programming problems from their natural language descriptions.”. “OptiMUS, a Large Language Model (LLM)-based agent designed to formulate and solve (mixed integer) linear programming problems from their natural language descriptions.”
- Intersection: The chatbot uses Advanced Audio Processing to perform semantic interpretation of informal audio sent by the producer. Udell’s work provides the technical foundation for these voice commands to be transformed by AI into triggers and mathematical models of operational execution
Accessibility for Small Businesses and Sectors without Experts
- “Automating optimization modeling would allow sectors that cannot afford to have access to optimization experts to improve efficiency using optimization techniques.” “Automating optimization modeling would allow sectors that cannot afford to have access to optimization experts to improve efficiency using optimization techniques.”
- Intersection: The chatbot’s target audience is rural producers who prefer “hands-on operation” and do not have operations research specialists. The system acts as the automated “executive secretary” that brings optimization efficiency into the farm without the need for advanced technical knowledge on the user’s part
""It Was a Magical Box”: Understanding Practitioner Workflows and Needs in Optimization”
This is a qualitative study analyzing real workflows of optimization model developers (OMDs). Udell and collaborators propose the “Three Ds” (Data, Decisions, Dialogue) as the pillars for success of optimization projects in the real world. The term “Dialogue” refers to ongoing communication with stakeholders to build trust, while “Problem Elicitation” describes the phase of translating vague business needs into technical requirements.
Importance of Dialogue for Trust and Adoption
- “Our findings reveal that optimization practice is not only about algorithms that deliver better decisions, but is equally shaped by data and dialogue—the ongoing communication with stakeholders that enables problem framing, trust, and adoption.” “Our findings reveal that optimization practice is not only about algorithms that deliver better decisions, but is equally shaped by data and dialogue—the ongoing communication with stakeholders that enables problem framing, trust, and adoption.”
- Intersection: The project chooses WhatsApp as the primary interface because of its “highly familiar” nature. Udell demonstrates that optimization fails if it is an opaque “magical box”; by using a daily dialogue platform, the chatbot builds the trust necessary for the rural producer to accept the AI’s alerts and suggestions
Dealing with “Messy” Real-World Data
- “optimization is characterized by messy and incomplete data that inform and constraint model formulation…” “optimization is characterized by messy and incomplete data that inform and constraint model formulation…”
- Intersection: The project’s Continuous Learning Engine handles data extracted from audio, messages and images of receipts, which are inherently informal and “messy.” Udell highlights that 70% of effort in real projects is spent processing this data, validating the project’s technological focus on transforming informal field routines into structured management data
Full papers
Madeleine Udell - OptiMUS Scalable Optimization Modeling with (MI)LP Solvers and Large Language Models.pdf Madeleine Udell - “It Was a Magical Box” Understanding Practitioner Workflows and Needs in Optimization.pdf