Agentic Language-to-Objective Synthesis for Optofluidic Assembly

2026-05-26

AI Summary

This work addresses the bottleneck in manufacturing automation wherein natural language instructions cannot be directly translated into executable objective functions. The authors propose a modular agent framework that leverages a conditioned large language model to map natural language commands into differentiable objective functions, integrated with a constraint-aware SLSQP inverse solver and laser-induced thermocapillary flow actuation to enable particle assembly on an optofluidic platform. This approach uniquely decouples natural language specification, objective function formulation, and physical execution, thereby supporting intent–actuation separation, partial trajectory reconstruction, and perturbation recovery. Experimental results demonstrate that AI-driven, light-mediated microscale particle patterning achieves high-precision placement, topological adaptability, and robust recovery, establishing the feasibility of natural language programming in optical manufacturing.

Abstract

Light-based advanced manufacturing increasingly requires programmable, closed-loop tools that translate human design intent into executable operations at small length scales. Yet a key bottleneck persists across robotic and manufacturing modalities: turning user intent into machine-readable objectives that are reliably executable. While micro-robotics offers versatile manipulation via optical actuation of fluids, mathematically tractable goal specification remains manual and hard to reuse. Here, we introduce Speak-to-Objective, a modular agentic pipeline that uses a conditioned Large Language Model (LLM) to translate spoken or written commands into fully differentiable objective functions for assembling microparticles in a constraint-aware inverse solver (SLSQP) and on an experimental optofluidic platform. The approach employs a compact loop - perceive -> compose -> propose -> act -> report & learn - that treats the objective as the interface between intent and actuation, separating what to assemble or pattern from how to actuate, while learning from user feedback. The pipeline composes geometry, spacing, and assignment/topology terms to generate robust descriptive objectives that assemble from partial traces and recover after perturbations, as well as explicit objectives for precise placement, all in an actuator-agnostic fashion. Using laser-induced thermoviscous flows as the physical actuation modality, we demonstrate natural-language-programmable, light-based microscale assembly of particle patterns in a microfluidic environment. Beyond its immediate impact on programmable microassembly, and using laser-induced optofluidic actuation as a reduced-complexity experimental platform, our work points toward self-driving, AI-assisted optical manufacturing platforms in which natural language, differentiable objectives, and laser-based actuation are coupled into a reusable digital workflow.

Problem

• language-to-objective synthesis
• optofluidic assembly
• microscale manufacturing
• human intent translation
• programmable microassembly

Innovation

• Agentic AI
• Differentiable Objectives
• Optofluidic Assembly
• Natural Language Programming
• Inverse Design