🤖 AI Summary
This work addresses the challenge of translating natural language descriptions of biological experimental protocols into executable robotic instructions, particularly in the context of microplate operations where a significant semantic gap exists. To bridge this gap, the authors propose a dual-agent framework: a parsing agent first structures the protocol and, through a rule-based mapping engine, generates device-specific commands; a heterogeneous large language model (LLM) verification agent then performs cross-validation and self-correction. The approach integrates a rule engine, LLM-based parsing and verification, structured protocol representation, and explicit modeling of microplate manipulation constraints to achieve high-fidelity, verifiable translation from natural language to robot-executable instructions. Evaluated on ELISA protocols, the system demonstrates the impact of model scale and verifier type on accuracy and successfully executes an end-to-end autonomous Bradford protein assay.
📝 Abstract
Biological experiment protocols are written in natural language, whereas automation systems rely on predefined control commands, creating a semantic gap that limits autonomous execution. Microplate-based automatic experiments are particularly challenging due to the need to simultaneously control well mapping, sample-reagent combinations, replicate placement, and parallel dispensing. This study proposes an agent-based protocol translation framework that converts natural-language microplate-based protocols into executable control commands for a robotic laboratory platform. A Parser Agent formalizes the natural-language protocol into a structured representation, and a rule-based mapping engine deterministically incorporates the operational constraints of the robotic laboratory platform to generate device-level control commands. A heterogeneous LLM Validation Agent verifies completeness, parameter accuracy, and execution order, and triggers a self-correction loop with structured feedback when errors are detected. A sweep involving 7 Parsers and 3 Validators on randomly selected ELISA protocols evaluates how model scale and Validator type affect translation accuracy and pass rates under cross-model verification. The accuracy-latency trade-off is further verified by comparing the rule-based mapping of the proposed framework with LLM end-to-end direct mapping. Finally, Bradford assay-based protein quantification using a microplate was demonstrated on a robotic laboratory platform, validating end-to-end autonomous execution from natural-language protocols to real-world experiments. The proposed framework provides a flexible approach to narrowing the semantic gap between natural-language protocols and microplate-based self-driving laboratories.