A Self-Evolving Agentic System for Automated Generation and Execution of Biological Protocols

• URL: http://arxiv.org/abs/2606.31763v2
• Date: Thu, 02 Jul 2026 09:27:31 GMT
• Title: A Self-Evolving Agentic System for Automated Generation and Execution of Biological Protocols
• Abstract summary: ProtoPilot is a self-evolving multi-agent system for wet-lab automation.<n>It incorporates layer-wise verifiability, multi-agent orchestration and a runtime skill-updated library to generate protocols.<n>It achieved a Top@3 expert-preference rate of 90.2%, an overall protocol-tocode gate pass rate of 89.5% and an Opentrons pass rate of 88.24%.
• Score: 26.510927882022884
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Autonomous wet-lab experimentation requires more than plausible protocol text: biological intent, quantitative procedures, device constraints and experimental feedback must remain aligned from protocol and SOP design to code and physical execution. We developed ProtoPilot, a self-evolving multi-agent system, together with an expert-grounded benchmark and evaluation framework for testing this conversion as an experimental automation problem. The framework spans 294 synthetic-biology and molecular-biology tasks derived from 98 gold-standard protocols, wet-lab expert rubrics, device-level validity gates and real experimental tests. ProtoPilot incorporates layer-wise verifiability, multi-agent orchestration and a runtime-updated skill library to generate protocols, expand SOPs, synthesize SDK-compliant code and revise workflows from wet-lab feedback. It achieved a Top@3 expert-preference rate of 90.2%, an overall protocol-to-code gate pass rate of 89.5% and an Opentrons pass rate of 88.24%, compared with 32.35% for OpenTrons-AI. Wet-lab validation produced interpretable readouts, Sanger-confirmed products and feedback-corrected PCA-assembled DNA targets, establishing a verifiable route to autonomous experimentation. Together, these results show that the evaluation framework captures execution-relevant requirements for autonomous wet-lab automation, and that ProtoPilot can meet them by converting protocol and code generation into validated execution and feedback-guided revision.

Related papers

• DianShi-RxnDB: A Large-Scale, Fine-Grained Organic Reaction Data Platform Built via a Fully Automated Pipeline for Researchers and AI Agents [77.19284650368924]
  We present DianShi-RxnDB, a large-scale, fine-grained organic reaction data platform.<n>It is built via a fully automated extraction and normalization pipeline.<n>The platform provides a Web research workbench for searching, filtering, comparing, and source-verifying records.
  arXiv  Detail & Related papers  (2026-09-06T16:20:43Z)
• ProtoAct: Turning Wet-Lab Protocols into Embodied Robotic Actions [21.45755897337409]
  We present ProtoAct, a structured protocol-grounding framework that converts free-form biological procedures into state-aware, embodiment-ready action sequences.<n>ProtoAct uses ProtoRAG to retrieve manually annotated examples for context-sensitive parsing, RefineChecker to detect and revise missing or inconsistent steps, and applies Act to map the refined procedure into constrained function sequences.
  arXiv  Detail & Related papers  (2026-08-03T04:39:01Z)
• Dual-Agent Framework for Cross-Model Verified Translation of Natural-Language Protocols into Robotic Laboratory Platform [1.0499611180329804]
  This study proposes an agent-based protocol translation framework that converts natural-language protocols into executable control commands.<n>The proposed framework provides a flexible approach to narrowing the semantic gap between natural-language protocols and microplate-based self-driving laboratories.
  arXiv  Detail & Related papers  (2026-06-18T11:43:27Z)
• LabVLA: Grounding Vision-Language-Action Models in Scientific Laboratories [95.20367571157679]
  Vision-Language-Action (VLA) models provide one possible interface between written protocols and robot execution.<n>Existing policies are trained mostly on household and tabletop demonstrations and rarely encounter the instruments, transparent liquids, or fixed protocol found in scientific laboratories.<n>We present LabVLA, trained with a two-stage recipe: FAST action token pretraining first makes the Qwen3-VL-4B-Instruct backbone action aware before any continuous control is learned, and flow matching posttraining then attaches a DiT action expert under knowledge insulation.
  arXiv  Detail & Related papers  (2026-06-11T17:03:53Z)
• From Prompts to Protocols: An AI Agent for Laboratory Automation [1.9609766210591626]
  We present an AI agent architecture that integrates large language models with laboratory orchestration.<n>The AI agent operates under an agentic loop with automated validation and error correction.<n>It supports the complete experimental lifecycle: creating protocols, running and monitoring both protocols and closed-loop optimization campaigns.
  arXiv  Detail & Related papers  (2026-05-15T18:52:41Z)
• Towards a Virtual Neuroscientist: Autonomous Neuroimaging Analysis via Multi-Agent Collaboration [53.772014300855375]
  We introduce NIAgent, a multi-agent system for autonomous end-to-end neuroimaging analysis.<n>Unlike conventional flat tool-calling agents, NIAgent adopts a code-centric execution paradigm.<n>We propose a hierarchical verification framework for autonomous quality control, integrating cohort-level metric screening with agentic visual inspection.
  arXiv  Detail & Related papers  (2026-05-10T06:30:19Z)
• BioProVLA-Agent: An Affordable, Protocol-Driven, Vision-Enhanced VLA-Enabled Embodied Multi-Agent System with Closed-Loop-Capable Reasoning for Biological Laboratory Manipulation [15.461936066333633]
  BioProVLA-Agent is a protocol-driven, vision-enhanced embodied multi-agent system for biological manipulation.<n>It integrates protocol parsing, visual state verification, and embodied execution in a closed-loop workflow.<n>We evaluate the system on a hierarchical benchmark covering 15 atomic tasks, 6 composite tasks, and 3 bimanual tasks.
  arXiv  Detail & Related papers  (2026-05-08T06:15:40Z)
• LightStim: A Framework for QEC Protocol Evaluation and Prototyping with Automated DEM Construction [15.182225662071167]
  We present LightStim, a framework that automates DEM construction concurrently with circuit compilation.<n>We benchmark LightStim across protocols from memory experiments to end-to-end distillation circuits.<n>We additionally accelerate the exploration of new protocols, which we demonstrate through a novel heterogeneous cross-code lattice surgery design.
  arXiv  Detail & Related papers  (2026-04-23T09:30:00Z)
• Autogenesis: A Self-Evolving Agent Protocol [60.15939127351914]
  We introduce Autogenesis Protocol (AGP), a self evolution protocol that decouples what evolves from how evolution occurs.<n>We present Autogenesis System (AGS), a self-evolving multi-agent system that dynamically instantiates, retrieves, and refines protocol-registered resources during execution.
  arXiv  Detail & Related papers  (2026-04-16T14:04:06Z)
• PRISM: Protocol Refinement through Intelligent Simulation Modeling [4.839327116611717]
  We introduce PRISM, a framework that automates the design, validation, and execution of experimental protocols.<n>PRISM uses a set of language-model-based agents that work together to generate and refine experimental steps.<n>We demonstrate PRISM as a practical end-to-end workflow that bridges language-based protocol generation, simulation-based validation, and automated robotic execution.
  arXiv  Detail & Related papers  (2026-01-08T20:15:28Z)
• DrugPilot: LLM-based Parameterized Reasoning Agent for Drug Discovery [54.79763887844838]
  Large language models (LLMs) integrated with autonomous agents hold significant potential for advancing scientific discovery through automated reasoning and task execution.<n>We introduce DrugPilot, a LLM-based agent system with a parameterized reasoning architecture designed for end-to-end scientific in drug discovery.<n>DrugPilot significantly outperforms state-of-the-art agents such as ReAct and LoT, achieving task completion rates of 98.0%, 93.5%, and 64.0% for simple, multi-tool, and multi-turn scenarios, respectively.
  arXiv  Detail & Related papers  (2025-05-20T05:18:15Z)
• SOEN-101: Code Generation by Emulating Software Process Models Using Large Language Model Agents [50.82665351100067]
  FlowGen is a code generation framework that emulates software process models based on multiple Large Language Model (LLM) agents. We evaluate FlowGenScrum on four benchmarks: HumanEval, HumanEval-ET, MBPP, and MBPP-ET.
  arXiv  Detail & Related papers  (2024-03-23T14:04:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.