# LabCompiler: A Framework for Verifiable Human-Machine Laboratory Execution from Imperfect Protocols

arXiv: https://arxiv.org/abs/2610.19550 · HTML: https://mlsanity.com/paper/2610.19550/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 34 references that are in the map.
- First posted on arXiv 14 Oct 2026.

## Builds on (most cited first, 13 of 13)

- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence](https://mlsanity.com/paper/2606.19348/) (2026)
- [Executable Code Actions Elicit Better LLM Agents](https://mlsanity.com/paper/2402.01030/) (2024)
- [ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Models](https://mlsanity.com/paper/2404.07738/) (2024)
- [LAB-Bench: Measuring Capabilities of Language Models for Biology Research](https://mlsanity.com/paper/2407.10362/) (2024)
- [Automated Hypothesis Validation with Agentic Sequential Falsifications](https://mlsanity.com/paper/2502.09858/) (2025)
- [BioProBench: A Corpus and Benchmark for Biological Protocol Reasoning in Autonomous Science](https://mlsanity.com/paper/2505.07889/) (2025)
- [LABBench2: An Improved Benchmark for AI Systems Performing Biology Research](https://mlsanity.com/paper/2604.09554/) (2026)
- [Completing A Systematic Review in Hours instead of Months with Interactive AI Agents](https://mlsanity.com/paper/2504.14822/) (2025)
- [Unleashing Scientific Reasoning for Bio-experimental Protocol Generation via Structured Component-based Reward Mechanism](https://mlsanity.com/paper/2510.15600/) (2025)
- [BioProAgent: Neuro-Symbolic Grounding for Constrained Scientific Planning](https://mlsanity.com/paper/2603.00876/) (2026)
- [ProtoAct: Turning Wet-Lab Protocols into Embodied Robotic Actions](https://mlsanity.com/paper/2608.01690/) (2026)
- [A Self-Evolving Agentic System for Automated Generation and Execution of Biological Protocols](https://mlsanity.com/paper/2606.31763/) (2026)

## Abstract (arXiv)

Closing the loop of AI-driven science requires reliably translating natural-language protocols into executable laboratory workflows despite protocol defects and heterogeneous hardware. Existing approaches often couple scientific interpretation with device-specific code generation, making errors difficult to localize and limiting reuse across laboratory platforms. We introduce LabCompiler, a robust protocol-to-execution framework that transforms imperfect natural-language protocols into verifiable human-machine workflows. Its protocol firewall diagnoses and repairs defects before compilation while preserving unaffected content, guided by troubleshooting knowledge accumulated through perturbation-guided self-evolution. A two-level, device-agnostic graph representation separates experimental semantics from hardware-specific implementation and supports capability-based device assignment with coordinated human execution. We further introduce a protocol recovery benchmark covering four controlled perturbation types and naturally occurring errors collected from protocols written by iGEM participants. Experiments show that LabCompiler outperforms frontier LLMs in protocol error correction while enabling coordinated human-machine execution across heterogeneous, partially automated laboratory settings.