simPCL: An Open-Framework Simulator and Benchmark Generator for Programmable Cloud Laboratories

Problem

Evaluating autonomous agents for experimental orchestration on real laboratory hardware is slow and expensive. Progress on planning, fault recovery, closed-loop scientific discovery, and decision-making needs simulation environments and benchmarks that support controlled offline study.

Approach

I am building simPCL, an open-framework simulator and benchmark generator for programmable cloud laboratories. It supports controlled study of:

• long-horizon experimental planning;
• recovery from instrument and workflow failures;
• reliable execution across multi-step protocols; and
• closed-loop decisions in which measurements determine the next experiment.

simPCL complements our work on physical laboratory automation using MHS: real equipment demonstrates what an agent can accomplish, while simulation makes it possible to evaluate many scenarios reproducibly before using scarce laboratory time.

I am interested in taking this further into 3D laboratory simulation: sim-to-real transfer, reinforcement learning in MuJoCo, and world models for those environments.

Status

Manuscript in preparation. Related work was presented at the AI Scientist Summer Workshop (Microsoft Research, 2026) in a contributed talk on agentic fault recovery. Code and benchmarks will be released with the paper.