# ChemWorld: Programmable Chemical Worlds for Controlled and Replayable Agent Experimentation

arXiv: https://arxiv.org/abs/2608.10792 · HTML: https://mlsanity.com/paper/2608.10792/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 22 references that are in the map.
- First posted on arXiv 11 Aug 2026.

## Builds on (most cited first, 14 of 14)

- [ChemCrow: Augmenting large-language models with chemistry tools](https://mlsanity.com/paper/2304.05376/) (2023)
- [DISCOVERYWORLD: A Virtual Environment for Developing and Evaluating Automated Scientific Discovery Agents](https://mlsanity.com/paper/2406.06769/) (2024)
- [ORGANA: A Robotic Assistant for Automated Chemistry Experimentation and Characterization](https://mlsanity.com/paper/2401.06949/) (2024)
- [NewtonBench: Benchmarking Generalizable Scientific Law Discovery in LLM Agents](https://mlsanity.com/paper/2510.07172/) (2025)
- [Olympus: a benchmarking framework for noisy optimization and experiment planning](https://mlsanity.com/paper/2010.04153/) (2020)
- [BoxingGym: Benchmarking Progress in Automated Experimental Design and Model Discovery](https://mlsanity.com/paper/2501.01540/) (2025)
- [LabUtopia: High-Fidelity Simulation and Hierarchical Benchmark for Scientific Embodied Agents](https://mlsanity.com/paper/2505.22634/) (2025)
- [AutoLabs: Cognitive Multi-Agent Systems with Self-Correction for Autonomous Chemical Experimentation](https://mlsanity.com/paper/2509.25651/) (2025)
- [Measuring Scientific Capabilities of Language Models with a Systems Biology Dry Lab](https://mlsanity.com/paper/2507.02083/) (2025)
- [PC-Gym: Benchmark Environments For Process Control Problems](https://mlsanity.com/paper/2410.22093/) (2024)
- [MADE: Benchmark Environments for Closed-Loop Materials Discovery](https://mlsanity.com/paper/2601.20996/) (2026)
- [Agentic Exploration of Physics Models](https://mlsanity.com/paper/2509.24978/) (2025)
- [Scaling Scientific Discovery Environments for Turn-Level Agentic RL](https://mlsanity.com/paper/2607.28990/) (2026)
- [Labimus: A Simulation and Benchmark for Humanoid Dexterous Manipulation in Chemical Laboratory](https://mlsanity.com/paper/2606.31037/) (2026)

## Abstract (arXiv)

Autonomous chemistry increasingly depends on environments in which agents can repeatedly act, observe, and adapt.Physical laboratories provide essential real-material evidence but are costly to repeat and difficult to use for tightly matched interventions, whereas most digital environments keep the underlying experimental world largely fixed. We introduce ChemWorld, a programmable chemical environment in which reusable process and observation components are compiled into executable worlds. ChemWorld separates the public experimental contract available to an agent from evaluator-owned chemical and material laws. Researchers can therefore vary world composition and operating conditions, or change a single hidden law while holding the public task and interaction conditions fixed. Transactional execution records operations, failures, resource changes, and state transitions, allowing complete environment-action trajectories to be replayed exactly and audited. Full-census qualification covered the reference registry, 52 generated compositions, and module, interface, compilation, and invalid-action tests. Eight deterministic experimental cases demonstrated shared lifecycle semantics, failure recovery, and exact replay, while six parent-child world-fork pairs isolated the effects of single private-law interventions under matched public conditions. An independent agent also completed a full lifecycle in a non-reference world through the same public interface. Within the declared component and model domain, ChemWorld provides a controlled and replayable substrate for studying experimentation across systematically varied chemical worlds, complementary to physical-laboratory evidence and calibration.