arXiv:2608.10792cs.AIcs.LG2026-08

构建可编程化学世界,实现实验过程精确复现与可控干预。

ChemWorld: Programmable Chemical Worlds for Controlled and Replayable Agent Experimentation

论文配图:ChemWorld: Programmable Chemical Worlds for Controlled and Replayable Agent Experimentation
图 1 · 摘自论文原文
  • 将化学环境拆分为公开接口与私有规则,支持灵活配置
  • 通过交易记录实现操作轨迹完整重放与审计,8个案例验证可靠性
  • 适合研究智能体在不同化学条件下的实验行为,互补物理实验

自主化学研究依赖于可重复交互的实验环境。物理实验室虽提供真实材料证据,但重复成本高且难以精准控制;多数数字环境则固化底层世界。本文提出ChemWorld,一个可编程的化学实验环境,将可复用的流程与观测组件编译为可执行世界。该系统将代理可见的公开实验契约与评估者拥有的化学与材料规则分离,使研究者可在保持公开任务和交互条件不变的前提下,动态调整世界构成、运行条件或单个隐藏规则。事务性执行记录操作、失败、资源变化与状态转移,确保环境-动作轨迹可精确重播与审计。全量验证覆盖参考注册表、52种生成组分及模块、接口、编译与无效操作测试。8个确定性实验案例证明了共享生命周期语义、故障恢复与精确重放能力;6对父子世界分支在相同公开条件下隔离了单一私有规则干预的影响。独立智能体亦通过同一公开接口完成非参考世界的完整生命周期。在声明的组件与模型范围内,ChemWorld为系统化研究跨化学世界的实验行为提供了可控且可复现的基底,补充物理实验室的实证与校准。

原文摘要 · Abstract (English)

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.

智能体实验可复现化学建模

Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。