用世界模型预判数据操作效果，让数据分析智能体更高效
DSWorld: A Data Science World Model for Efficient Autonomous Agents
- 构建数据科学世界模型，预测操作后的状态变化
- 训练加速14倍，推理搜索提速3-6倍，预测准确率高35.6%
- 适合想提升数据自动化效率的研究者与工程师
尽管自主数据科学智能体具备强大的数据理解与决策能力，仍依赖耗时的试错流程，导致计算成本高昂。为此，本文提出数据科学世界模型，通过预测当前工作流状态与候选操作下的环境状态转移，模拟执行环境。我们进一步构建了DSWorld框架，整合结构化状态构建、成本感知路由、轻量级真实执行及基于大模型的昂贵操作仿真器。为支持训练，我们构建了8000规模的状态转移轨迹数据集，并提出反思式世界模型优化策略，一种面向错误的强化学习方法以提升预测能力。实验表明，DSWorld使基于强化学习的智能体训练提速约14倍，基于搜索的推理提速3-6倍，同时保持优异性能；在状态转移预测任务上，比最强的LLM基线高出35.6%。代码已开源。
原文摘要 · Abstract (English)
Despite strong capabilities in data understanding and decision-making, autonomous data science agents still heavily rely on trial-and-error workflows that involve expensive computation. This bottleneck motivates models that can anticipate the effects of data science operations before real execution. In this paper, we introduce the concept of Data Science World Model, which model the data science execution environment by predicting environment state transitions conditioned on current workflow states and candidate operations. We further propose DSWorld, a practical framework that combines structured state construction, cost-aware routing, lightweight real execution, and an LLM-based simulator for expensive operations. To support training, we construct an 8K-scale transition trajectory dataset and introduce Reflective World Model Optimization, an error-aware reinforcement learning strategy for improving transition prediction. Experiments show that DSWorld accelerates RL-based agent training by approximately $14\times$ and search-based inference by approximately $3$-$6\times$ while maintaining competitive performance, and outperforms the strongest LLM baseline by 35.6% on transition prediction tasks. The code is available at https://anonymous.4open.science/r/DSWorld.
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。