EnvLunch:環境是學習互動的免費資源
EnvLunch: The Environment as a Free Lunch for Learning to Interact
EnvLunch 利用可執行環境生成可驗證、無需人工標註的訓練軌跡,作為智能體強化學習前的預熱階段,提升下游任務表現。在不同下游訓練預算下,模型平均較基線高逾 9 分;標註資料較少時,基線需要 8 至 32 倍的標註例子,才能達到 EnvLunch 在最低訓練預算下的準確度。
Published on Oct 24
·
on Oct 27
Authors:
,
,
Abstract
EnvLunch leverages executable environments to generate verifiable training trajectories without human annotations, improving agent performance and reducing labeled data requirements for downstream tasks.
For agentic data analysis, language-model agents often require a large number of annotated tasks to learn how to interact effectively with executable environments (i.e., databases). While high-quality annotated tasks require heavy manual effort, an executable environment already provides rich interaction structure and verifiable outcomes. In this sense, the environment itself offers a free lunch, an additional set of verifiable tasks that require no human annotation. We propose EnvLunch, a warm-up stage that turns this environmental signal into agent training without human-written or model-generated task descriptions, before downstream agentic reinforcement learning. EnvLunch samples valid action trajectories, executes them to obtain final observations, and trains an agent to recover a functionally equivalent trajectory given only its final observation. This label-free warm-up enables the model to outperform the baseline by over 9 points on average across all downstream training budgets, and with few labels, the baseline needs 8 to 32 times as many annotated examples to match the accuracy that the EnvLunch model reaches at its smallest training budget. Letting the environment alone define the task yields a larger gain than having the model write its own tasks over the same environments, and this warm-up also improves fine-tuning on benchmarks beyond data analysis. EnvLunch therefore saves annotated tasks and provides a better starting point for fine-tuning agentic models when such tasks are limited.
View arXiv page View PDF GitHub Add to collection
Get this paper in your agent:
hf papers read 2610.33817
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2610.33817 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2610.33817 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2610.33817 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co