Paper page - EnvLunch: The Environment as a Free Lunch for Learning to Interact

Source: https://huggingface.co/papers/2610.33817 Published on Oct 24

·

Submitted byhttps://huggingface.co/thinkwee

weiliuon Oct 27

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 withexecutable environments(i.e., databases). While high-quality annotated tasks require heavy manual effort, an executable environment already provides rich interaction structure andverifiable 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 downstreamagentic reinforcement learning. EnvLunch samples validaction trajectories, executes them to obtain final observations, and trains an agent to recover a functionally equivalent trajectory given only its final observation. Thislabel-free warm-upenables 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 pageView PDFGitHub0Add 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 paper0

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 paper0

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 paper0

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 paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.