Metraipolis › archive › dc_a92a434255ee

EnvLunch: The Environment as a Free Lunch for Learning to Interact — arXiv:2610.33817

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.33817
License (as archived)
CC0-1.0
Archived
2026-10-27T07:57:24.500Z
SHA-256 of the archived text
3bc916b13494139d475fd34570df070c0f5a33d4c4a278f81dc93b587e7cad7b
Stable URL of this page
https://metraipolis.com/documento/dc_a92a434255ee

How to cite

EnvLunch: The Environment as a Free Lunch for Learning to Interact — arXiv:2610.33817 — arXiv (en), https://arxiv.org/abs/2610.33817 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a92a434255ee (Metraipolis archive dc_a92a434255ee, sha256 3bc916b13494139d475fd34570df070c0f5a33d4c4a278f81dc93b587e7cad7b)
BibTeX
@misc{dca92a434255ee,
  title = {EnvLunch: The Environment as a Free Lunch for Learning to Interact — arXiv:2610.33817},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.33817},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a92a434255ee; sha256 3bc916b13494139d475fd34570df070c0f5a33d4c4a278f81dc93b587e7cad7b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.33817. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Databases (cs.DB).
Pagina del lavoro: https://arxiv.org/abs/2610.33817 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-27T07:55:30.672Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).