# Amazon AGI paper proposes AutoGym for agent RL environments

A paper from Amazon AGI proposes AutoGym, which writes an agent task, an executable environment, and a verifier together from a small domain seed or past model trajectories.

Language: en
Time zone: America/Los_Angeles
Current time (UTC, cached as of): 2026-10-23T18:45:00.000Z
Query date (America/Los_Angeles): 2026-10-23

HTML: https://didcodexreset.com/news/0cc65f7d7b86416fac59dcbe.html

Content language: en
Localization state: sameLanguage

Source: elvis · Published 9/28/2026, 20:22:54

A paper from Amazon AGI proposes AutoGym for generating reinforcement-learning environments for agents. AutoGym writes the task, the executable environment, and the verifier together, starting from a small domain seed or past model trajectories.

The paper is [arXiv:2609.22592](https://arxiv.org/abs/2609.22592). A [Chat with Paper](https://academy.dair.ai/papers/autogym-blueprint-first-generation-of-verifiable-agent-gyms-2609.22592) page is also available.

Tags: AutoGym, Amazon AGI, Reinforcement learning, AI agents

[View original post](https://x.com/omarsar0/status/2104746239061586055)