open-ended-environments

Introduces AgentOdyssey, a procedural text game generation framework designed to evaluate agents on test-time continual learning abilities including exploration, episodic memory, world knowledge acquisition, skill learning, and long-horizon planning. The framework highlights significant gaps between current agents and human performance.

This paper introduces JAMEL, a framework that jointly trains agentic memory and exploration policies using novelty signals, enabling efficient exploration in open-ended environments with reduced computational costs.

GRLO introduces a novel reinforcement learning post-training method that achieves strong generalization across multiple domains (math, code, etc.) from only 5K prompts and 22.7 GPU hours, significantly outperforming in-domain RLVR baselines in efficiency and data requirements.