interactive-environments

MemCo提出了一种以记忆为中心的协作框架，通过维护互补的局部与全局记忆空间，帮助LLM智能体在未见过的交互环境中实现更好的泛化，实验表明其在交互式决策基准上提升了任务成功率并减少了冗余探索。

AgentGarten is a framework that couples simulators and game engines with a shared neural renderer to build real-time interactive environments where agents learn from visual observations and distill experience into inherited playbooks, achieving major learning efficiency gains over conventional RL with just 4 rounds of experience.

EvoPolicyGym is a benchmark for evaluating how autonomous agents iteratively improve policies through feedback in interactive environments, with GPT-5.5 achieving top performance.

This paper systematically reviews text world models for LLM-based agents, covering foundations, construction paradigms, applications in planning and training, and evaluation methods.

WorldCraft extends interactive video world models to enable object-level trajectory control while maintaining camera navigation capabilities through specialized control pipelines.