| See and Think: Embodied Agent in Virtual Environment | Nov 26, 2023 | MinecraftQuestion Answering | —Unverified | 0 |
| JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Models | Nov 10, 2023 | Minecraft | —Unverified | 0 |
| Active Reasoning in an Open-World Environment | Nov 3, 2023 | Instruction FollowingMinecraft | —Unverified | 0 |
| Convolutional State Space Models for Long-Range Spatiotemporal Modeling | Oct 30, 2023 | MinecraftState Space Models | CodeCode Available | 1 |
| Probabilistic Modeling of Human Teams to Infer False Beliefs | Oct 19, 2023 | AI AgentMinecraft | —Unverified | 0 |
| Progressively Efficient Learning | Oct 13, 2023 | Decision MakingImitation Learning | —Unverified | 0 |
| LLaMA Rider: Spurring Large Language Models to Explore the Open World | Oct 13, 2023 | Decision MakingMinecraft | —Unverified | 0 |
| GROOT: Learning to Follow Instructions by Watching Gameplay Videos | Oct 12, 2023 | DecoderInstruction Following | —Unverified | 0 |
| Towards Evaluating Generalist Agents: An Automated Benchmark in Open World | Oct 12, 2023 | BenchmarkingDiversity | CodeCode Available | 1 |
| Octopus: Embodied Vision-Language Programmer from Environmental Feedback | Oct 12, 2023 | BenchmarkingCode Generation | CodeCode Available | 2 |
