Mars Benchmark

SOCIAL MEDIA DESCRIPTION TAG TAG

Mars Benchmark Mars Situated Inductive Reasoning in an Open-World Environment NeurIPS Datasets and Benchmark 2024 Xiaojuan Tang 1,2 , Jiaqi Li 2 , Yitao Liang 1,2 Song-chun Zhu 1,2 , Muhan Zhang 1,2, , Zilong Zheng 2, 1 Peking Univeristy 2 Beijing Institute for General Artificial Intelligence Paper Code arXiv 🏆 Leaderboard Your video here Aliquam vitae elit ullamcorper tellus egestas pellentesque. Ut lacus tellus, maximus vel lectus at, placerat pretium mi. Maecenas dignissim tincidunt vestibulum. Sed consequat hendrerit nisl ut maximus. --> Default Default: --> Follow behaviors in Crafter. M

saved by

• Eva L

related reading

• [2504.15785] WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agentsarxiv.org
• DeepSeek-R1arxiv.org
• the-illusion-of-thinking.pdfml-site.cdn-apple.com
• Language Models can Solve Computer Tasksarxiv.org
• Reasoning in General Domains without Verifiersarxiv.org
• A Taxonomy of RL Environments for LLM Agentsleehanchung.github.io
• [2603.21972] Demystifying Reinforcement Learning for Long-Horizon Tool-Using Agents: A Comprehensive Recipearxiv.org
• Theory of Mind for Multi-Agent Collaboration via Large Language Modelsarxiv.org
• combinatorial reasoning environments for LLMs and RLdjdumpling.github.io
• [2605.20873] PlanningBench: Generating Scalable and Verifiable Planning Data for Evaluating and Training Large Language Modelsarxiv.org
• Reasoning Models Reason Well, Until They Don'tarxiv.org
• [2606.10346] Reasoning or Memorization? Direction-Aware Diversity Exploration in LLM Reinforcement Learningarxiv.org