Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers Paper • 2506.23918 • Published Jun 30 • 89
A Survey of Context Engineering for Large Language Models Paper • 2507.13334 • Published Jul 17 • 259
GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning Paper • 2507.01006 • Published Jul 1 • 246
BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games Paper • 2411.13543 • Published Nov 20, 2024 • 19
Artificial Generals Intelligence: Mastering Generals.io with Reinforcement Learning Paper • 2507.06825 • Published Jul 9 • 2