FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction Paper • 2508.11987 • Published Aug 16, 2025 • 71
InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency Paper • 2508.18265 • Published Aug 25, 2025 • 212
Less is More: Recursive Reasoning with Tiny Networks Paper • 2510.04871 • Published Oct 6, 2025 • 506
