miHoYo unveils Gamer, a VLA foundation model for real-time game agents
Run Luo · hf · 2026-11-16
miHoYo's Honkai AI R&D team released Gamer, a generalist vision-language-action foundation model for long-horizon, real-time game agents in complex interactive environments.
- Continued pre-training on tens of thousands of hours of device-level keyboard/mouse trajectories spanning simulated games and embodied environments
- Sparse-thinking instruction tuning cuts redundant computation while preserving reasoning for complex decisions
- Policy trained with multi-turn RL for long-horizon interaction in both 2D UIs and 3D simulated worlds
More from Embodied
- WeituAI's streaming video brain scores 69.9 on OVBench, beating Gemini baseline by 11 points — 机器之心 · 2026-11-16
- Grid Robotics Proposes Agentic Robotics Paradigm Built on Embodied System 2 — Grid Robotics · 2026-11-16
- Shenzhen hosts APEC 2026, showcasing humanoid robots and its design-to-mass-production cycle — CyberRobooo · 2026-11-16
- Tongxin Intelligent raises hundreds of millions RMB to build AGI-native inference chips — 量子位 · 2026-11-16
- Qiming's Shen Jin: Safety is the final hurdle for PhysicalAI mass adoption — 创业邦 · 2026-11-16
- Analog chip AX100 tape-out solves matrix equations in under 100ns; humanoid capacity scales — 创业邦 · 2026-11-16