Survey: Towards Agentic Robots organizes the field into 17 categories across four domains
Chonghan Qin · hf · 2026-10-15
A unified survey from CUHK MMLab, Fudan, Tsinghua, Zhejiang, Sun Yat-sen and others (Dahua Lin, Yu-Gang Jiang, Xiangyu Yue) charts the shift toward agentic robots.
- Robot intelligence is moving beyond low-level action prediction to foundation-model-driven, goal-directed orchestration of data collection, training, planning, and real-world execution, with agents that reason over instructions, correct errors autonomously, and adapt strategies.
- The paper traces the path from robot policies to agentic systems (VLA models, world models, world-action models) and organizes research into 17 categories across four domains: Model, Data, Environment, and Harness.
- It closes with open challenges and future directions for capable, reliable, adaptive agentic robots.
More from Embodied
- MimicX refines humanoid tracking with policy-in-the-loop feedback: 25.7% error cut — Shuaijun Liu · 2026-10-15
- Gracia's new world model targets Real2Sim2Real and Physical AI — jonstephens85 · 2026-10-15
- Niantic Spatial built VPS on Pokémon Go imagery; a dev already prototyped it solo — jonstephens85 · 2026-10-15
- RoboParty launches RP1, a fully open-source full-stack humanoid robotics platform — GuanyaShi · 2026-10-15
- HumanoidToolBench benchmarks humanoid tool use from selection to mobile execution on real Unitree G1 — snupilab · 2026-10-15
- RegisterWAM adds learnable registers to world action models, hitting 81.6% on LIBERO-Plus and 93% on RoboTwin 2.0 — AutoLab-SJTU · 2026-10-15