AGIBOT publishes LWD fleet-scale reinforcement learning for deployed generalist robots - 2026-04-30 - Research Publication - AGIBOT Finch published Learning while Deploying as a fleet-scale offline-to-online reinforcement learning framework for continual post-training of generalist VLA policies. The official page evaluates LWD on a fleet of… - source: finch.agibot.com
X2-N paper presents transformable wheel-legged humanoid based on the AgiBot X2 line - 2026-04-23 - Research Publication - The X2-N paper presents a high-DoF transformable robot that can operate in both humanoid and wheel-legged forms. The authors pair the hardware with a reinforcement-learning whole-body controller for locomotion… - source: arxiv.org
AgiBot releases AGIBOT WORLD 2026 real-world embodied AI dataset - 2026-04-07 - Research Publication - AgiBot released AGIBOT WORLD 2026, a real-world embodied AI dataset intended to support multiple research directions in embodied intelligence. According to the dataset card, the data comes from real commercial, home, and… - source: huggingface.co
AGIBOT publishes SOP framework for fleet-scale online VLA post-training - 2026-01-06 - Research Publication - AGIBOT Research introduced SOP as a scalable online post-training framework for Vision-Language-Action models running across robot fleets in the real world. The official writeup says SOP enables online updates across… - source: agibot.com
AGIBOT publishes UniFact embodied reasoning and action framework - 2026-01-01 - Research Publication - AGIBOT Finch published UniFact, presenting GenieReasoner and the FACT action tokenizer to unify embodied reasoning and robotic action inside a single autoregressive transformer. The official page positions the work as a… - source: finch.agibot.com
AGIBOT publishes Act2Goal goal-conditioned policy framework - 2026-01-01 - Research Publication - AGIBOT Finch published Act2Goal as a unified autoregressive framework that jointly pre-trains vision-language reasoning and robotic action generation. The official research page highlights strong simulated benchmark gains… - source: finch.agibot.com
WholeBodyVLA paper validates large-space loco-manipulation on AgiBot X2 - 2025-12-11 - Research Publication - WholeBodyVLA introduces a unified latent VLA framework for whole-body humanoid loco-manipulation. The work is validated through experiments on AgiBot X2, reporting stronger performance than prior baselines across… - source: arxiv.org
AgiBot brings G2 Max to JD Logistics - 2026-07-18 - The wheeled dual-arm robot is intended to automate depalletising, tote movement and palletising inside JD warehouses.