Robots that learn on the job: AgiBot tests reinforcement learning in real-world manufacturing.
Updated
January 8, 2026 6:34 PM
A humanoid robot works on a factory line, showcasing advanced automation in real-world production. PHOTO: AGIBOT
Shanghai-based robotics firm AgiBot has taken a major step toward bringing artificial intelligence into real manufacturing. The company announced that its Real-World Reinforcement Learning (RW-RL) system has been successfully deployed on a pilot production line run in partnership with Longcheer Technology. It marks one of the first real applications of reinforcement learning in industrial robotics.
The project represents a key shift in factory automation. For years, precision manufacturing has relied on rigid setups: robots that need custom fixtures, intricate programming and long calibration cycles. Even newer systems combining vision and force control often struggle with slow deployment and complex maintenance. AgiBot’s system aims to change that by letting robots learn and adapt on the job, reducing the need for extensive tuning or manual reconfiguration.
The RW-RL setup allows a robot to pick up new tasks within minutes rather than weeks. Once trained, the system can automatically adjust to variations, such as changes in part placement or size tolerance, maintaining steady performance throughout long operations. When production lines switch models or products, only minor hardware tweaks are needed. This flexibility could significantly cut downtime and setup costs in industries where rapid product turnover is common.
The system’s main strengths lie in faster deployment, high adaptability and easier reconfiguration. In practice, robots can be retrained quickly for new tasks without needing new fixtures or tools — a long-standing obstacle in consumer electronics production. The platform also works reliably across different factory layouts, showing potential for broader use in complex or varied manufacturing environments.
Beyond its technical claims, the milestone demonstrates a deeper convergence between algorithmic intelligence and mechanical motion.Instead of being tested only in the lab, AgiBot’s system was tried in real factory settings, showing it can perform reliably outside research conditions.
This progress builds on years of reinforcement learning research, which has gradually pushed AI toward greater stability and real-world usability. AgiBot’s Chief Scientist Dr. Jianlan Luo and his team have been at the forefront of that effort, refining algorithms capable of reliable performance on physical machines. Their work now underpins a production-ready platform that blends adaptive learning with precision motion control — turning what was once a research goal into a working industrial solution.
Looking forward, the two companies plan to extend the approach to other manufacturing areas, including consumer electronics and automotive components. They also aim to develop modular robot systems that can integrate smoothly with existing production setups.
Keep Reading
How a Korean biotech startup is using AI to move drug discovery from trial-and-error to precision design
A close up of a protein structure model. PHOTO: UNSPLASH
For decades, drug discovery has relied on trial and error, with scientists testing thousands of molecules to find one that works. Galux, a South Korean biotech startup, is changing that by using AI to design proteins from scratch. This method, called “de novo” design, makes it possible to build precise new therapies instead of searching through existing ones.
The company recently announced a US$29 million Series B funding round, bringing its total capital to US$47 million.This significant investment attracted a substantial roster of institutional backers, including the Korea Development Bank (KDB), Yuanta Investment, SL Investment and NCORE Ventures. These firms joined existing investors such as InterVest, DAYLI Partners and PATHWAY Investment, as well as new participants including SneakPeek Investments, Korea Investment & Securities and Mirae Asset Securities.
At the core of the company’s work is a platform called GaluxDesign. Unlike many AI tools that only predict how existing proteins fold, this system uses deep learning and physics to create entirely new therapeutic antibodies. This “from scratch” approach lets the team go after so-called “undruggable” proteins. These are targets that traditional small-molecule drugs can’t reach because they lack clear binding pockets. By designing proteins to fit these complex shapes, Galux aims to unlock treatments that have stayed out of reach for decades. And that’s exactly why investors are paying attention.
The pharmaceutical industry is actively looking for faster and more efficient ways to develop new drugs, and Galux is built for exactly that. The company connects its AI platform directly to its own wet lab, where designs can be tested in real time. Each result feeds straight back into the system, sharpening the next round of models. This continuous loop speeds up discovery and improves precision at every step. It’s also why partners like Celltrion, LG Chem and Boehringer Ingelheim are already working with Galux.
Galux is no longer just trying to make drugs that stick to a target. The company now wants its AI to design medicines that actually work in the body and can be made at scale. In simple terms, a drug has to do more than bind to a disease—it must be stable, safe and strong enough to change how the illness behaves. Galux is moving into tougher targets such as ion channels and GPCRs. These play key roles in heart function and sensory signals. Ultimately, the goal is to show that AI-driven design can turn complex biology into real treatments. And instead of hunting blindly for a solution, the team is building exactly what they need.