Yue Liu, Zhiyuan Hu, Flood Sung, Jiaheng Zhang, Bryan Hooi
KLong is a new LLM agent designed to tackle long-horizon tasks using a novel training method combining trajectory-splitting SFT and progressive RL, outperforming existing models on various benchmarks.
Researchers have developed KLong, an advanced AI model capable of handling complex tasks that require long-term planning and execution. The model is trained using a unique method that first prepares the model with basic abilities and then enhances its performance through progressive reinforcement learning. This approach allows KLong to effectively process long sequences of information, making it superior to other models in solving intricate problems. It has been shown to outperform other models on a variety of benchmarks, demonstrating its effectiveness and versatility.
