Despite the proliferation of powerful agentic models, the lack of critical post-training details hinders the development of strong counterparts in the open-source community. In this study, we present a comprehensive and fully open-source pipeline for training a high-performance agentic model for interacting with external tools and environments, named Klear-Qwen3-AgentForge, starting from the Qwen3-8B base model. We design effective supervised fine-tuning (SFT) with synthetic data followed by multi-turn reinforcement learning (RL) to unlock the potential for multiple diverse agentic tasks. We perform exclusive experiments on various agentic benchmarks in both tool use and coding domains. Klear-Qwen3-AgentForge-8B achieves state-of-the-art performance among LLMs of similar size and remains competitive with significantly larger models.
@article{arxiv.2511.05951,
title = {Klear-AgentForge: Forging Agentic Intelligence through Posttraining Scaling},
author = {Qi Wang and Hongzhi Zhang and Jia Fu and Kai Fu and Yahui Liu and Tinghai Zhang and Chenxi Sun and Gangwei Jiang and Jingyi Tang and Xingguang Ji and Yang Yue and Jingyuan Zhang and Fuzheng Zhang and Kun Gai and Guorui Zhou},
journal= {arXiv preprint arXiv:2511.05951},
year = {2025}
}