TIPS-Qwen3-4B-Thinking-2507-Agent
This TIPS agent checkpoint is initialized from Qwen/Qwen3-4B-Thinking-2507 and trained with outcome-only GRPO. It is a generative reward model for step-level verification and first-error localization in multi-turn agent trajectories.
Training data and code are available at https://huggingface.co/datasets/XingYing-stack/TIPS-Training-Data and https://github.com/RUCBM/TIPS.
Use the prompt templates and evaluation scripts in the TIPS repository. This checkpoint is intended for reward modeling and process verification rather than general-purpose chat.
Built upon verl and released under Apache-2.0.