This is the multimodal model released with the paper Context-Aware RL for Agentic and Multimodal LLMs.

It is fine-tuned from Qwen3-VL-8B-Instruct using ContextRL, a context-aware reinforcement learning method that augments standard GRPO with an auxiliary context-selection objective to improve fine-grained visual grounding.

Across 12 diverse multimodal benchmarks, ContextRL improves over the standard GRPO baseline by +1.6 points on average, while improving every individual benchmark.

This model follows the same interface as Qwen3-VL-8B-Instruct and can be loaded with transformers. Training and evaluation code, data construction pipelines, and detailed configurations are available in the repository:

👉 https://github.com/xupy2003/ContextAwareRL

Please refer to the repo's README for environment setup, inference scripts, and reproduction instructions.