Intelligent-Internet/II-Search-CIR-4B is a 4 billion parameter language model developed by Intelligent Internet, based on the Qwen3-4B architecture. It introduces Code-Integrated Reasoning (CIR), a novel approach that allows the model to generate and execute code blocks for enhanced tool interaction and programmatic reasoning. This model is specifically fine-tuned for information-seeking tasks, excelling in web search and data processing by leveraging external resources through code.
Loading preview...
II-Search-CIR-4B: Code-Integrated Reasoning for Enhanced Search
II-Search-CIR-4B is a 4-billion parameter model from Intelligent Internet, built upon the Qwen3-4B architecture. It significantly advances tool interaction through its unique Code-Integrated Reasoning (CIR) methodology. Unlike traditional tool-calling paradigms, CIR enables the model to generate and execute Python code blocks, allowing for programmatic interaction with external resources.
Key Capabilities:
- Code-Integrated Reasoning (CIR): The model generates code blocks (e.g.,
web_search,web_visit) to interact with external tools, process information, and reason programmatically. - Enhanced Information Seeking: Specifically fine-tuned to excel in tasks requiring external information retrieval and processing.
- Improved Performance: Outperforms its base model (Qwen3-4B) and other small-sized search-specialized models like Jan-4B and WebSailor-3B on benchmarks such as Google Frames and Seal_0.
Training Methodology:
The model underwent a two-stage training process:
- SFT Fine-tuning: Initial Supervised Fine-Tuning on a curated dataset to efficiently produce the required code format.
- DAPO Optimization: Further optimized using DAPO (Direct Advantage Policy Optimization) on a hard-reasoning dataset to boost performance.
Good for:
- Applications requiring advanced web search and information synthesis.
- Developing agents that need to programmatically interact with external APIs or data sources.
- Tasks where reasoning over retrieved information is critical, beyond simple retrieval.
For more details on the training methodology and datasets, refer to the II-Search-4B blog post and the released datasets: II-Search-CIR-SFT and II-Search-RL.