Instructions to use XingYing-stack/FocalRL-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use XingYing-stack/FocalRL-4B with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("XingYing-stack/FocalRL-4B") model = AutoModelForMultimodalLM.from_pretrained("XingYing-stack/FocalRL-4B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
FocalRL-4B
FocalRL-4B is a deep research agent based on Qwen3.5-4B, trained with FocalRL for long-horizon web research. It combines full-trajectory outcome rewards with rubric-scored local action repair to improve credit assignment across extended search and browsing trajectories.
This repository provides FocalRL-4B model weights in Hugging Face Transformers format.
FocalRL compared with an SFT baseline and GRPO on Qwen3.5-9B Deep Research, and with the base model and GRPO on Qwen3.5-4B SWE-bench Verified. BrowseComp in this figure uses the first 200 tasks.
Accuracy on the full BrowseComp benchmark (1,266 tasks) versus total model parameters, including FocalRL-4B (41.3%) and FocalRL-9B (57.9%).
Focal Credit Assignment
FocalRL trains long-horizon agents through local action repair. It collects full trajectories, identifies consequential errors in failed attempts, and branches from the corresponding pre-error states. Short continuations are scored against task-specific repair rubrics, and the policy is optimized jointly with full-trajectory outcome rewards and local repair rewards.
Each local continuation spans at most five assistant turns. Repair rewards are 0 for repeating the identified error, 0.5 for avoiding it, and 1 for avoiding it and making the specified correction.
Performance
Accuracy (%) across five Deep Research benchmarks, compared with 4B search agents:
| Model | Parameters | BrowseComp | BrowseComp-ZH | xbench-2505 | xbench-2510 | GAIA-text |
|---|---|---|---|---|---|---|
| DR-Venus | 4B | 29.1 | 37.7 | 74.7 | 40.7 | 64.4 |
| AgentCPM-Explore | 4B | 24.1 | 29.1 | 70.0 | 34.0 | 63.9 |
| ABSeeker | 4B | 37.3 | 39.1 | 77.0 | 46.0 | 81.6 |
| FocalRL-4B | 4B | 41.3 | 46.1 | 78.0 | 48.0 | 82.5 |
Bold and underlined scores indicate the best and second-best results in the 4B category.
Code and Usage
Use this checkpoint as the policy model with the FocalRL Deep Research agent. The agent uses web search and page fetching to gather evidence, with browser summarization for fetched content.
- Deep Research setup: search, browsing, summarization, and answer judging.
- Training guide: environment setup, checkpoint conversion, and FocalRL training.
- Agent implementation.
License
Apache-2.0.
- Downloads last month
- 5