Question Answering
Safetensors
qwen3
MrLight's picture
Update README.md
31aa69a verified
metadata
license: apache-2.0
datasets:
  - TIGER-Lab/WebInstruct-verified
base_model:
  - Qwen/Qwen3-14B-Base
pipeline_tag: question-answering

General-Reasoner: Advancing LLM Reasoning Across All Domains

馃捇 Code | 馃搫 Paper | 馃搳 Dataset | 馃 Model | 馃寪 Project Page

Overview

General-Reasoner Teaser

Figure: Effectiveness of General-Reasoner trained with diverse verifiable reasoning questions using model-based verifier compared to baseline methods on various reasoning tasks.

General-Reasoner is a training paradigm for large language models (LLMs), designed to robustly enhance reasoning abilities across diverse domains鈥攏ot just mathematics and coding, but also physics, chemistry, finance, humanities, and more.

Key features:

  • Zero RL Training: Direct reinforcement learning from base LLMs, bypassing intermediate supervised stages.
  • Diverse Reasoning Data: 230K+ high-quality, verifiable questions sourced from the web and filtered for answer verifiability across disciplines.
  • Model-Based Verifier: Compact 1.5B generative verifier model for context-aware, chain-of-thought answer validation, outperforming traditional rule-based methods.

This specific model is the General-Reasoner variant trained based on Qwen3-14B-Base.

Main Results

General-Reasoner outperforms base and supervised models on a variety of reasoning benchmarks, demonstrating robust generalization across domains:

Main Results

Citation

If you feel our work is helpful, please cite:

@article{general-reasoner,
  title={{G}eneral-{R}easoner: Advancing LLM Reasoning Across All Domains},
  author={Xueguang Ma and Qian Liu and Dongfu Jiang and Ge Zhang and Zejun Ma and Wenhu Chen},
  year={2025},
  journal={arXiv:2505.14652},
  url={https://arxiv.org/abs/2505.14652}
}