RitvikPW
Abstract
Aryabhata 1.0, a compact math reasoning model, outperforms existing models on educational exams and benchmarks by using supervised fine-tuning, reinforcement learning with verifiable rewards, and novel exploration strategies.
We present Aryabhata 1.0, a compact 7B parameter math reasoning model optimized for the Indian academic exam, the Joint Entrance Examination (JEE). Despite rapid progress in large language models (LLMs), current models often remain unsuitable for educational use. Aryabhata 1.0 is built by merging strong open-weight reasoning models, followed by supervised fine-tuning (SFT) with curriculum learning on verified chain-of-thought (CoT) traces curated through best-of-n rejection sampling. To further boost performance, we apply reinforcement learning with verifiable rewards (RLVR) using A2C objective with group-relative advantage estimation alongwith novel exploration strategies such as Adaptive Group Resizing and Temperature Scaling. Evaluated on both in-distribution (JEE Main 2025) and out-of-distribution (MATH, GSM8K) benchmarks, Aryabhata outperforms existing models in accuracy and efficiency, while offering pedagogically useful step-by-step reasoning. We release Aryabhata as a foundation model to advance exam-centric, open-source small language models. This marks our first open release for community feedback (https://huggingface.co/PhysicsWallahAI/Aryabhata-1.0{Aryabhata 1.0 on Hugging Face}); PW is actively training future models to further improve learning outcomes for students.
Community
Aryabhata 1.0 is a 7B parameter small language model for mathematics developed by Physics Wallah AI Research, optimized for high-stakes Indian competitive exams like JEE Mains. Despite its compact size, Aryabhata 1.0 achieves state-of-the-art performance on exam-centric reasoning tasks with impressive token efficiency and low inference cost.
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- JT-Math: A Multi-Stage Framework for Advanced Mathematical Reasoning in Large Language Models (2025)
- Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning (2025)
- Logit Arithmetic Elicits Long Reasoning Capabilities Without Training (2025)
- Omni-Think: Scaling Cross-Domain Generalization in LLMs via Multi-Task RL with Hybrid Rewards (2025)
- The Synergy Dilemma of Long-CoT SFT and RL: Investigating Post-Training Techniques for Reasoning VLMs (2025)
- StructVRM: Aligning Multimodal Reasoning with Structured and Verifiable Reward Models (2025)
- Multimodal Mathematical Reasoning with Diverse Solving Perspective (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 1
Datasets citing this paper 0
No dataset linking this paper