General-Reasoner: Advancing LLM Reasoning Across All Domains

TL;DR

This paper introduces General-Reasoner, a training paradigm that enhances large language models' reasoning across diverse domains by leveraging a new dataset and a generative answer verifier, leading to improved performance on multiple benchmarks.

Contribution

The paper presents a novel training framework with a large, diverse dataset and a generative verifier, enabling LLM reasoning across broad disciplines beyond math and coding.

Findings

Outperforms existing methods on 12 diverse benchmarks.

Achieves robust reasoning in physics, chemistry, finance, and electronics.

Maintains high effectiveness in mathematical reasoning tasks.

Abstract

Reinforcement learning (RL) has recently demonstrated strong potential in enhancing the reasoning capabilities of large language models (LLMs). Particularly, the "Zero" reinforcement learning introduced by Deepseek-R1-Zero, enables direct RL training of base LLMs without relying on an intermediate supervised fine-tuning stage. Despite these advancements, current works for LLM reasoning mainly focus on mathematical and coding domains, largely due to data abundance and the ease of answer verification. This limits the applicability and generalization of such models to broader domains, where questions often have diverse answer representations, and data is more scarce. In this paper, we propose General-Reasoner, a novel training paradigm designed to enhance LLM reasoning capabilities across diverse domains. Our key contributions include: (1) constructing a large-scale, high-quality dataset of questions with verifiable answers curated by web crawling, covering a wide range of disciplines; and (2) developing a generative model-based answer verifier, which replaces traditional rule-based verification with the capability of chain-of-thought and context-awareness. We train a series of models and evaluate them on a wide range of datasets covering wide domains like physics, chemistry, finance, electronics etc. Our comprehensive evaluation across these 12 benchmarks (e.g. MMLU-Pro, GPQA, SuperGPQA, TheoremQA, BBEH and MATH AMC) demonstrates that General-Reasoner outperforms existing baseline methods, achieving robust and generalizable reasoning performance while maintaining superior effectiveness in mathematical reasoning tasks.