InternBootcamp Technical Report: Boosting LLM Reasoning with Verifiable Task Scaling

TL;DR

InternBootcamp is an open-source framework with over 1000 diverse reasoning tasks for LLMs, enabling automated data generation, verification, and significant performance improvements through task scaling.

Contribution

We introduce InternBootcamp, a comprehensive, automated task environment framework that enhances LLM reasoning research and demonstrates the benefits of large-scale task scaling.

Findings

Training with InternBootcamp significantly improves model performance.

Including more diverse tasks leads to substantial reasoning ability gains.

The 32B model achieves state-of-the-art results on Bootcamp-EVAL.

Abstract

Large language models (LLMs) have revolutionized artificial intelligence by enabling complex reasoning capabilities. While recent advancements in reinforcement learning (RL) have primarily focused on domain-specific reasoning tasks (e.g., mathematics or code generation), real-world reasoning scenarios often require models to handle diverse and complex environments that narrow-domain benchmarks cannot fully capture. To address this gap, we present InternBootcamp, an open-source framework comprising 1000+ domain-diverse task environments specifically designed for LLM reasoning research. Our codebase offers two key functionalities: (1) automated generation of unlimited training/testing cases with configurable difficulty levels, and (2) integrated verification modules for objective response evaluation. These features make InternBootcamp fundamental infrastructure for RL-based model optimization, synthetic data generation, and model evaluation. Although manually developing such a framework with enormous task coverage is extremely cumbersome, we accelerate the development procedure through an automated agent workflow supplemented by manual validation protocols, which enables the task scope to expand rapidly. % With these bootcamps, we further establish Bootcamp-EVAL, an automatically generated benchmark for comprehensive performance assessment. Evaluation reveals that frontier models still underperform in many reasoning tasks, while training with InternBootcamp provides an effective way to significantly improve performance, leading to our 32B model that achieves state-of-the-art results on Bootcamp-EVAL and excels on other established benchmarks. In particular, we validate that consistent performance gains come from including more training tasks, namely \textbf{task scaling}, over two orders of magnitude, offering a promising route towards capable reasoning generalist.