LiteResearcher: A Scalable Agentic RL Training Framework for Deep Research Agent

TL;DR

LiteResearcher introduces a scalable RL training framework using a virtual world to improve deep research agents, outperforming larger models on key benchmarks.

Contribution

It presents a novel virtual world-based RL training framework that enhances scalability and performance of research agents beyond existing methods.

Findings

LiteResearcher-4B achieves 71.3% on GAIA and 78.0% on Xbench.

The framework enables small agents to outperform larger models.

Scalable RL training is shown to be crucial for deep research agents.

Abstract

Reinforcement Learning (RL) has emerged as a powerful training paradigm for LLM-based agents. However, scaling agentic RL for deep research remains constrained by two coupled challenges: hand-crafted synthetic data fails to elicit genuine real-world search capabilities, and real-world search dependency during RL training introduces instability and prohibitive cost, which limits the scalability of Agentic RL. LiteResearcher is a training framework that makes Agentic RL scalable: by constructing a lite virtual world that mirrors real-world search dynamics, we enable a continuously improving training recipe that empowers a tiny search agent to outperform large-scale open-source and commercial models (e.g., Tongyi DeepResearch and Claude-4.5 Sonnet). Specifically, on common benchmarks such as GAIA and Xbench, our LiteResearcher-4B achieves open-source state-of-the-art results of 71.3% and 78.0% respectively, demonstrating that scalable RL training is a key enabler for Deep Research Agents.