Unlocking Long-Horizon Agentic Search with Large-Scale End-to-End RL

Jiaxuan Gao, Wei Fu, Minyang Xie, Shusheng Xu, Chuyi He, Zhiyu Mei, Banghua Zhu, Yi Wu

Keywords: Agentic RL; Asynchronous RL; Search Agent

TL;DR: This paper introduces training expert-level search agents with large-scale RL. By using 128 turn limit and high-quality synthetic data, the agent learns complex long-horizon search strategies, reaching competitive results on frontier benchmarks.

Abstract: Recent advancements in LLM-based agents have demonstrated remarkable capabilities in handling knowledge-intensive tasks using external tools. One representative example is search agent. Existing open-source search agents heavily rely on advanced commercial LLMs: they either collect trajectories from the larger, stronger models for supervised fine-tuning or directly use them as specialized tools. In this work, we develop ASearcher, a single-model search agent purely trained by reinforcement learning (RL) without using any commercial APIs for data or tools. Based on an RL-trained QwQ-32B model, ASearcher is capable of conducting complex reasoning, such as uncertainty analysis and conflict verification, and achieve comparable performances to commercial search agents. There are two key techniques to unlock such long-horizon information-seeking abilities: first, we design a two-staged agentic process to synthesize high-quality QA pairs as the training data for RL; second, we conduct large-scale long-horizon RL, allowing the agent to take up to 128 actions per rollout for sufficient exploration. In particular, after RL training, ASearcher achieved scores of GAIA 58.1, xBench 51.1, and Frames 74.5 using only basic search tools. Furthermore, ASearcher also demonstrates strong zero-shot transferability: ASearcher can be further augmented with an additional summary tool, which is supported by DeepSeek-V3, and test-time scaling, which aggregates the answer from 16 parallel rollouts. With both zero-shot enhancements, the performances of ASearcher further rise to 71.8, 75.0, and 83.4, respectively, outperforming OpenAI DeepResearch and Kimi-Researcher, suggesting the great potential of RL scaling for agentic tasks. We release all the code and data at an anonymous link. The model will be released after the review process.

Primary Area: foundation or frontier models, including LLMs

Submission Number: 10590