Parallel thinking expands exploration breadth, complementing the deep exploration of information-seeking (IS) agents to further enhance problem-solving capability. However, conventional parallel thinking faces two key challenges in this setting: inefficiency from repeatedly rolling out from scratch, and difficulty in integrating long-horizon reasoning trajectories during answer generation, as limited context capacity prevents full consideration of the reasoning process. To address these issues, we propose ParallelMuse, a two-stage paradigm designed for deep IS agents. The first stage, Functionality-Specified Partial Rollout, partitions generated sequences into functional regions and performs uncertainty-guided path reuse and branching to enhance exploration efficiency. The second stage, Compressed Reasoning Aggregation, exploits reasoning redundancy to losslessly compress information relevant to answer derivation and synthesize a coherent final answer. Experiments across multiple open-source agents and benchmarks demonstrate up to 62% performance improvement with a 10--30% reduction in exploratory token consumption.
@article{arxiv.2510.24698,
title = {ParallelMuse: Agentic Parallel Thinking for Deep Information Seeking},
author = {Baixuan Li and Dingchu Zhang and Jialong Wu and Wenbiao Yin and Zhengwei Tao and Yida Zhao and Liwen Zhang and Haiyang Shen and Runnan Fang and Pengjun Xie and Jingren Zhou and Yong Jiang},
journal= {arXiv preprint arXiv:2510.24698},
year = {2025}
}