Holistically Guided Monte Carlo Tree Search for Intricate Information Seeking

TL;DR

This paper presents HG-MCTS, a novel search method combining holistic guidance and Monte Carlo tree search to improve complex information retrieval, ensuring comprehensive and accurate responses in multi-step web search tasks.

Contribution

The paper introduces a new HG-MCTS framework that integrates an adaptive checklist and multi-perspective reward modeling for improved intricate information seeking.

Findings

HG-MCTS outperforms existing methods in accuracy and coverage.

The approach effectively balances local exploration and global guidance.

Experimental results show enhanced knowledge collection and response quality.

Abstract

In the era of vast digital information, the sheer volume and heterogeneity of available information present significant challenges for intricate information seeking. Users frequently face multistep web search tasks that involve navigating vast and varied data sources. This complexity demands every step remains comprehensive, accurate, and relevant. However, traditional search methods often struggle to balance the need for localized precision with the broader context required for holistic understanding, leaving critical facets of intricate queries underexplored. In this paper, we introduce an LLM-based search assistant that adopts a new information seeking paradigm with holistically guided Monte Carlo tree search (HG-MCTS). We reformulate the task as a progressive information collection process with a knowledge memory and unite an adaptive checklist with multi-perspective reward modeling in MCTS. The adaptive checklist provides explicit sub-goals to guide the MCTS process toward comprehensive coverage of complex user queries. Simultaneously, our multi-perspective reward modeling offers both exploration and retrieval rewards, along with progress feedback that tracks completed and remaining sub-goals, refining the checklist as the tree search progresses. By striking a balance between localized tree expansion and global guidance, HG-MCTS reduces redundancy in search paths and ensures that all crucial aspects of an intricate query are properly addressed. Extensive experiments on real-world intricate information seeking tasks demonstrate that HG-MCTS acquires thorough knowledge collections and delivers more accurate final responses compared with existing baselines.