@inproceedings{chen-etal-2025-search,
title = "Search-in-Context: Efficient Multi-Hop {QA} over Long Contexts via {M}onte {C}arlo Tree Search with Dynamic {KV} Retrieval",
author = "Chen, Jiabei and
Liu, Guang and
He, Shizhu and
Luo, Kun and
Xu, Yao and
Zhao, Jun and
Liu, Kang",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.1356/",
doi = "10.18653/v1/2025.findings-acl.1356",
pages = "26443--26455",
ISBN = "979-8-89176-256-5",
abstract = "Recent advancements in large language models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks, such as math problem-solving and code generation. However, multi-hop question answering (MHQA) over long contexts, which demands both robust knowledge-intensive reasoning and efficient processing of lengthy documents, remains a significant challenge. Existing approaches often struggle to balance these requirements, either neglecting explicit reasoning or incurring expensive computational costs due to full-attention mechanisms over long contexts. To address this, we propose **Search-in-Context (SIC)**, a novel framework that integrates Monte Carlo Tree Search (MCTS) with dynamic key-value (KV) retrieval to enable iterative, context-aware reasoning. SIC dynamically retrieves critical KV pairs (e.g., 4K tokens) at each step, prioritizing relevant evidence while mitigating the ``lost in the middle'' problem. Furthermore, the paper introduces a Process-Reward Model (PRM) trained on auto-labeled data to guide the MCTS process with stepwise rewards, promoting high-quality reasoning trajectories without manual annotation. Experiments on three long-context MHQA benchmarks (HotpotQA, 2WikiMultihopQA, MuSiQue) and a counterfactual multi-hop dataset demonstrate SIC{'}s superiority, achieving state-of-the-art performance while significantly reducing computational overhead."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2025-search">
<titleInfo>
<title>Search-in-Context: Efficient Multi-Hop QA over Long Contexts via Monte Carlo Tree Search with Dynamic KV Retrieval</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiabei</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shizhu</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kun</namePart>
<namePart type="family">Luo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yao</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-256-5</identifier>
</relatedItem>
<abstract>Recent advancements in large language models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks, such as math problem-solving and code generation. However, multi-hop question answering (MHQA) over long contexts, which demands both robust knowledge-intensive reasoning and efficient processing of lengthy documents, remains a significant challenge. Existing approaches often struggle to balance these requirements, either neglecting explicit reasoning or incurring expensive computational costs due to full-attention mechanisms over long contexts. To address this, we propose **Search-in-Context (SIC)**, a novel framework that integrates Monte Carlo Tree Search (MCTS) with dynamic key-value (KV) retrieval to enable iterative, context-aware reasoning. SIC dynamically retrieves critical KV pairs (e.g., 4K tokens) at each step, prioritizing relevant evidence while mitigating the “lost in the middle” problem. Furthermore, the paper introduces a Process-Reward Model (PRM) trained on auto-labeled data to guide the MCTS process with stepwise rewards, promoting high-quality reasoning trajectories without manual annotation. Experiments on three long-context MHQA benchmarks (HotpotQA, 2WikiMultihopQA, MuSiQue) and a counterfactual multi-hop dataset demonstrate SIC’s superiority, achieving state-of-the-art performance while significantly reducing computational overhead.</abstract>
<identifier type="citekey">chen-etal-2025-search</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.1356</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.1356/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>26443</start>
<end>26455</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Search-in-Context: Efficient Multi-Hop QA over Long Contexts via Monte Carlo Tree Search with Dynamic KV Retrieval
%A Chen, Jiabei
%A Liu, Guang
%A He, Shizhu
%A Luo, Kun
%A Xu, Yao
%A Zhao, Jun
%A Liu, Kang
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F chen-etal-2025-search
%X Recent advancements in large language models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks, such as math problem-solving and code generation. However, multi-hop question answering (MHQA) over long contexts, which demands both robust knowledge-intensive reasoning and efficient processing of lengthy documents, remains a significant challenge. Existing approaches often struggle to balance these requirements, either neglecting explicit reasoning or incurring expensive computational costs due to full-attention mechanisms over long contexts. To address this, we propose **Search-in-Context (SIC)**, a novel framework that integrates Monte Carlo Tree Search (MCTS) with dynamic key-value (KV) retrieval to enable iterative, context-aware reasoning. SIC dynamically retrieves critical KV pairs (e.g., 4K tokens) at each step, prioritizing relevant evidence while mitigating the “lost in the middle” problem. Furthermore, the paper introduces a Process-Reward Model (PRM) trained on auto-labeled data to guide the MCTS process with stepwise rewards, promoting high-quality reasoning trajectories without manual annotation. Experiments on three long-context MHQA benchmarks (HotpotQA, 2WikiMultihopQA, MuSiQue) and a counterfactual multi-hop dataset demonstrate SIC’s superiority, achieving state-of-the-art performance while significantly reducing computational overhead.
%R 10.18653/v1/2025.findings-acl.1356
%U https://aclanthology.org/2025.findings-acl.1356/
%U https://doi.org/10.18653/v1/2025.findings-acl.1356
%P 26443-26455
Markdown (Informal)
[Search-in-Context: Efficient Multi-Hop QA over Long Contexts via Monte Carlo Tree Search with Dynamic KV Retrieval](https://aclanthology.org/2025.findings-acl.1356/) (Chen et al., Findings 2025)
ACL