<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2026-coprm">
    <titleInfo>
        <title>CoPRM: A Collaborative Process Reward Model for Guiding Search Agent Reasoning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Xingquan</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yang</namePart>
        <namePart type="family">Zhao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chong</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Donglei</namePart>
        <namePart type="family">Yu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Pu</namePart>
        <namePart type="family">Jian</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chengqing</namePart>
        <namePart type="family">Zong</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Hung-Yi</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sunipa</namePart>
            <namePart type="family">Dev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jessy</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Desmond</namePart>
            <namePart type="family">Elliott</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-459-0</identifier>
    </relatedItem>
    <abstract>Large Language Model (LLM)-based search agents have demonstrated superior performance in knowledge-intensive tasks through interleaved reasoning and search interactions. Process Reward Models (PRMs) can enhance search agent performance by guiding step selection during inference. However, existing PRMs for search agents face a critical bottleneck: assessment unreliability in their training data. This issue stems from an over-reliance on single-source supervision, forcing a compromise between global solvability and local validity. We propose CoPRM (Collaborative Process Reward Model), a process reward model trained on high-quality preference data generated through our Collaborative Calibration methodology. This approach synthesizes immediate quality assessments with outcome-informed evaluations through a dual-strategy mechanism: strictly enforcing consensus filtering to eliminate unreliable signals, and employing an outcome-informed gating mechanism to resolve heterogeneous cross-type trade-offs. Trained on 10k preference pairs, CoPRM provides universal test-time guidance, enabling diverse search agents to achieve consistent performance improvements across four multi-hop QA benchmarks, demonstrating substantial gains, robust cross-domain generalization, and superior efficiency.</abstract>
    <identifier type="citekey">zhang-etal-2026-coprm</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.65/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>1472</start>
            <end>1504</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T CoPRM: A Collaborative Process Reward Model for Guiding Search Agent Reasoning
%A Zhang, Xingquan
%A Zhao, Yang
%A Li, Chong
%A Yu, Donglei
%A Jian, Pu
%A Zong, Chengqing
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F zhang-etal-2026-coprm
%X Large Language Model (LLM)-based search agents have demonstrated superior performance in knowledge-intensive tasks through interleaved reasoning and search interactions. Process Reward Models (PRMs) can enhance search agent performance by guiding step selection during inference. However, existing PRMs for search agents face a critical bottleneck: assessment unreliability in their training data. This issue stems from an over-reliance on single-source supervision, forcing a compromise between global solvability and local validity. We propose CoPRM (Collaborative Process Reward Model), a process reward model trained on high-quality preference data generated through our Collaborative Calibration methodology. This approach synthesizes immediate quality assessments with outcome-informed evaluations through a dual-strategy mechanism: strictly enforcing consensus filtering to eliminate unreliable signals, and employing an outcome-informed gating mechanism to resolve heterogeneous cross-type trade-offs. Trained on 10k preference pairs, CoPRM provides universal test-time guidance, enabling diverse search agents to achieve consistent performance improvements across four multi-hop QA benchmarks, demonstrating substantial gains, robust cross-domain generalization, and superior efficiency.
%U https://aclanthology.org/2026.emnlp-main.65/
%P 1472-1504

Markdown (Informal)

[CoPRM: A Collaborative Process Reward Model for Guiding Search Agent Reasoning](https://aclanthology.org/2026.emnlp-main.65/) (Zhang et al., EMNLP 2026)

• CoPRM: A Collaborative Process Reward Model for Guiding Search Agent Reasoning (Zhang et al., EMNLP 2026)

ACL

• Xingquan Zhang, Yang Zhao, Chong Li, Donglei Yu, Pu Jian, and Chengqing Zong. 2026. CoPRM: A Collaborative Process Reward Model for Guiding Search Agent Reasoning. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 1472–1504, Budapest, Hungary. Association for Computational Linguistics.