<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2026-ramp">
    <titleInfo>
        <title>RAMP: Adapting One Agent to Multiple Retrievers via Behavioral Probing</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Weijun</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tao</namePart>
        <namePart type="family">Yang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jiayu</namePart>
        <namePart type="family">Yang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Fei</namePart>
        <namePart type="family">Chao</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>Agentic RAG agents must generate effective queries across diverse retriever backends, yet current agents produce retriever-oblivious queries, leading to large performance gaps when the backend changes. We observe that different retrievers, despite dissimilar architectures, exhibit structured behavioral patterns in their document-return overlap, forming a continuous behavioral space that can guide retriever-adaptive query generation. We propose RAMP (Retriever-Adaptive Multi-retriever Policy), which probes a black-box retriever with shared queries, encodes the resulting overlap patterns into a compact behavioral embedding, and injects it as soft tokens to condition query generation. A single RAMP model replaces four retriever-specific specialists without per-retriever retraining and generalizes to unseen retrievers by interpolating in behavioral space. On four QA benchmarks, RAMP matches 96–98% of four retriever-specific specialists (+3.8 EM over unconditioned training) and reaches 91.8% of the retrained upper bound on unseen retrievers, outperforming routing, few-shot, and fusion alternatives.</abstract>
    <identifier type="citekey">li-etal-2026-ramp</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.1977/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>44989</start>
            <end>45005</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T RAMP: Adapting One Agent to Multiple Retrievers via Behavioral Probing
%A Li, Weijun
%A Yang, Tao
%A Yang, Jiayu
%A Chao, Fei
%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 li-etal-2026-ramp
%X Agentic RAG agents must generate effective queries across diverse retriever backends, yet current agents produce retriever-oblivious queries, leading to large performance gaps when the backend changes. We observe that different retrievers, despite dissimilar architectures, exhibit structured behavioral patterns in their document-return overlap, forming a continuous behavioral space that can guide retriever-adaptive query generation. We propose RAMP (Retriever-Adaptive Multi-retriever Policy), which probes a black-box retriever with shared queries, encodes the resulting overlap patterns into a compact behavioral embedding, and injects it as soft tokens to condition query generation. A single RAMP model replaces four retriever-specific specialists without per-retriever retraining and generalizes to unseen retrievers by interpolating in behavioral space. On four QA benchmarks, RAMP matches 96–98% of four retriever-specific specialists (+3.8 EM over unconditioned training) and reaches 91.8% of the retrained upper bound on unseen retrievers, outperforming routing, few-shot, and fusion alternatives.
%U https://aclanthology.org/2026.emnlp-main.1977/
%P 44989-45005

Markdown (Informal)

[RAMP: Adapting One Agent to Multiple Retrievers via Behavioral Probing](https://aclanthology.org/2026.emnlp-main.1977/) (Li et al., EMNLP 2026)

• RAMP: Adapting One Agent to Multiple Retrievers via Behavioral Probing (Li et al., EMNLP 2026)

ACL

• Weijun Li, Tao Yang, Jiayu Yang, and Fei Chao. 2026. RAMP: Adapting One Agent to Multiple Retrievers via Behavioral Probing. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 44989–45005, Budapest, Hungary. Association for Computational Linguistics.