<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fu-etal-2026-ask">
    <titleInfo>
        <title>Ask, Answer, or Act: Learning Interaction Modes for Tool-Use Agents</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Tianyu</namePart>
        <namePart type="family">Fu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yangrui</namePart>
        <namePart type="family">Xie</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yunpu</namePart>
        <namePart type="family">Ma</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wanyuan</namePart>
        <namePart type="family">Wang</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>Robust tool-use agents must navigate mixed-intent interactions, deciding whether to ask for missing information, answer directly, or invoke tools. We tackle this challenge by introducing a novel task formulation that structures the planner’s action space into explicit interaction instructions over an explicit Ask/Answer/Act space, thereby making these behavioral boundaries an explicit target of optimization. In this framework, a planner predicts the interaction mode and semantic payload, while a frozen executor realizes the instruction into an observable behavior. Coupled with this structured decision process, we propose Executor-Grounded Failure-Routed Planner Learning (EFPL). EFPL optimizes the planner via executor-observed outcomes and strategically leverages privileged feedback for targeted correction when outcome rewards provide insufficient guidance, further refining these behavioral boundaries. Experiments on BFCL and When2Call across three backbone sizes show that EFPL consistently improves clarification, abstention, when-to-call decisions, and robustness to irrelevant tools, while fully preserving strong multi-turn tool-calling performance.</abstract>
    <identifier type="citekey">fu-etal-2026-ask</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.1335/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>30447</start>
            <end>30473</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Ask, Answer, or Act: Learning Interaction Modes for Tool-Use Agents
%A Fu, Tianyu
%A Xie, Yangrui
%A Ma, Yunpu
%A Wang, Wanyuan
%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 fu-etal-2026-ask
%X Robust tool-use agents must navigate mixed-intent interactions, deciding whether to ask for missing information, answer directly, or invoke tools. We tackle this challenge by introducing a novel task formulation that structures the planner’s action space into explicit interaction instructions over an explicit Ask/Answer/Act space, thereby making these behavioral boundaries an explicit target of optimization. In this framework, a planner predicts the interaction mode and semantic payload, while a frozen executor realizes the instruction into an observable behavior. Coupled with this structured decision process, we propose Executor-Grounded Failure-Routed Planner Learning (EFPL). EFPL optimizes the planner via executor-observed outcomes and strategically leverages privileged feedback for targeted correction when outcome rewards provide insufficient guidance, further refining these behavioral boundaries. Experiments on BFCL and When2Call across three backbone sizes show that EFPL consistently improves clarification, abstention, when-to-call decisions, and robustness to irrelevant tools, while fully preserving strong multi-turn tool-calling performance.
%U https://aclanthology.org/2026.emnlp-main.1335/
%P 30447-30473

Markdown (Informal)

[Ask, Answer, or Act: Learning Interaction Modes for Tool-Use Agents](https://aclanthology.org/2026.emnlp-main.1335/) (Fu et al., EMNLP 2026)

• Ask, Answer, or Act: Learning Interaction Modes for Tool-Use Agents (Fu et al., EMNLP 2026)

ACL

• Tianyu Fu, Yangrui Xie, Yunpu Ma, and Wanyuan Wang. 2026. Ask, Answer, or Act: Learning Interaction Modes for Tool-Use Agents. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 30447–30473, Budapest, Hungary. Association for Computational Linguistics.