<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lu-etal-2026-bitter">
    <titleInfo>
        <title>The Bitter Lesson of Diffusion Language Models for Agentic Workflows: A Comprehensive Reality Check</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Qingyu</namePart>
        <namePart type="family">Lu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Liang</namePart>
        <namePart type="family">Ding</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kanjian</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jinxia</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Dacheng</namePart>
        <namePart type="family">Tao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Maria</namePart>
            <namePart type="family">Liakata</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Viviane</namePart>
            <namePart type="given">P</namePart>
            <namePart type="family">Moreira</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jiajun</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="family">Jurgens</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">San Diego, California, United States</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-390-6</identifier>
    </relatedItem>
    <abstract>The pursuit of real-time agentic interaction has driven interest in Diffusion-based Large Language Models (dLLMs) as alternatives to auto-regressive backbones, promising to break the sequential latency bottleneck. **However, does such efficiency gains translate into effective agentic behavior?** In this work, we present a comprehensive evaluation of dLLMs (e.g., LLaDA, Dream) across two distinct agentic paradigms: Embodied Agents (requiring long-horizon planning) and Tool-Calling Agents (requiring precise formatting).Contrary to the efficiency hype, our results on Agentboard and BFCL reveal a “**bitter lesson**”: current dLLMs fail to serve as reliable agentic backbones, frequently leading to systematically failure. **(1) In Embodied settings**, dLLMs suffer repeated attempts, failing to branch under temporal feedback. **(2) In Tool-Calling settings**, dLLMs fail to maintain symbolic precision (e.g. strict JSON schemas) under diffusion noise. To assess the potential of dLLMs in agentic workflows, we introduce **DiffuAgent**, a multi-agent evaluation framework that integrates dLLMs as plug-and-play cognitive cores. Our analysis shows that dLLMs are effective in non-causal roles (e.g., memory summarization and tool selection) but require the incorporation of causal, precise, and logically grounded reasoning mechanisms into the denoising process to be viable for agentic tasks.</abstract>
    <identifier type="citekey">lu-etal-2026-bitter</identifier>
    <location>
        <url>https://aclanthology.org/2026.acl-long.2036/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>43997</start>
            <end>44020</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T The Bitter Lesson of Diffusion Language Models for Agentic Workflows: A Comprehensive Reality Check
%A Lu, Qingyu
%A Ding, Liang
%A Zhang, Kanjian
%A Zhang, Jinxia
%A Tao, Dacheng
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F lu-etal-2026-bitter
%X The pursuit of real-time agentic interaction has driven interest in Diffusion-based Large Language Models (dLLMs) as alternatives to auto-regressive backbones, promising to break the sequential latency bottleneck. **However, does such efficiency gains translate into effective agentic behavior?** In this work, we present a comprehensive evaluation of dLLMs (e.g., LLaDA, Dream) across two distinct agentic paradigms: Embodied Agents (requiring long-horizon planning) and Tool-Calling Agents (requiring precise formatting).Contrary to the efficiency hype, our results on Agentboard and BFCL reveal a “**bitter lesson**”: current dLLMs fail to serve as reliable agentic backbones, frequently leading to systematically failure. **(1) In Embodied settings**, dLLMs suffer repeated attempts, failing to branch under temporal feedback. **(2) In Tool-Calling settings**, dLLMs fail to maintain symbolic precision (e.g. strict JSON schemas) under diffusion noise. To assess the potential of dLLMs in agentic workflows, we introduce **DiffuAgent**, a multi-agent evaluation framework that integrates dLLMs as plug-and-play cognitive cores. Our analysis shows that dLLMs are effective in non-causal roles (e.g., memory summarization and tool selection) but require the incorporation of causal, precise, and logically grounded reasoning mechanisms into the denoising process to be viable for agentic tasks.
%U https://aclanthology.org/2026.acl-long.2036/
%P 43997-44020

Markdown (Informal)

[The Bitter Lesson of Diffusion Language Models for Agentic Workflows: A Comprehensive Reality Check](https://aclanthology.org/2026.acl-long.2036/) (Lu et al., ACL 2026)

• The Bitter Lesson of Diffusion Language Models for Agentic Workflows: A Comprehensive Reality Check (Lu et al., ACL 2026)

ACL

• Qingyu Lu, Liang Ding, Kanjian Zhang, Jinxia Zhang, and Dacheng Tao. 2026. The Bitter Lesson of Diffusion Language Models for Agentic Workflows: A Comprehensive Reality Check. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 43997–44020, San Diego, California, United States. Association for Computational Linguistics.