<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ding-zhan-2026-trains">
    <titleInfo>
        <title>Trains but Doesn’t Learn: A Post-Training Delivery Benchmark for LLM Agents as Forward-Deployed Engineers</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Weihang</namePart>
        <namePart type="family">Ding</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Junfei</namePart>
        <namePart type="family">Zhan</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: Industry Track</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Pepa</namePart>
            <namePart type="family">Atanasova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Gholamreza</namePart>
            <namePart type="family">Haffari</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Minghan</namePart>
            <namePart type="family">Wang</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">979-8-89176-460-6</identifier>
    </relatedItem>
    <abstract>Post-training is becoming a service (PTaaS): a customer hands an operator data and a goal, and a forward-deployed engineer (FDE) returns a fine-tuned, evaluated, and deployed model under a budget, a human-approval gate, and reproducibility requirements. Seating an LLM agent in the FDE seat raises a question existing benchmarks cannot answer: not whether an agent can raise a metric, but whether it can be trusted to deliver. We answer it on a governed delivery plane, where an agent drives ten stages and an oracle scores each stage from platform-recorded facts. The central silent failure is the run that trains but does not learn (TBDL): loss falls, every signal stays green, and the delivered model is no better than the base. A detector calibrated on known-corrupted runs flags every such run before payment. We ran four frontier agents (Claude Opus 5, GPT-5.6-luna, Gemini 3.7 Flash, DeepSeek-V4-Pro) end to end on metered L40S, A100, and H200 GPUs across 8B to 70B open bases, certifying every scenario before scoring. We also ran a human FDE arm under the same oracle and compare every agent against it.</abstract>
    <identifier type="citekey">ding-zhan-2026-trains</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-industry.52/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>868</start>
            <end>879</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Trains but Doesn’t Learn: A Post-Training Delivery Benchmark for LLM Agents as Forward-Deployed Engineers
%A Ding, Weihang
%A Zhan, Junfei
%Y Atanasova, Pepa
%Y Haffari, Gholamreza
%Y Wang, Minghan
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-460-6
%F ding-zhan-2026-trains
%X Post-training is becoming a service (PTaaS): a customer hands an operator data and a goal, and a forward-deployed engineer (FDE) returns a fine-tuned, evaluated, and deployed model under a budget, a human-approval gate, and reproducibility requirements. Seating an LLM agent in the FDE seat raises a question existing benchmarks cannot answer: not whether an agent can raise a metric, but whether it can be trusted to deliver. We answer it on a governed delivery plane, where an agent drives ten stages and an oracle scores each stage from platform-recorded facts. The central silent failure is the run that trains but does not learn (TBDL): loss falls, every signal stays green, and the delivered model is no better than the base. A detector calibrated on known-corrupted runs flags every such run before payment. We ran four frontier agents (Claude Opus 5, GPT-5.6-luna, Gemini 3.7 Flash, DeepSeek-V4-Pro) end to end on metered L40S, A100, and H200 GPUs across 8B to 70B open bases, certifying every scenario before scoring. We also ran a human FDE arm under the same oracle and compare every agent against it.
%U https://aclanthology.org/2026.emnlp-industry.52/
%P 868-879

Markdown (Informal)

[Trains but Doesn’t Learn: A Post-Training Delivery Benchmark for LLM Agents as Forward-Deployed Engineers](https://aclanthology.org/2026.emnlp-industry.52/) (Ding & Zhan, EMNLP 2026)

• Trains but Doesn’t Learn: A Post-Training Delivery Benchmark for LLM Agents as Forward-Deployed Engineers (Ding & Zhan, EMNLP 2026)

ACL

• Weihang Ding and Junfei Zhan. 2026. Trains but Doesn’t Learn: A Post-Training Delivery Benchmark for LLM Agents as Forward-Deployed Engineers. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 868–879, Budapest, Hungary. Association for Computational Linguistics.