@inproceedings{linich-etal-2026-trace,
title = "Trace-{GRAF}: Trace-Guided Granularity Routing for Sequential Agentic Workflows",
author = "Linich, Anastasiia and
Sosedka, Artyom and
Budennyy, Semen",
editor = "Atanasova, Pepa and
Haffari, Gholamreza and
Wang, Minghan",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-industry.265/",
pages = "4450--4460",
ISBN = "979-8-89176-460-6",
abstract = "Multi-agent LLM results can conflate decomposition with roles, communication, parallelism, and extra compute. We study strictly ordered tool-use workflows of dependent state-changing steps, where segmentation may also support auditing and handoff constraints. We introduce Trace-GRAF, a granularity selector that aligns one single-agent trace to target workflow steps, converts order violations and unrelated drift into split pressure, and selects the smallest granularity on the minimum-pressure plateau. It executes balanced contiguous segments because boundary ablation finds no significant success difference from semantic segmentation; pressure-minimizing partitions characterize cuts. Across held-out cohorts spanning two benchmarks and three executors, fixed decomposition sometimes improves and sometimes reduces success, while greater granularity both rescues failures and regresses solved runs. When SA success is observable, the pressure route preserves successful runs by construction. Across validation resplits on TerminalWorld, the calibrated extension{'}s mean recovery is 2.3{--}3.0{\%} for GPT-OSS, 0.0{--}0.1{\%} for Gemini, and 2.3{--}4.9{\%} for DeepSeek. Simple fixed fallbacks match much of the observed gain. Trace-GRAF therefore provides a risk-aware routing diagnostic with benchmark- and split-dependent gains."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="linich-etal-2026-trace">
<titleInfo>
<title>Trace-GRAF: Trace-Guided Granularity Routing for Sequential Agentic Workflows</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anastasiia</namePart>
<namePart type="family">Linich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Artyom</namePart>
<namePart type="family">Sosedka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Semen</namePart>
<namePart type="family">Budennyy</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>Multi-agent LLM results can conflate decomposition with roles, communication, parallelism, and extra compute. We study strictly ordered tool-use workflows of dependent state-changing steps, where segmentation may also support auditing and handoff constraints. We introduce Trace-GRAF, a granularity selector that aligns one single-agent trace to target workflow steps, converts order violations and unrelated drift into split pressure, and selects the smallest granularity on the minimum-pressure plateau. It executes balanced contiguous segments because boundary ablation finds no significant success difference from semantic segmentation; pressure-minimizing partitions characterize cuts. Across held-out cohorts spanning two benchmarks and three executors, fixed decomposition sometimes improves and sometimes reduces success, while greater granularity both rescues failures and regresses solved runs. When SA success is observable, the pressure route preserves successful runs by construction. Across validation resplits on TerminalWorld, the calibrated extension’s mean recovery is 2.3–3.0% for GPT-OSS, 0.0–0.1% for Gemini, and 2.3–4.9% for DeepSeek. Simple fixed fallbacks match much of the observed gain. Trace-GRAF therefore provides a risk-aware routing diagnostic with benchmark- and split-dependent gains.</abstract>
<identifier type="citekey">linich-etal-2026-trace</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-industry.265/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>4450</start>
<end>4460</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Trace-GRAF: Trace-Guided Granularity Routing for Sequential Agentic Workflows
%A Linich, Anastasiia
%A Sosedka, Artyom
%A Budennyy, Semen
%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 linich-etal-2026-trace
%X Multi-agent LLM results can conflate decomposition with roles, communication, parallelism, and extra compute. We study strictly ordered tool-use workflows of dependent state-changing steps, where segmentation may also support auditing and handoff constraints. We introduce Trace-GRAF, a granularity selector that aligns one single-agent trace to target workflow steps, converts order violations and unrelated drift into split pressure, and selects the smallest granularity on the minimum-pressure plateau. It executes balanced contiguous segments because boundary ablation finds no significant success difference from semantic segmentation; pressure-minimizing partitions characterize cuts. Across held-out cohorts spanning two benchmarks and three executors, fixed decomposition sometimes improves and sometimes reduces success, while greater granularity both rescues failures and regresses solved runs. When SA success is observable, the pressure route preserves successful runs by construction. Across validation resplits on TerminalWorld, the calibrated extension’s mean recovery is 2.3–3.0% for GPT-OSS, 0.0–0.1% for Gemini, and 2.3–4.9% for DeepSeek. Simple fixed fallbacks match much of the observed gain. Trace-GRAF therefore provides a risk-aware routing diagnostic with benchmark- and split-dependent gains.
%U https://aclanthology.org/2026.emnlp-industry.265/
%P 4450-4460
Markdown (Informal)
[Trace-GRAF: Trace-Guided Granularity Routing for Sequential Agentic Workflows](https://aclanthology.org/2026.emnlp-industry.265/) (Linich et al., EMNLP 2026)
ACL