@inproceedings{tao-etal-2026-fuse,
title = "{FUSE}: Failure-Guided Scenario Synthesis and Weighted Refinement for {LLM} Function Calling",
author = "Tao, Zhiguo and
Li, Linhan and
Sun, Lifan and
Yuan, Zichen",
editor = "Kamalloo, Ehsan and
Gontier, Nicolas and
Rozanov, Nikolai and
Hashemzadeh, Maryam and
Arora, Akhil",
booktitle = "Proceedings of the Second Workshop for {RE}search on Agent Language Models ({REALM} 2026)",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.realm-1.13/",
pages = "177--186",
ISBN = "979-8-89176-485-9",
abstract = "Large language model (LLM) agents increasingly rely on function calling to act across multi-turn interactions, but compact models remain brittle when tool availability, required parameters, and dialogue constraints change over time. Existing synthetic tool-use data often broadens coverage without targeting the recurring failures of a specific model. We present \textbf{FUSE}, a failure-guided refinement approach that uses the model{'}s own function-calling errors to synthesize harder training scenarios and then emphasizes difficult examples during supervised fine-tuning. This data-centric design turns diagnostic failures into targeted training signal while remaining simple to apply with standard offline fine-tuning. Experiments on BFCLv3 show that FUSE substantially improves a compact Qwen3-based model across standard and stress categories, including missing functions, missing parameters, and long-context interactions. Evaluation on BFCLv4 provides initial evidence that the same refinement strategy can transfer to selected agentic function-calling tasks."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tao-etal-2026-fuse">
<titleInfo>
<title>FUSE: Failure-Guided Scenario Synthesis and Weighted Refinement for LLM Function Calling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhiguo</namePart>
<namePart type="family">Tao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Linhan</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lifan</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zichen</namePart>
<namePart type="family">Yuan</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 Second Workshop for REsearch on Agent Language Models (REALM 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ehsan</namePart>
<namePart type="family">Kamalloo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicolas</namePart>
<namePart type="family">Gontier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikolai</namePart>
<namePart type="family">Rozanov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maryam</namePart>
<namePart type="family">Hashemzadeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akhil</namePart>
<namePart type="family">Arora</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">979-8-89176-485-9</identifier>
</relatedItem>
<abstract>Large language model (LLM) agents increasingly rely on function calling to act across multi-turn interactions, but compact models remain brittle when tool availability, required parameters, and dialogue constraints change over time. Existing synthetic tool-use data often broadens coverage without targeting the recurring failures of a specific model. We present FUSE, a failure-guided refinement approach that uses the model’s own function-calling errors to synthesize harder training scenarios and then emphasizes difficult examples during supervised fine-tuning. This data-centric design turns diagnostic failures into targeted training signal while remaining simple to apply with standard offline fine-tuning. Experiments on BFCLv3 show that FUSE substantially improves a compact Qwen3-based model across standard and stress categories, including missing functions, missing parameters, and long-context interactions. Evaluation on BFCLv4 provides initial evidence that the same refinement strategy can transfer to selected agentic function-calling tasks.</abstract>
<identifier type="citekey">tao-etal-2026-fuse</identifier>
<location>
<url>https://aclanthology.org/2026.realm-1.13/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>177</start>
<end>186</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T FUSE: Failure-Guided Scenario Synthesis and Weighted Refinement for LLM Function Calling
%A Tao, Zhiguo
%A Li, Linhan
%A Sun, Lifan
%A Yuan, Zichen
%Y Kamalloo, Ehsan
%Y Gontier, Nicolas
%Y Rozanov, Nikolai
%Y Hashemzadeh, Maryam
%Y Arora, Akhil
%S Proceedings of the Second Workshop for REsearch on Agent Language Models (REALM 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-485-9
%F tao-etal-2026-fuse
%X Large language model (LLM) agents increasingly rely on function calling to act across multi-turn interactions, but compact models remain brittle when tool availability, required parameters, and dialogue constraints change over time. Existing synthetic tool-use data often broadens coverage without targeting the recurring failures of a specific model. We present FUSE, a failure-guided refinement approach that uses the model’s own function-calling errors to synthesize harder training scenarios and then emphasizes difficult examples during supervised fine-tuning. This data-centric design turns diagnostic failures into targeted training signal while remaining simple to apply with standard offline fine-tuning. Experiments on BFCLv3 show that FUSE substantially improves a compact Qwen3-based model across standard and stress categories, including missing functions, missing parameters, and long-context interactions. Evaluation on BFCLv4 provides initial evidence that the same refinement strategy can transfer to selected agentic function-calling tasks.
%U https://aclanthology.org/2026.realm-1.13/
%P 177-186
Markdown (Informal)
[FUSE: Failure-Guided Scenario Synthesis and Weighted Refinement for LLM Function Calling](https://aclanthology.org/2026.realm-1.13/) (Tao et al., REALM 2026)
ACL