Attributing Structured-Output Gains in Function Calling: Interface Alignment versus Procedural Transfer

[2607.02595] Attributing Structured-Output Gains in Function Calling: Interface Alignment versus Procedural Transfer Skip to main content Search Submit Donate Log in Computer Science > Software Engineering arXiv:2607.02595 (cs) [Submitted on 1 Jul 2026 ( v1 ), last revised 25 Aug 2026 (this version, v2)] Title: Attributing Structured-Output Gains in Function Calling: Interface Alignment versus Procedural Transfer Authors: Wanyi Chen , Daoyuan Chen , Fang Kong View PDF Abstract: Structured-output benchmarks reward both task decisions and interface compliance, so prompt-induced function-calling gains require attribution before they can be interpreted as transferable skill. We introduce a four-layer gain-attribution protocol for prompt-prepended skill injection, combining canonicalized rescoring, format-only controls, repaired/balanced induction, and portability checks. Applied to the Berkeley Function Calling Leaderboard (BFCL) and scoped with API-Bank, MATH-500, and MultiHop-RAG, the protocol shows that several apparent gains are better attributed to interface alignment than to procedural transfer: format-only prompts match or exceed full skills in key BFCL cells, repaired/balanced induction removes the largest sub-frontier gains, and API-Bank target-native gains are matched within 0.5 percentage points (pp) by length-matched generic procedural prompts. These findings treat format compliance as a useful engineering capability while clarifying what a structured-output score certifies. We release BFCL-CANONICAL and recommend canonicalized metrics, balanced induction, and format-only baselines for function-calling skill-gain attribution. Code and data are available at this https URL . Comments: 18 pages, 5 figures Subjects: Software Engineering (cs.SE) ; Programming Languages (cs.PL) Cite as: arXiv:2607.02595 [cs.SE] (or arXiv:2607.02595v2 [cs.SE] for this version) https://doi.org/10.48550/arXiv.2607.02595 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Wanyi Chen [ view email ] [v1] Wed, 1 Jul 2026 08:32:14 UTC (15,074 KB) [v2] Tue, 25 Aug 2026 09:22:50 UTC (15,179 KB) Full-text links: Access Paper: View PDF TeX Source view license Current browse context: cs.SE < prev | next > new | recent | 2026-07 Change to browse by: cs cs.PL References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Attributing Structured-Output Gains in Function Calling: Interface Alignment versus Procedural Transfer#670666
• Stäckel transform, coupling constant metamorphosis and algebraization of quasi-exactly solvable systems#629759
• Stäckel transform, coupling constant metamorphosis and algebraization of quasi-exactly solvable systems#627897
• Individual-Level Large-Scale Circuit Modelling of Human Cortex#256635
• Pushout Attachments and Conditional Complexity of Executable Models#1051517