The Calls are Coming from Inside the Model: Investigating Probe-based Detection of Tool-Calling Errors in LLMs

[2608.27750] The Calls are Coming from Inside the Model: Investigating Probe-based Detection of Tool-Calling Errors in LLMs Skip to main content Search Submit Donate Log in Computer Science > Machine Learning arXiv:2608.27750 (cs) [Submitted on 27 Aug 2026] Title: The Calls are Coming from Inside the Model: Investigating Probe-based Detection of Tool-Calling Errors in LLMs Authors: Eric Yeats , Brendan Kennedy , Loc Truong , John Buckheit , Jung Lee , Jesse Friedbaum , John Emanuello , Henry Kvinge View PDF HTML (experimental) Abstract: The hidden states of large language models (LLMs) are known to capture rich information relating to model knowledge and behavior that can be hard to extract from examination of input and output alone. As LLM-based systems increasingly interface with the external world, one area of concern is detecting incorrect or improper use of tools. Motivated by this, we study the effectiveness of using linear probes to detect incorrect tool-calls, measuring probe efficacy across 18 tool-calling LLMs evaluated on the Berkeley Function Calling Leaderboard. Overall, we find that probing is an effective means to catch a range of different tool-calling errors, including errors arising from using an argument that has the wrong value but the correct type, which might not be recorded by standard logging frameworks. Important factors in success include model size, probing layer, and model post-training type. We also show that probes are capable of generalizing to novel types of errors, which is critical in real world deployments. Comments: 4 main pages, 8 pages of references and appendices Subjects: Machine Learning (cs.LG) ; Computation and Language (cs.CL) Cite as: arXiv:2608.27750 [cs.LG] (or arXiv:2608.27750v1 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2608.27750 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Eric Yeats [ view email ] [v1] Thu, 27 Aug 2026 22:26:25 UTC (3,391 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.LG < prev | next > new | recent | 2026-08 Change to browse by: cs cs.CL References & Citations SciX 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? ) IArxiv recommender toggle IArxiv Recommender ( What is IArxiv? ) 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)

Related documents

• The Calls are Coming from Inside the Model: Investigating Probe-based Detection of Tool-Calling Errors in LLMs#779670
• LLM-Enhanced Log Anomaly Detection: A Comprehensive Benchmark of Large Language Models for Automated System Diagnostics#13168
• From Detection to Refusal: Safer LLMs via Circuit-Guided Weight Scaling#819535
• From Detection to Refusal: Safer LLMs via Circuit-Guided Weight Scaling#809539
• FIRE: Failure-Informed Runtime Engineering for Reliable Language-Model Agents#1061953