mlsanityData to 14 Oct 2026

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

arXiv 2608.27750 ↗First posted 27 Aug 2026cs.LG cs.CLcited by 0

On the map: LLM agents and tool use → Tool learning and function calling

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Tool learning and function calling, one of 16 directions in LLM agents and tool use. Builds on 16 of its 17 references that are in the map. First posted on arXiv 27 Aug 2026.

Builds on

16 of 17 references.

Closest ancestors · 3

Same direction, newest first

  1. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs31 Jul
  2. 2023Gorilla: Large Language Model Connected with Massive APIs24 May
  3. 2023Toolformer: Language Models Can Teach Themselves to Use Tools9 Feb

Other references · 13

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  3. 2022Language Models (Mostly) Know What They Knowcited by 1,856
  4. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,601
  5. 2023A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivitycited by 894
  6. 2022Discovering Latent Knowledge in Language Models Without Supervisioncited by 767
  7. 2023The Linear Representation Hypothesis and the Geometry of Large Language Modelscited by 716
  8. 2023The Internal State of an LLM Knows When It's Lyingcited by 659
  9. 2024INSIDE: LLMs' Internal States Retain the Power of Hallucination Detectioncited by 323
  10. 2025Layer by Layer: Uncovering Hidden Representations in Language Modelscited by 311
  11. 2024LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinationscited by 244
  12. 2023A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generationcited by 206
1 more
  1. 2026Internal Representations as Indicators of Hallucinations in Agent Tool Selectioncited by 19

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026ToolFailBench: Diagnosing Tool-Use Failures in LLM Agents
  2. 2026ToolRobustBench: Stage-Wise Perturbation Evaluation and Failure Diagnosis for Tool-Calling Agents
  3. 2026Calibration is the Bottleneck: An Action-Class Diagnostic of Multi-Turn Tool-Calling
  4. 2026Getting the Parameters Right: A Difficulty-Graded Benchmark and Probe-Guided Training for LLM Tool Calls
  5. 2026Lost in Execution: On the Multilingual Robustness of Tool Calling in Large Language Models
  6. 2024ToolScan: A Benchmark for Characterizing Errors in Tool-Use LLMs
  7. 2026Try, Check and Retry: A Divide-and-Conquer Framework for Boosting Long-context Tool-Calling Performance of LLMs
  8. 2025AskToAct: Enhancing LLMs Tool Use via Self-Correcting Clarification