# Tools Fail: Detecting Silent Errors in Faulty Tools

arXiv: https://arxiv.org/abs/2406.19228 · HTML: https://mlsanity.com/paper/2406.19228/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 53 references that are in the map.
- First posted on arXiv 27 Jun 2024.

## Builds on (most cited first, 30 of 36)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [Code as Policies: Language Model Programs for Embodied Control](https://mlsanity.com/paper/2209.07753/) (2022)
- [Inner Monologue: Embodied Reasoning through Planning with Language Models](https://mlsanity.com/paper/2207.05608/) (2022)
- [Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents](https://mlsanity.com/paper/2201.07207/) (2022)
- [Teaching Large Language Models to Self-Debug](https://mlsanity.com/paper/2304.05128/) (2023)
- [ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks](https://mlsanity.com/paper/1912.01734/) (2019)
- [Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models](https://mlsanity.com/paper/2303.04671/) (2023)
- [Learning To Retrieve Prompts for In-Context Learning](https://mlsanity.com/paper/2112.08633/) (2021)
- [AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors](https://mlsanity.com/paper/2308.10848/) (2023)
- [MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action](https://mlsanity.com/paper/2303.11381/) (2023)
- [Visual Programming: Compositional visual reasoning without training](https://mlsanity.com/paper/2211.11559/) (2022)
- [Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language](https://mlsanity.com/paper/2204.00598/) (2022)
- [Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning](https://mlsanity.com/paper/2305.12295/) (2023)
- [MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback](https://mlsanity.com/paper/2309.10691/) (2023)
- [Integrated Task and Motion Planning](https://mlsanity.com/paper/2010.01083/) (2020)
- [Task and Motion Planning with Large Language Models for Object Rearrangement](https://mlsanity.com/paper/2303.06247/) (2023)
- [Investigating the Limitations of Transformers with Simple Arithmetic Tasks](https://mlsanity.com/paper/2102.13019/) (2021)
- [FILM: Following Instructions in Language with Modular Methods](https://mlsanity.com/paper/2110.07342/) (2021)
- [Self-Edit: Fault-Aware Code Editor for Code Generation](https://mlsanity.com/paper/2305.04087/) (2023)
- [A Persistent Spatial Semantic Representation for High-level Natural Language Instruction Execution](https://mlsanity.com/paper/2107.05612/) (2021)
- [Goat: Fine-tuned LLaMA Outperforms GPT-4 on Arithmetic Tasks](https://mlsanity.com/paper/2305.14201/) (2023)
- [Semantic Curiosity for Active Visual Learning](https://mlsanity.com/paper/2006.09367/) (2020)

## Built on by (most cited first, 25 of 25)

- [ST-WebAgentBench: A Benchmark for Evaluating Safety and Trustworthiness in Web Agents](https://mlsanity.com/paper/2410.06703/) (2024)
- [LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directions](https://mlsanity.com/paper/2509.18970/) (2025)
- [CRITICTOOL: Evaluating Self-Critique Capabilities of Large Language Models in Tool-Calling Error Scenarios](https://mlsanity.com/paper/2506.13977/) (2025)
- [ToolFuzz -- Automated Agent Tool Testing](https://mlsanity.com/paper/2503.04479/) (2025)
- [Learning Evolving Tools for Large Language Models](https://mlsanity.com/paper/2410.06617/) (2024)
- [SHIELDA: Structured Handling of Exceptions in LLM-Driven Agentic Workflows](https://mlsanity.com/paper/2508.07935/) (2025)
- [Towards Reliable Benchmarking: A Contamination Free, Controllable Evaluation Framework for Multi-step LLM Function Calling](https://mlsanity.com/paper/2509.26553/) (2025)
- [Benchmarking Failures in Tool-Augmented Language Models](https://mlsanity.com/paper/2503.14227/) (2025)
- [Hell or High Water: Evaluating Agentic Recovery from External Failures](https://mlsanity.com/paper/2508.11027/) (2025)
- [KVEraser: Learning to Steer KV Cache for Efficient Localized Context Erasing](https://mlsanity.com/paper/2606.17034/) (2026)
- [Giving AI Agents Access to Cryptocurrency and Smart Contracts Creates New Vectors of AI Harm](https://mlsanity.com/paper/2507.08249/) (2025)
- [How Can Input Reformulation Improve Tool Usage Accuracy in a Complex Dynamic Environment? A Study on τ-bench](https://mlsanity.com/paper/2508.20931/) (2025)
- [SARC-DQ: Runtime Data-Quality Gating for Agentic AI: Silent Evidence Defects, the Incompetence Shield, and Downstream-Only Remediation](https://mlsanity.com/paper/2607.26313/) (2026)
- [Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoning](https://mlsanity.com/paper/2506.15894/) (2025)
- [RIVA: Leveraging LLM Agents for Reliable Configuration Drift Detection](https://mlsanity.com/paper/2603.02345/) (2026)
- [PEARL: Plan Exploration and Adaptive Reinforcement Learning for Multihop Tool Use](https://mlsanity.com/paper/2601.20439/) (2026)
- [From Task Solving to Robust Real-World Adaptation in LLM Agents](https://mlsanity.com/paper/2602.02760/) (2026)
- [Failure-Transparent Agents: Benchmarking Post-Failure Reporting in Tool-Using Language Models](https://mlsanity.com/paper/2609.35732/) (2026)
- [Repairing Tool Calls Using Post-tool Execution Reflection and RAG](https://mlsanity.com/paper/2510.17874/) (2025)
- [Grounding LLMs in Scientific Discovery via Embodied Actions](https://mlsanity.com/paper/2602.20639/) (2026)
- [Multi-Source Evidence Fusion for Audio Question Answering](https://mlsanity.com/paper/2603.17822/) (2026)
- [Towards Robust Tool Use in Agents via Experience-Driven Adaptive Guidance](https://mlsanity.com/paper/2608.03403/) (2026)
- [When Tools Silently Lie: Evaluating and Mitigating Blind Compliance in Tool-Augmented Data Agents](https://mlsanity.com/paper/2609.37153/) (2026)
- [RSure-Agent: Reliable Use of Tool Observations for Remote Sensing Agents](https://mlsanity.com/paper/2610.04836/) (2026)
- [Beyond Perfect Teammates: Multi-Agent Collaboration with Unreliable Colleagues](https://mlsanity.com/paper/2610.16117/) (2026)

## Abstract (arXiv)

Tools have become a mainstay of LLMs, allowing them to retrieve knowledge not in their weights, to perform tasks on the web, and even to control robots. However, most ontologies and surveys of tool-use have assumed the core challenge for LLMs is choosing the tool. Instead, we introduce a framework for tools more broadly which guides us to explore a model's ability to detect "silent" tool errors, and reflect on how to plan. This more directly aligns with the increasingly popular use of models as tools. We provide an initial approach to failure recovery with promising results both on a controlled calculator setting and embodied agent planning.