mlsanityData to 7 Oct 2026

Tools Fail: Detecting Silent Errors in Faulty Tools

arXiv 2406.19228 ↗First posted 27 Jun 2024cs.CL cs.AI cs.LGcited by 23

Not on the map. Why?

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.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). Builds on 36 of its 53 references that are in the map. First posted on arXiv 27 Jun 2024.

Builds on

36 of 53 references.

References · 36

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  4. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  5. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  6. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  7. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  8. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,880
  9. 2022Language Models (Mostly) Know What They Knowcited by 1,783
  10. 2022Code as Policies: Language Model Programs for Embodied Controlcited by 1,172
  11. 2022Inner Monologue: Embodied Reasoning through Planning with Language Modelscited by 1,057
  12. 2022Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agentscited by 1,029
24 more
  1. 2023Teaching Large Language Models to Self-Debugcited by 963
  2. 2019ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Taskscited by 773
  3. 2023Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Modelscited by 659
  4. 2021Learning To Retrieve Prompts for In-Context Learningcited by 641
  5. 2023AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviorscited by 580
  6. 2022Socratic Models: Composing Zero-Shot Multimodal Reasoning with Languagecited by 513
  7. 2023MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Actioncited by 511
  8. 2022Visual Programming: Compositional visual reasoning without trainingcited by 507
  9. 2023Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoningcited by 379
  10. 2023MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedbackcited by 293
  11. 2020Integrated Task and Motion Planningcited by 281
  12. 2023Task and Motion Planning with Large Language Models for Object Rearrangementcited by 140
  13. 2021Investigating the Limitations of Transformers with Simple Arithmetic Taskscited by 136
  14. 2021FILM: Following Instructions in Language with Modular Methodscited by 119
  15. 2023Self-Edit: Fault-Aware Code Editor for Code Generationcited by 110
  16. 2021A Persistent Spatial Semantic Representation for High-level Natural Language Instruction Executioncited by 91
  17. 2023Goat: Fine-tuned LLaMA Outperforms GPT-4 on Arithmetic Taskscited by 84
  18. 2020Semantic Curiosity for Active Visual Learningcited by 44
  19. 2023Interactive Task Planning with Language Modelscited by 36
  20. 2022When to Ask for Help: Proactive Interventions in Autonomous Reinforcement Learningcited by 20
  21. 2022Ask4Help: Learning to Leverage an Expert for Embodied Taskscited by 18
  22. 2020Detect, Reject, Correct: Crossmodal Compensation of Corrupted Sensorscited by 17
  23. 2023From Interpolation to Extrapolation: Complete Length Generalization for Arithmetic Transformerscited by 10
  24. 2024GenAudit: Fixing Factual Errors in Language Model Outputs with Evidencecited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 11; 2026: 10.

23 papers.

Sort:

By area:

  1. 2024ST-WebAgentBench: A Benchmark for Evaluating Safety and Trustworthiness in Web Agentscited by 126
  2. 2025LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directionscited by 49
  3. 2025CRITICTOOL: Evaluating Self-Critique Capabilities of Large Language Models in Tool-Calling Error Scenarioscited by 19
  4. 2025ToolFuzz -- Automated Agent Tool Testingcited by 18
  5. 2024Learning Evolving Tools for Large Language Modelscited by 15
  6. 2025Towards Reliable Benchmarking: A Contamination Free, Controllable Evaluation Framework for Multi-step LLM Function Callingcited by 13
  7. 2025SHIELDA: Structured Handling of Exceptions in LLM-Driven Agentic Workflowscited by 12
  8. 2025Benchmarking Failures in Tool-Augmented Language Modelscited by 9
  9. 2025Hell or High Water: Evaluating Agentic Recovery from External Failurescited by 6
  10. 2026KVEraser: Learning to Steer KV Cache for Efficient Localized Context Erasingcited by 4
  11. 2025Giving AI Agents Access to Cryptocurrency and Smart Contracts Creates New Vectors of AI Harmcited by 3
  12. 2025How Can Input Reformulation Improve Tool Usage Accuracy in a Complex Dynamic Environment? A Study on τ-benchcited by 3
11 more
  1. 2026SARC-DQ: Runtime Data-Quality Gating for Agentic AI: Silent Evidence Defects, the Incompetence Shield, and Downstream-Only Remediationcited by 3
  2. 2025Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoningcited by 2
  3. 2026PEARL: Plan Exploration and Adaptive Reinforcement Learning for Multihop Tool Usecited by 1
  4. 2026RIVA: Leveraging LLM Agents for Reliable Configuration Drift Detectioncited by 1
  5. 2025Repairing Tool Calls Using Post-tool Execution Reflection and RAGcited by 0
  6. 2026From Task Solving to Robust Real-World Adaptation in LLM Agentscited by 0
  7. 2026Grounding LLMs in Scientific Discovery via Embodied Actionscited by 0
  8. 2026Multi-Source Evidence Fusion for Audio Question Answeringcited by 0
  9. 2026Towards Robust Tool Use in Agents via Experience-Driven Adaptive Guidancecited by 0
  10. 2026Failure-Transparent Agents: Benchmarking Post-Failure Reporting in Tool-Using Language Modelscited by 0
  11. 2026When Tools Silently Lie: Evaluating and Mitigating Blind Compliance in Tool-Augmented Data Agentscited by 0