mlsanityData to 14 Oct 2026

Benchmarking Failures in Tool-Augmented Language Models

arXiv 2503.14227 ↗First posted 18 Mar 2025cs.SE cs.CLcited by 9

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

Abstract (arXiv)

The integration of tools has extended the capabilities of language models (LMs) beyond vanilla text generation to versatile scenarios. However, tool-augmented language models (TaLMs) often assume 'perfect' information access and tool availability, which may not hold in the real world. To systematically study TaLMs' imperfections, we introduce the FAIL-TALMS benchmark, featuring two major failures: under-specified user queries and non-available tools. FAIL-TALMS contains 1,749 examples using 906 tools across 21 categories, including single- and multi-tool usage. We evaluate top-performing proprietary and open-source models, and find all current models except for Claude struggle to recognize missing tools or information. Further, to study possible mitigation of the failures, we enable real-time human interaction, named the Ask-and-Help (AAH) method, to provide missing information or replace non-functional tools. While AAH can help models solve tasks more correctly when queries are under-specified, it brings minimal benefit when complex tools are broken.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Placed in Tool learning and function calling, one of 16 directions in LLM agents and tool use. Builds on 13 of its 38 references that are in the map. First posted on arXiv 18 Mar 2025.

Builds on

13 of 38 references.

Closest ancestors · 6

Same direction, newest first

  1. 2023MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Use4 Oct
  2. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs31 Jul
  3. 2023ToolQA: A Dataset for LLM Question Answering with External Tools23 Jun
  4. 2023ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases8 Jun
  5. 2023GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction30 May
  6. 2023Gorilla: Large Language Model Connected with Massive APIs24 May

Other references · 7

  1. 2022Visual Programming: Compositional visual reasoning without trainingcited by 516
  2. 2020AmbigQA: Answering Ambiguous Open-domain Questionscited by 390
  3. 2023An LLM Compiler for Parallel Function Callingcited by 179
  4. 2023T-Eval: Evaluating the Tool Utilization Capability of Large Language Models Step by Stepcited by 93
  5. 2024TroVE: Inducing Verifiable and Efficient Toolboxes for Solving Programmatic Taskscited by 75
  6. 2024What Are Tools Anyway? A Survey from the Language Model Perspectivecited by 54
  7. 2024Tools Fail: Detecting Silent Errors in Faulty Toolscited by 25

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 7.

9 papers.

  1. 2026The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestrationcited by 14
  2. 2025ToolHaystack: Stress-Testing Tool-Augmented Language Models in Realistic Long-Term Interactionscited by 5
  3. 2026When May an Agent Stop? Evidence-Carrying Termination for Tool-Using LLMscited by 3
  4. 2025WebDS: An End-to-End Benchmark for Web-based Data Sciencecited by 2
  5. 2026ToolMATH: A Diagnostic Benchmark for Long-Horizon Tool Use under Systematic Tool-Catalog Constraintscited by 1
  6. 2026FlowMind: Execute-Summarize for Structured Workflow Generation from LLM Reasoningcited by 0
  7. 2026OctoNest: Adaptive Cross-Device Execution through Stateful Controlcited by 0
  8. 2026Representation Robustness Under Executable Reasoning Constraints in Large Language Models for Mathematical Problem Solvingcited by 0
  9. 2026PAUSE: A User-Centric Benchmark for Personal AI Assistants in Unified Service Environmentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025ToolDial: Multi-turn Dialogue Generation Method for Tool-Augmented Language Models
  2. 2022TALM: Tool Augmented Language Models
  3. 2023Augmented Language Models: a Survey
  4. 2025ToolHop: A Query-Driven Benchmark for Evaluating Large Language Models in Multi-Hop Tool Use
  5. 2024Can Tool-augmented Large Language Models be Aware of Incomplete Conditions?
  6. 2024ToolEyes: Fine-Grained Evaluation for Tool Learning Capabilities of Large Language Models in Real-world Scenarios
  7. 2026Lost in Execution: On the Multilingual Robustness of Tool Calling in Large Language Models
  8. 2026Beyond Ideal Instruction: A Comprehensive Framework for Evaluating LLMs in Realistic Interactions