# Benchmarking Failures in Tool-Augmented Language Models

arXiv: https://arxiv.org/abs/2503.14227 · HTML: https://mlsanity.com/paper/2503.14227/

## 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.

## Placed in

- LLM agents and tool use / [Tool learning and function calling](https://mlsanity.com/agents/tool-learning-and-function-calling/)

## Builds on (most cited first, 13 of 13)

- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [Gorilla: Large Language Model Connected with Massive APIs](https://mlsanity.com/paper/2305.15334/) (2023)
- [Visual Programming: Compositional visual reasoning without training](https://mlsanity.com/paper/2211.11559/) (2022)
- [ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases](https://mlsanity.com/paper/2306.05301/) (2023)
- [AmbigQA: Answering Ambiguous Open-domain Questions](https://mlsanity.com/paper/2004.10645/) (2020)
- [ToolQA: A Dataset for LLM Question Answering with External Tools](https://mlsanity.com/paper/2306.13304/) (2023)
- [GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction](https://mlsanity.com/paper/2305.18752/) (2023)
- [MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Use](https://mlsanity.com/paper/2310.03128/) (2023)
- [An LLM Compiler for Parallel Function Calling](https://mlsanity.com/paper/2312.04511/) (2023)
- [T-Eval: Evaluating the Tool Utilization Capability of Large Language Models Step by Step](https://mlsanity.com/paper/2312.14033/) (2023)
- [TroVE: Inducing Verifiable and Efficient Toolboxes for Solving Programmatic Tasks](https://mlsanity.com/paper/2401.12869/) (2024)
- [What Are Tools Anyway? A Survey from the Language Model Perspective](https://mlsanity.com/paper/2403.15452/) (2024)
- [Tools Fail: Detecting Silent Errors in Faulty Tools](https://mlsanity.com/paper/2406.19228/) (2024)

## Built on by (most cited first, 9 of 9)

- [The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestration](https://mlsanity.com/paper/2603.22862/) (2026)
- [ToolHaystack: Stress-Testing Tool-Augmented Language Models in Realistic Long-Term Interactions](https://mlsanity.com/paper/2505.23662/) (2025)
- [When May an Agent Stop? Evidence-Carrying Termination for Tool-Using LLMs](https://mlsanity.com/paper/2608.23623/) (2026)
- [WebDS: An End-to-End Benchmark for Web-based Data Science](https://mlsanity.com/paper/2508.01222/) (2025)
- [ToolMATH: A Diagnostic Benchmark for Long-Horizon Tool Use under Systematic Tool-Catalog Constraints](https://mlsanity.com/paper/2602.21265/) (2026)
- [FlowMind: Execute-Summarize for Structured Workflow Generation from LLM Reasoning](https://mlsanity.com/paper/2602.11782/) (2026)
- [OctoNest: Adaptive Cross-Device Execution through Stateful Control](https://mlsanity.com/paper/2606.20487/) (2026)
- [Representation Robustness Under Executable Reasoning Constraints in Large Language Models for Mathematical Problem Solving](https://mlsanity.com/paper/2607.20520/) (2026)
- [PAUSE: A User-Centric Benchmark for Personal AI Assistants in Unified Service Environments](https://mlsanity.com/paper/2607.27354/) (2026)

## 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.