# RoTBench: A Multi-Level Benchmark for Evaluating the Robustness of Large Language Models in Tool Learning

arXiv: https://arxiv.org/abs/2401.08326 · HTML: https://mlsanity.com/paper/2401.08326/

## Key facts

- Cited by 47 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 21 of its 34 references that are in the map.
- First posted on arXiv 16 Jan 2024.

## 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, 21 of 21)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [Extending Context Window of Large Language Models via Positional Interpolation](https://mlsanity.com/paper/2306.15595/) (2023)
- [ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases](https://mlsanity.com/paper/2306.05301/) (2023)
- [AgentTuning: Enabling Generalized Agent Abilities for LLMs](https://mlsanity.com/paper/2310.12823/) (2023)
- [Tool Learning with Foundation Models](https://mlsanity.com/paper/2304.08354/) (2023)
- [ToolQA: A Dataset for LLM Question Answering with External Tools](https://mlsanity.com/paper/2306.13304/) (2023)
- [A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models](https://mlsanity.com/paper/2303.10420/) (2023)
- [ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings](https://mlsanity.com/paper/2305.11554/) (2023)
- [MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Use](https://mlsanity.com/paper/2310.03128/) (2023)
- [On the Robustness of ChatGPT: An Adversarial and Out-of-distribution Perspective](https://mlsanity.com/paper/2302.12095/) (2023)
- [Foundation Models for Decision Making: Problems, Methods, and Opportunities](https://mlsanity.com/paper/2303.04129/) (2023)
- [How Robust is GPT-3.5 to Predecessors? A Comprehensive Study on Language Understanding Tasks](https://mlsanity.com/paper/2303.00293/) (2023)
- [Improving the Robustness of Summarization Systems with Dual Augmentation](https://mlsanity.com/paper/2306.01090/) (2023)
- [DemoNSF: A Multi-task Demonstration-based Generative Framework for Noisy Slot Filling Task](https://mlsanity.com/paper/2310.10169/) (2023)

## Built on by (most cited first, 30 of 47)

- [Tool Learning with Large Language Models: A Survey](https://mlsanity.com/paper/2405.17935/) (2024)
- [ToolSword: Unveiling Safety Issues of Large Language Models in Tool Learning Across Three Stages](https://mlsanity.com/paper/2402.10753/) (2024)
- [ToolHop: A Query-Driven Benchmark for Evaluating Large Language Models in Multi-Hop Tool Use](https://mlsanity.com/paper/2501.02506/) (2025)
- [Retrieval Models Aren't Tool-Savvy: Benchmarking Tool Retrieval for Large Language Models](https://mlsanity.com/paper/2503.01763/) (2025)
- [Speech-Copilot: Leveraging Large Language Models for Speech Processing via Task Decomposition, Modularization, and Program Generation](https://mlsanity.com/paper/2407.09886/) (2024)
- [reWordBench: Benchmarking and Improving the Robustness of Reward Models with Transformed Inputs](https://mlsanity.com/paper/2503.11751/) (2025)
- [On the Robustness of Agentic Function Calling](https://mlsanity.com/paper/2504.00914/) (2025)
- [CRITICTOOL: Evaluating Self-Critique Capabilities of Large Language Models in Tool-Calling Error Scenarios](https://mlsanity.com/paper/2506.13977/) (2025)
- [Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build Environments](https://mlsanity.com/paper/2508.08791/) (2025)
- [VLM-RobustBench: A Comprehensive Benchmark for Robustness of Vision-Language Models](https://mlsanity.com/paper/2603.06148/) (2026)
- [The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestration](https://mlsanity.com/paper/2603.22862/) (2026)
- [ElecBench: a Power Dispatch Evaluation Benchmark for Large Language Models](https://mlsanity.com/paper/2407.05365/) (2024)
- [TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use](https://mlsanity.com/paper/2412.15495/) (2024)
- [GenTool: Enhancing Tool Generalization in Language Models through Zero-to-One and Weak-to-Strong Simulation](https://mlsanity.com/paper/2502.18990/) (2025)
- [Impatient Users Confuse AI Agents: High-fidelity Simulations of Human Traits for Testing Agents](https://mlsanity.com/paper/2510.04491/) (2025)
- [Can Tool-augmented Large Language Models be Aware of Incomplete Conditions?](https://mlsanity.com/paper/2406.12307/) (2024)
- [SOK: A Taxonomy of Attack Vectors and Defense Strategies for Agentic Supply Chain Runtime](https://mlsanity.com/paper/2602.19555/) (2026)
- [Trustworthy Medical Question Answering: An Evaluation-Centric Survey](https://mlsanity.com/paper/2506.03659/) (2025)
- [Analyzing the Effects of Supervised Fine-Tuning on Model Knowledge from Token and Parameter Levels](https://mlsanity.com/paper/2509.16596/) (2025)
- [ToolSpectrum : Towards Personalized Tool Utilization for Large Language Models](https://mlsanity.com/paper/2505.13176/) (2025)
- [DICE-BENCH: Evaluating the Tool-Use Capabilities of Large Language Models in Multi-Round, Multi-Party Dialogues](https://mlsanity.com/paper/2506.22853/) (2025)
- [Don't Adapt Small Language Models for Tools; Adapt Tool Schemas to the Models](https://mlsanity.com/paper/2510.07248/) (2025)
- [When Simulation Lies: A Sim-to-Real Benchmark and Domain-Randomized RL Recipe for Tool-Use Agents](https://mlsanity.com/paper/2605.11928/) (2026)
- [FamilyTool: A Multi-hop Personalized Tool Use Benchmark](https://mlsanity.com/paper/2504.06766/) (2025)
- [MME-CoF-Pro: Evaluating Reasoning Coherence in Video Generative Models with Text and Visual Hints](https://mlsanity.com/paper/2603.20194/) (2026)
- [What Affects the Stability of Tool Learning? An Empirical Study on the Robustness of Tool Learning Frameworks](https://mlsanity.com/paper/2407.03007/) (2024)
- [Agentic Tool Use in Large Language Models](https://mlsanity.com/paper/2604.00835/) (2026)
- [Can Agents Generalize to the Open World? Unveiling the Fragility of Static Training in Tool Use](https://mlsanity.com/paper/2607.01084/) (2026)
- [PEToolLLM: Towards Personalized Tool Learning in Large Language Models](https://mlsanity.com/paper/2502.18980/) (2025)
- [FinToolSyn: A forward synthesis Framework for Financial Tool-Use Dialogue Data with Dynamic Tool Retrieval](https://mlsanity.com/paper/2603.24051/) (2026)

## Abstract (arXiv)

Tool learning has generated widespread interest as a vital means of interaction between Large Language Models (LLMs) and the physical world. Current research predominantly emphasizes LLMs' capacity to utilize tools in well-structured environments while overlooking their stability when confronted with the inevitable noise of the real world. To bridge this gap, we introduce RoTBench, a multi-level benchmark for evaluating the robustness of LLMs in tool learning. Specifically, we establish five external environments, each featuring varying levels of noise (i.e., Clean, Slight, Medium, Heavy, and Union), providing an in-depth analysis of the model's resilience across three critical phases: tool selection, parameter identification, and content filling. Experiments involving six widely-used models underscore the urgent necessity for enhancing the robustness of LLMs in tool learning. For instance, the performance of GPT-4 even drops significantly from 80.00 to 58.10 when there is no substantial change in manual accuracy. More surprisingly, the noise correction capability inherent in the GPT family paradoxically impedes its adaptability in the face of mild noise. In light of these findings, we propose RoTTuning, a strategy that enriches the diversity of training environments to bolster the robustness of LLMs in tool learning. The code and data are available at https://github.com/Junjie-Ye/RoTBench.