ToolFlood: Beyond Selection -- Hiding Valid Tools from LLM Agents via Semantic Covering
cs.CL
Submitted: 2026-03-14
Updated: 2026-11-17
Code: https://github.com/as1-prog/ToolFlood
Terminology
Sources
- Do As I Can, Not As I Say: Grounding Language in Robotic Affordances
- StableToolBench: Towards Stable Large-Scale Benchmarking on Tool Learning of Large Language Models
- MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Use
- MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning
- Prompt Injection attack against LLM-integrated Applications
- Attractive Metadata Attack: Inducing LLM Agents to Invoke Malicious Tools
- WebGPT: Browser-assisted question-answering with human feedback
- Gorilla: Large Language Model Connected with Massive APIs
- ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs
- Toolformer: Language Models Can Teach Themselves to Use Tools
- POISONCRAFT: Practical Poisoning of Retrieval-Augmented Generation for Large Language Models
- Prompt Injection Attack to Tool Selection in LLM Agents
- ToolTweak: An Attack on Tool Selection in LLM-based Agents
- BadRAG: Identifying Vulnerabilities in Retrieval Augmented Generation of Large Language Models
- ReAct: Synergizing Reasoning and Acting in Language Models
- InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents
- Practical Poisoning Attacks against Retrieval-Augmented Generation
- Traceback of Poisoning Attacks to Retrieval-Augmented Generation
- Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data