Related papers: ToolTweak: An Attack on Tool Selection in LLM-base…

Large language models (LLMs) have demonstrated impressive capabilities in utilizing external tools. In practice, however, LLMs are often exposed to tools that are irrelevant to the user's query, in which case the desired behavior is to…

Large language model (LLM)-based agents combine LLMs with external tools to automate tasks such as scheduling meetings, managing documents, or booking travel. While these integrations unlock powerful capabilities, they also create new and…

Considering the premise that the number of products offered grow in an exponential fashion and the amount of data that a user can assimilate before making a decision is relatively small, recommender systems help in categorizing content…

The proliferation of autonomous agents powered by large language models (LLMs) has revolutionized popular business applications dealing with tabular data, i.e., tabular agents. Although LLMs are observed to be vulnerable against prompt…

The use of language technologies in high-stake settings is increasing in recent years, mostly motivated by the success of Large Language Models (LLMs). However, despite the great performance of LLMs, they are are susceptible to ethical…

While integrating external tools into large language models (LLMs) enhances their ability to access real-time information and domain-specific services, existing approaches focus narrowly on functional tool selection following user…

Large language models (LLMs) are increasingly deployed as agents with access to executable tools, enabling direct interaction with external systems. However, most safety evaluations remain text-centric and assume that compliant language…

Many internet applications are powered by machine learned models, which are usually trained on labeled datasets obtained through either implicit / explicit user feedback signals or human judgments. Since societal biases may be present in…

The advent of Large Language Models (LLMs) has revolutionized product recommenders, yet their susceptibility to adversarial manipulation poses critical challenges, particularly in real-world commercial applications. Our approach is the…

Modern LLM agents combine long-term memory for personalization with tool-calling interfaces for taking actions in the world -- a combination underpinning contemporary production systems. We study a previously unexamined failure of this…

Recent advances in Language Model (LM) agents and tool use, exemplified by applications like ChatGPT Plugins, enable a rich set of capabilities but also amplify potential risks - such as leaking private data or causing financial losses.…

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…

Targeted bit-flip attacks (BFAs) exploit hardware faults to manipulate model parameters, posing a significant security threat. While prior work targets single-step inference models (e.g., image classifiers), LLM-based agents with…

Tool use enables large language models (LLMs) to access external information, invoke software systems, and act in digital environments beyond what can be solved from model parameters alone. Early research mainly studied whether a model…

Web agents, powered by large language models (LLMs), are increasingly deployed to automate complex web interactions. The rise of open-source frameworks (e.g., Browser Use, Skyvern-AI) has accelerated adoption, but also broadened the attack…

Large language models (LLMs) have garnered significant attention due to their impressive natural language processing (NLP) capabilities. Recently, many studies have focused on the tool utilization ability of LLMs. They primarily…

Large Language Models (LLMs) enhance their problem-solving capability by utilizing external tools. However, in open-world scenarios with massive and evolving tool repositories, existing methods relying on static embedding retrieval or…

Tool-augmented reasoning has become a popular direction for LLM-based agents, and it is widely assumed to improve reasoning and reliability. However, we demonstrate that this consensus does not always hold: in the presence of semantic…

We present Natural Language Tools (NLT), a framework that replaces programmatic JSON tool calling in large language models (LLMs) with natural language outputs. By decoupling tool selection from response generation, NLT eliminates task…

Large language models (LLMs) have displayed massive improvements in reasoning and decision-making skills and can hold natural conversations with users. Many recent works seek to augment LLM-based assistants with external tools so they can…