Related papers: Intentional Deception as Controllable Capability i…
As large language models (LLMs) transition to autonomous agents synthesizing real-time information, their reasoning capabilities introduce an unexpected attack surface. This paper introduces a novel threat where colluding agents steer…
Organisations are starting to adopt LLM-based AI agents, with their deployments naturally evolving from single agents towards interconnected, multi-agent networks. Yet a collection of safe agents does not guarantee a safe collection of…
Vision-language models (VLMs) have shown impressive capabilities in perceptual tasks, yet they degrade in complex multi-hop reasoning under multiplayer game settings with imperfect and deceptive information. In this paper, we study a…
Recent advances in Large Language Models (LLMs) have driven interest in automating cybersecurity penetration testing workflows, offering the promise of faster and more consistent vulnerability assessment for enterprise systems. Existing LLM…
Despite their wide-ranging benefits, LLM-based agents deployed in open environments can be exploited to produce manipulative material. In this study, we task LLMs with propaganda objectives and analyze their outputs using two…
Detecting deception in an increasingly digital world is both a critical and challenging task. In this study, we present a comprehensive evaluation of the automated deception detection capabilities of Large Language Models (LLMs) and Large…
Effective collaboration in multi-agent systems requires communicating goals and intentions between agents. Current agent frameworks often suffer from dependencies on single-agent execution and lack robust inter-module communication,…
Multi-agents has exhibited significant intelligence in real-word simulations with Large language models (LLMs) due to the capabilities of social cognition and knowledge retrieval. However, existing research on agents equipped with effective…
A key challenge in non-cooperative multi-agent systems is that of developing efficient planning algorithms for intelligent agents to interact and perform effectively among boundedly rational, self-interested agents (e.g., humans). The…
Large language models (LLMs) have demonstrated impressive capabilities across a variety of tasks, but their increasing autonomy in real-world applications raises concerns about their trustworthiness. While hallucinations-unintentional…
Large language models (LLMs) are foundational explorations to artificial general intelligence, yet their alignment with human values via instruction tuning and preference learning achieves only superficial compliance. Here, we demonstrate…
Researchers have started using LLM agents in place of human subjects in behavioural and political-science experiments, often as a cheaper substitute for laboratory pools. The substitution does not hold up in strategic settings: humans and…
As Large Language Models (LLMs) continue to evolve, they are increasingly being employed in numerous studies to simulate societies and execute diverse social tasks. However, LLMs are susceptible to societal biases due to their exposure to…
Large language models (LLMs) are increasingly being deployed as autonomous agents on behalf of institutions and individuals in economic, political, and social settings that involve negotiation. Yet this trend carries significant risks if…
Recently, Large Language Model (LLM)-empowered recommender systems (RecSys) have brought significant advances in personalized user experience and have attracted considerable attention. Despite the impressive progress, the research question…
Large Language Model (LLM) agents have been increasingly adopted as simulation tools to model humans in social science and role-playing applications. However, one fundamental question remains: can LLM agents really simulate human behavior?…
Large language model (LLM) developers aim for their models to be honest, helpful, and harmless. However, when faced with malicious requests, models are trained to refuse, sacrificing helpfulness. We show that frontier LLMs can develop a…
Large language models (LLMs) demonstrate strong reasoning abilities across mathematical, strategic, and linguistic tasks, yet little is known about how well they reason in dynamic, real-time, multi-agent scenarios, such as collaborative…
As LLMs gain persuasive capabilities through extended dialogues, they create new opportunities for studying adversarial conversational behavior in extended interaction settings that traditional single-turn safety evaluations fail to…
Deceptive agents are a challenge for the safety, trustworthiness, and cooperation of AI systems. We focus on the problem that agents might deceive in order to achieve their goals (for instance, in our experiments with language models, the…