Related papers: Interpretable Risk Mitigation in LLM Agent Systems

Large Language Models (LLMs) are effective at deceiving, when prompted to do so. But under what conditions do they deceive spontaneously? Models that demonstrate better performance on reasoning tasks are also better at prompted deception.…

Large language models (LLMs) are increasingly used as behavioral proxies for self-interested travelers in agent-based traffic models. Although more flexible and generalizable than conventional models, the practical use of these approaches…

Werewolf is an incomplete information game, which has several challenges when creating a computer agent as a player given the lack of understanding of the situation and individuality of utterance (e.g., computer agents are not capable of…

Large Language Models' (LLMs) programming capabilities enable their participation in open-source games: a game-theoretic setting in which players submit computer programs in lieu of actions. These programs offer numerous advantages,…

Quantifying the deceptive potential of Large Language Models (LLMs) is critical for AI safety, yet difficult to achieve in uncontrolled environments. This work investigates the reasoning, persuasion, and deceptive capabilities of LLMs…

Modeling subrational agents, such as humans or economic households, is inherently challenging due to the difficulty in calibrating reinforcement learning models or collecting data that involves human subjects. Existing work highlights the…

Recently, text world games have been proposed to enable artificial agents to understand and reason about real-world scenarios. These text-based games are challenging for artificial agents, as it requires an understanding of and interaction…

We propose a suite of tasks to evaluate the instrumental self-reasoning ability of large language model (LLM) agents. Instrumental self-reasoning ability could improve adaptability and enable self-modification, but it could also pose…

Machines driven by large language models (LLMs) have the potential to augment humans across various tasks, a development with profound implications for business settings where effective communication, collaboration, and stakeholder trust…

Multi-agent robotic systems are increasingly operating in real-world environments in close proximity to humans, yet are largely controlled by policy models with inscrutable deep neural network representations. We introduce a method for…

In this paper, we explore the potential of Large Language Models (LLMs) Agents in playing the strategic social deduction game, Resistance Avalon. Players in Avalon are challenged not only to make informed decisions based on dynamically…

This paper examines the reasoning capabilities of Large Language Models (LLMs) from a novel perspective, focusing on their ability to operate within formally specified, rule-governed environments. We evaluate four LLMs (Gemini 2.5 Pro and…

Agents powered by large language models (LLMs) have demonstrated strong planning and decision-making capabilities in complex embodied environments. However, such agents often suffer from inefficiencies in multi-turn interactions, frequently…

As large language models (LLMs) become increasingly capable of autonomous decision-making, they introduce new challenges and opportunities for human-AI cooperation in mixed-motive contexts. While prior research has primarily examined AI in…

Decision-making agents based on pre-trained Large Language Models (LLMs) are increasingly being deployed across various domains of human activity. While their applications are currently rather specialized, several research efforts are…

Autonomous Driving (AD) encounters significant safety hurdles in long-tail unforeseen driving scenarios, largely stemming from the non-interpretability and poor generalization of the deep neural networks within the AD system, particularly…

Large Language Models are increasingly proposed as cognitive components for robotic systems, yet their opaque decision processes make it difficult to explain success or failure in closed-loop embodied tasks. Following an empirical AI…

By formally defining the training processes of large language models (LLMs), which usually encompasses pre-training, supervised fine-tuning, and reinforcement learning with human feedback, within a single and unified machine learning…

AI agents, predominantly powered by large language models (LLMs), are vulnerable to indirect prompt injection, in which malicious instructions embedded in untrusted data can trigger dangerous agent actions. This position paper discusses our…

Protecting cyberspace requires not only advanced tools but also a shift in how we reason about threats, trust, and autonomy. Traditional cybersecurity methods rely on manual responses and brittle heuristics. To build proactive and…