Related papers: Uncovering Systemic and Environment Errors in Auto…

One of the main research areas in Artificial Intelligence is the coding of agents (programs) which are able to learn by themselves in any situation. This means that agents must be useful for purposes other than those they were created for,…

Independent reinforcement learning algorithms have no theoretical guarantees for finding the best policy in multi-agent settings. However, in practice, prior works have reported good performance with independent algorithms in some domains…

In the intrinsically motivated skills acquisition problem, the agent is set in an environment without any pre-defined goals and needs to acquire an open-ended repertoire of skills. To do so the agent needs to be autotelic (deriving from the…

Large Language Models (LLMs) are increasingly deployed within agentic systems - collections of interacting, LLM-powered agents that execute complex, adaptive workflows using memory, tools, and dynamic planning. While enabling powerful new…

Despite their groundbreaking performance, autonomous agents can misbehave when training and environmental conditions become inconsistent, with minor mismatches leading to undesirable behaviors or even catastrophic failures. Robustness…

Autonomous driving (AD) systems are often built and tested in a modular fashion, where the performance of different modules is measured using task-specific metrics. These metrics should be chosen so as to capture the downstream impact of…

Autonomous systems use independent decision-making with only limited human intervention to accomplish goals in complex and unpredictable environments. As the autonomy technologies that underpin them continue to advance, these systems will…

Contemporary machine learning paradigm excels in statistical data analysis, solving problems that classical AI couldn't. However, it faces key limitations, such as a lack of integration with planning, incomprehensible internal structure,…

AI coding agents are increasingly integrated into real-world software development workflows, yet their robustness under diverse and adversarial scenarios remains poorly understood. We present ABTest, a behavior-driven fuzzing framework that…

Safe planning of an autonomous agent in interactive environments -- such as the control of a self-driving vehicle among pedestrians -- poses a major challenge as the behavior of the environment is unknown and reactive to the behavior of the…

Many software engineering tasks, such as testing, and anomaly detection can benefit from the ability to infer a behavioral model of the software.Most existing inference approaches assume access to code to collect execution sequences. In…

In order for agents trained by deep reinforcement learning to work alongside humans in realistic settings, we will need to ensure that the agents are \emph{robust}. Since the real world is very diverse, and human behavior often changes in…

The rapid advancement of artificial intelligence, particularly autonomous agentic systems based on Large Language Models (LLMs), presents new opportunities to accelerate drug discovery by improving in-silico modeling and reducing dependence…

Modelling other agents' behaviors plays an important role in decision models for interactions among multiple agents. To optimise its own decisions, a subject agent needs to model what other agents act simultaneously in an uncertain…

AI agents are autonomous systems that combine LLMs with external tools to solve complex tasks. While such tools extend capability, improper tool permissions introduce security risks such as indirect prompt injection and tool misuse. We…

Autonomous agent systems powered by Large Language Models (LLMs) have demonstrated promising capabilities in automating complex tasks. However, current evaluations largely rely on success rates without systematically analyzing the…

While multi-agent trust region algorithms have achieved great success empirically in solving coordination tasks, most of them, however, suffer from a non-stationarity problem since agents update their policies simultaneously. In contrast, a…

Given an increasing prevalence of intelligent systems capable of autonomous actions or augmenting human activities, it is important to consider scenarios in which the human, autonomous system, or both can exhibit failures as a result of one…

Software supply-chain security requires provenance mechanisms that support reproducibility and vulnerability assessment under dynamic execution conditions. Conventional Software Bills of Materials (SBOMs) provide static dependency…

Large language model-based multi-agent systems have shown great abilities across various tasks due to the collaboration of expert agents, each focusing on a specific domain. However, the impact of clumsy or even malicious agents--those who…