Related papers: Enforcement Agents: Enhancing Accountability and R…
Recent advances in reinforcement learning (RL) and Human-in-the-Loop (HitL) learning have made human-AI collaboration easier for humans to team with AI agents. Leveraging human expertise and experience with AI in intelligent systems can be…
We present a system that enables real-time interaction between human users and agents trained to control fighter jets in simulated 3D air combat scenarios. The agents are trained in a dedicated environment using Multi-Agent Reinforcement…
We present a suite of reinforcement learning environments illustrating various safety properties of intelligent agents. These problems include safe interruptibility, avoiding side effects, absent supervisor, reward gaming, safe exploration,…
We introduce Embedded Safety-Aligned Intelligence (ESAI), a theoretical framework for multi-agent reinforcement learning that embeds alignment constraints directly into agents internal representations using differentiable internal alignment…
Autonomous agents (AA) will increasingly be interacting with us in our daily lives. While we want the benefits attached to AAs, it is essential that their behavior is aligned with our values and norms. Hence, an AA will need to estimate the…
Recent advancements in automatic code generation using large language model (LLM) agent have brought us closer to the future of automated software development. However, existing single-agent approaches face limitations in generating and…
With the rapid proliferation of large language models and vision-language models, AI agents have evolved from isolated, task-specific systems into autonomous, interactive entities capable of perceiving, reasoning, and acting without human…
AI agents are AI systems that can achieve complex goals autonomously. Assessing the level of agent autonomy is crucial for understanding both their potential benefits and risks. Current assessments of autonomy often focus on specific risks…
AI Agents can perform complex operations at great speed, but just like all the humans we have ever hired, their intelligence remains fallible. Miscommunications aren't noticed, systemic biases have no counter-action, and inner monologues…
Agent-based AutoML systems rely on large language models to make complex, multi-stage decisions across data processing, model selection, and evaluation. However, existing evaluation practices remain outcome-centric, focusing primarily on…
Runtime enforcement refers to the theories, techniques, and tools for enforcing correct behavior with respect to a formal specification of systems at runtime. In this paper, we are interested in techniques for constructing runtime enforcers…
As generative AI (GenAI) agents become more common in enterprise settings, they introduce security challenges that differ significantly from those posed by traditional systems. These agents are not just LLMs; they reason, remember, and act,…
This paper summarizes in depth the state of the art of aerial swarms, covering both classical and new reinforcement-learning-based approaches for their management. Then, it proposes a hybrid AI system, integrating deep reinforcement…
Language model (LM) agents have gained significant attention for their ability to autonomously complete tasks through interactions with environments, tools, and APIs. LM agents are primarily built with prompt engineering or supervised…
Enterprise AI Assistants are increasingly deployed in domains where accuracy is paramount, making each erroneous output a potentially significant incident. This paper presents a comprehensive framework for monitoring, benchmarking, and…
The creation of effective governance mechanisms for AI agents requires a deeper understanding of their core properties and how these properties relate to questions surrounding the deployment and operation of agents in the world. This paper…
In shared autonomy, user input is combined with semi-autonomous control to achieve a common goal. The goal is often unknown ex-ante, so prior work enables agents to infer the goal from user input and assist with the task. Such methods tend…
Embodied agents operating in complex and uncertain environments face considerable challenges. While some advanced agents handle complex manipulation tasks with proficiency, their success often hinges on extensive training data to develop…
We introduce the Agent GPA (Goal-Plan-Action) framework, driven by the fundamental insight that critical agent failures emerge at the intersections of setting goals, devising plans, and executing actions. We operationalize the framework…
Entity alignment (EA) aims to identify entities referring to the same real-world object across different knowledge graphs (KGs). Recent approaches based on large language models (LLMs) typically obtain entity embeddings through knowledge…