A multi-agent system (MAS) powered by large language models (LLMs) can automate tedious user tasks such as meeting scheduling that requires inter-agent collaboration. LLMs enable nuanced protocols that account for unstructured private data, user constraints, and preferences. However, this design introduces new risks, including misalignment and attacks by malicious parties that compromise agents or steal user data. In this paper, we propose the Terrarium framework for fine-grained study on safety, privacy, and security in LLM-based MAS. We repurpose the blackboard design, an early approach in multi-agent systems, to create a modular, configurable testbed for multi-agent collaboration. We identify key attack vectors such as misalignment, malicious agents, compromised communication, and data poisoning. We implement three collaborative MAS scenarios with four representative attacks to demonstrate the framework's flexibility. By providing tools to rapidly prototype, evaluate, and iterate on defenses and designs, Terrarium aims to accelerate progress toward trustworthy multi-agent systems.

Since the COVID-19 pandemic in 2020, universities and companies have increasingly integrated hybrid features into their meeting spaces, or even created dedicated rooms for this purpose. While the importance of a fast and stable internet connection is often prioritized, the acoustic design of seminar rooms is frequently overlooked. Poor acoustics, particularly excessive reverberation, can lead to issues such as misunderstandings, reduced speech intelligibility or cognitive and vocal fatigue. This pilot study investigates whether room acoustic interventions in a seminar room at Graz University of Technology support better communication in hybrid meetings. For this purpose, we recorded two groups of persons twice, once before and once after improving the acoustics of the room. Our findings -- despite not reaching statistical significance due to the small sample size - indicate clearly that our spatial interventions improve communicative success in hybrid meetings. To make the paper accessible also for readers from the speech communication community, we explain room acoustics background, relevant for the interpretation of our results.

Behavior Trees (BTs) are high-level controllers that are useful in a variety of planning tasks and are gaining traction in robotic mission planning. As they gain popularity in safety-critical domains, it is important to formalize their syntax and semantics, as well as verify properties for them. In this paper, we formalize a class of BTs we call Stateful Behavior Trees (SBTs) that have auxiliary variables and operate in an environment that can change over time. SBTs have access to persistent shared memory (often known as a blackboard) that keeps track of these auxiliary variables. We demonstrate that SBTs are equivalent in computational power to Turing Machines when the blackboard can store mathematical (i.e., unbounded) integers. We further identify syntactic assumptions where SBTs have computational power equivalent to finite state automata, specifically where the auxiliary variables are of finitary types. We present a domain specific language (DSL) for writing SBTs and adapt the tool BehaVerify for use with this DSL. This new DSL in BehaVerify supports interfacing with popular BT libraries in Python, and also provides generation of Haskell code and nuXmv models, the latter of which is used for model checking temporal logic specifications for the SBTs. We include examples and scalability results where BehaVerify outperforms another verification tool by a factor of 100.

Online learning in a decentralized two-sided matching markets, where the demand-side (players) compete to match with the supply-side (arms), has received substantial interest because it abstracts out the complex interactions in matching platforms (e.g. UpWork, TaskRabbit). However, past works assume that each arm knows their preference ranking over the players (one-sided learning), and each player aim to learn the preference over arms through successive interactions. Moreover, several (impractical) assumptions on the problem are usually made for theoretical tractability such as broadcast player-arm match Liu et al. (2020; 2021); Kong & Li (2023) or serial dictatorship Sankararaman et al. (2021); Basu et al. (2021); Ghosh et al. (2022). In this paper, we study a decentralized two-sided matching market, where we do not assume that the preference ranking over players are known to the arms apriori. Furthermore, we do not have any structural assumptions on the problem. We propose a multi-phase explore-then-commit type algorithm namely epoch-based CA-ETC (collision avoidance explore then commit) (\texttt{CA-ETC} in short) for this problem that does not require any communication across agents (players and arms) and hence decentralized. We show that for the initial epoch length of $T_{\circ}$ and subsequent epoch-lengths of $2^{l/\gamma} T_{\circ}$ (for the $l-$th epoch with $\gamma \in (0,1)$ as an input parameter to the algorithm), \texttt{CA-ETC} yields a player optimal expected regret of $\mathcal{O}\left(T_{\circ} (\frac{K \log T}{T_{\circ} \Delta^2})^{1/\gamma} + T_{\circ} (\frac{T}{T_{\circ}})^\gamma\right)$ for the $i$-th player, where $T$ is the learning horizon, $K$ is the number of arms and $\Delta$ is an appropriately defined problem gap. Furthermore, we propose a blackboard communication based baseline achieving logarithmic regret in $T$.

Language models trained on internet-scale data sets have shown an impressive ability to solve problems in Natural Language Processing and Computer Vision. However, experience is showing that these models are frequently brittle in unexpected ways, and require significant scaffolding to ensure that they operate correctly in the larger systems that comprise "language-model agents." In this paper, we argue that behavior trees provide a unifying framework for combining language models with classical AI and traditional programming. We introduce Dendron, a Python library for programming language model agents using behavior trees. We demonstrate the approach embodied by Dendron in three case studies: building a chat agent, a camera-based infrastructure inspection agent for use on a mobile robot or vehicle, and an agent that has been built to satisfy safety constraints that it did not receive through instruction tuning or RLHF.

Deep neural networks (DNNs) detect patterns in data and have shown versatility and strong performance in many computer vision applications. However, DNNs alone are susceptible to obvious mistakes that violate simple, common sense concepts and are limited in their ability to use explicit knowledge to guide their search and decision making. While overall DNN performance metrics may be good, these obvious errors, coupled with a lack of explainability, have prevented widespread adoption for crucial tasks such as medical image analysis. The purpose of this paper is to introduce SimpleMind, an open-source software framework for Cognitive AI focused on medical image understanding. It allows creation of a knowledge base that describes expected characteristics and relationships between image objects in an intuitive human-readable form. The SimpleMind framework brings thinking to DNNs by: (1) providing methods for reasoning with the knowledge base about image content, such as spatial inferencing and conditional reasoning to check DNN outputs; (2) applying process knowledge, in the form of general-purpose software agents, that are chained together to accomplish image preprocessing, DNN prediction, and result post-processing, and (3) performing automatic co-optimization of all knowledge base parameters to adapt agents to specific problems. SimpleMind enables reasoning on multiple detected objects to ensure consistency, providing cross checking between DNN outputs. This machine reasoning improves the reliability and trustworthiness of DNNs through an interpretable model and explainable decisions. Example applications are provided that demonstrate how SimpleMind supports and improves deep neural networks by embedding them within a Cognitive AI framework.

How can we become efficient learners? Education is an essential part of society and leads to our progression in general. However, it can be difficult for some to learn as much as others, and studying can fail to hold many people's attention. Combining technology and education is another element of the technological evolution, with the common goal of making learning easier on students while at the same time producing more outstanding results. Technology can not only ease the learning process but also dissect the students' progress and provide responses accordingly.

Behavior trees (BTs) are a popular method of modeling the behavior of NPCs and enemy AI and have found widespread use in a large number of commercial games. In this paper, rather than use BTs to model game-playing agents, we demonstrate their use for modeling game design agents, defining behaviors as executing content generation tasks rather than in-game actions. Similar to how traditional BTs enable modeling behaviors in a modular and dynamic manner, BTs for PCG enable simple subtrees for generating parts of levels to be combined modularly to form more complex trees for generating whole levels as well as generators that can dynamically vary the generated content. We demonstrate this approach by using BTs to model generators for Super Mario Bros., Mega Man and Metroid levels as well as dungeon layouts and discuss several ways in which this PCGBT paradigm could be applied and extended in the future.

In 1680, Edward Lloyd arrived in London. He was 32 years old and hunting for opportunity. He found one in coffee. Fueled by this then novel beverage, London's coffeehouse scene was exploding. Over three thousand java shops were already scattered throughout the city. Was the marketplace too crowded for another competitor?

The abstraction levels represent a general progression from the test cases through available and derived values to partial and complete solutions. The abstraction levels include: - test cases; - input and output elements; - derived values (symbolic and numeric); - code fragments; - target values; - case solutions; - case set solutions; - program solutions; - solution code. The data on the blackboard represents a set of more or less promising solution fragments at different stages of identification, characterisation and elaboration. It is worth noting that progression from test cases to solution code is not a strictly linear process. Instead knowledge sources respond to changes at one or more specific abstraction levels to produce, enhance or remove elements on different levels. The blackboard model allows this to happen in more or less any order.