Spatial reasoning tasks in multi-agent environments such as event prediction, agent type identification, or missing data imputation are important for multiple applications (e.g., autonomous surveillance over sensor networks and subtasks for reinforcement learning (RL)). StarCraft II game replays encode intelligent (and adversarial) multi-agent behavior and could provide a testbed for these tasks; however, extracting simple and standardized representations for prototyping these tasks is laborious and hinders reproducibility. In contrast, MNIST and CIFAR10, despite their extreme simplicity, have enabled rapid prototyping and reproducibility of ML methods. Following the simplicity of these datasets, we construct a benchmark spatial reasoning dataset based on StarCraft II replays that exhibit complex multi-agent behaviors, while still being as easy to use as MNIST and CIFAR10. Specifically, we carefully summarize a window of 255 consecutive game states to create 3.6 million summary images from 60,000 replays, including all relevant metadata such as game outcome and player races. We develop three formats of decreasing complexity: Hyperspectral images that include one channel for every unit type (similar to multispectral geospatial images), RGB images that mimic CIFAR10, and grayscale images that mimic MNIST. We show how this dataset can be used for prototyping spatial reasoning methods. All datasets, code for extraction, and code for dataset loading can be found at https://starcraftdata.davidinouye.com

We study the ability of LLMs to generate feedback for scientific papers and develop MARG, a feedback generation approach using multiple LLM instances that engage in internal discussion. By distributing paper text across agents, MARG can consume the full text of papers beyond the input length limitations of the base LLM, and by specializing agents and incorporating sub-tasks tailored to different comment types (experiments, clarity, impact) it improves the helpfulness and specificity of feedback. In a user study, baseline methods using GPT-4 were rated as producing generic or very generic comments more than half the time, and only 1.7 comments per paper were rated as good overall in the best baseline. Our system substantially improves the ability of GPT-4 to generate specific and helpful feedback, reducing the rate of generic comments from 60% to 29% and generating 3.7 good comments per paper (a 2.2x improvement).

Human communication is a complex and diverse process that not only involves multiple factors such as language, commonsense, and cultural backgrounds but also requires the participation of multimodal information, such as speech. Large Language Model (LLM)-based multi-agent systems have demonstrated promising performance in simulating human society. Can we leverage LLM-based multi-agent systems to simulate human communication? However, current LLM-based multi-agent systems mainly rely on text as the primary medium. In this paper, we propose SpeechAgents, a multi-modal LLM based multi-agent system designed for simulating human communication. SpeechAgents utilizes multi-modal LLM as the control center for individual agent and employes multi-modal signals as the medium for exchanged messages among agents. Additionally, we propose Multi-Agent Tuning to enhance the multi-agent capabilities of LLM without compromising general abilities. To strengthen and evaluate the effectiveness of human communication simulation, we build the Human-Communication Simulation Benchmark. Experimental results demonstrate that SpeechAgents can simulate human communication dialogues with consistent content, authentic rhythm, and rich emotions and demonstrate excellent scalability even with up to 25 agents, which can apply to tasks such as drama creation and audio novels generation. Code and models will be open-sourced at https://github. com/0nutation/SpeechAgents

Recently it has been shown that tensor networks (TNs) have the ability to represent the expected return of a single-agent finite Markov decision process (FMDP). The TN represents a distribution model, where all possible trajectories are considered. When extending these ideas to a multi-agent setting, distribution models suffer from the curse of dimensionality: the exponential relation between the number of possible trajectories and the number of agents. The key advantage of using TNs in this setting is that there exists a large number of established optimisation and decomposition techniques that are specific to TNs, that one can apply to ensure the most efficient representation is found. In this report, these methods are used to form a TN that represents the expected return of a multi-agent reinforcement learning (MARL) task. This model is then applied to a 2 agent random walker example, where it was shown that the policy is correctly optimised using a DMRG technique. Finally, I demonstrate the use of an exact decomposition technique, reducing the number of elements in the tensors by 97.5%, without experiencing any loss of information.

Robotic well-being coaches have been shown to successfully promote people's mental well-being. To provide successful coaching, a robotic coach should have the capability to repair the mistakes it makes. Past investigations of robot mistakes are limited to game or task-based, one-off and in-lab studies. This paper presents a 4-phase design process to design repair strategies for robotic longitudinal well-being coaching with the involvement of real-world stakeholders: 1) designing repair strategies with a professional well-being coach; 2) a longitudinal study with the involvement of experienced users (i.e., who had already interacted with a robotic coach) to investigate the repair strategies defined in (1); 3) a design workshop with users from the study in (2) to gather their perspectives on the robotic coach's repair strategies; 4) discussing the results obtained in (2) and (3) with the mental well-being professional to reflect on how to design repair strategies for robotic coaching. Our results show that users have different expectations for a robotic coach than a human coach, which influences how repair strategies should be designed. We show that different repair strategies (e.g., apologizing, explaining, or repairing empathically) are appropriate in different scenarios, and that preferences for repair strategies change during longitudinal interactions with the robotic coach.

The prominent large language models (LLMs) of today differ from past language models not only in size, but also in the fact that they are trained on a combination of natural language and formal language (code). As a medium between humans and computers, code translates high-level goals into executable steps, featuring standard syntax, logical consistency, abstraction, and modularity. In this survey, we present an overview of the various benefits of integrating code into LLMs' training data. Specifically, beyond enhancing LLMs in code generation, we observe that these unique properties of code help (i) unlock the reasoning ability of LLMs, enabling their applications to a range of more complex natural language tasks; (ii) steer LLMs to produce structured and precise intermediate steps, which can then be connected to external execution ends through function calls; and (iii) take advantage of code compilation and execution environment, which also provides diverse feedback for model improvement. In addition, we trace how these profound capabilities of LLMs, brought by code, have led to their emergence as intelligent agents (IAs) in situations where the ability to understand instructions, decompose goals, plan and execute actions, and refine from feedback are crucial to their success on downstream tasks. Finally, we present several key challenges and future directions of empowering LLMs with code.

In recent years, multi-objective optimization (MOO) emerges as a foundational problem underpinning many multi-agent multi-task learning applications. However, existing algorithms in MOO literature remain limited to centralized learning settings, which do not satisfy the distributed nature and data privacy needs of such multi-agent multi-task learning applications. This motivates us to propose a new federated multi-objective learning (FMOL) framework with multiple clients distributively and collaboratively solving an MOO problem while keeping their training data private. Notably, our FMOL framework allows a different set of objective functions across different clients to support a wide range of applications, which advances and generalizes the MOO formulation to the federated learning paradigm for the first time. For this FMOL framework, we propose two new federated multi-objective optimization (FMOO) algorithms called federated multi-gradient descent averaging (FMGDA) and federated stochastic multi-gradient descent averaging (FSMGDA). Both algorithms allow local updates to significantly reduce communication costs, while achieving the {\em same} convergence rates as those of their algorithmic counterparts in the single-objective federated learning. Our extensive experiments also corroborate the efficacy of our proposed FMOO algorithms.

Past research into robotic planning with temporal logic specifications, notably Linear Temporal Logic (LTL), was largely based on singular formulas for individual or groups of robots. But with increasing task complexity, LTL formulas unavoidably grow lengthy, complicating interpretation and specification generation, and straining the computational capacities of the planners. A recent development has been the hierarchical representation of LTL [1] that contains multiple temporal logic specifications, providing a more interpretable framework. However, the proposed planning algorithm assumes the independence of robots within each specification, limiting their application to multi-robot coordination with complex temporal constraints. In this work, we formulated a decomposition-based hierarchical framework. At the high level, each specification is first decomposed into a set of atomic sub-tasks. We further infer the temporal relations among the sub-tasks of different specifications to construct a task network. Subsequently, a Mixed Integer Linear Program is utilized to assign sub-tasks to various robots. At the lower level, domain-specific controllers are employed to execute sub-tasks. Our approach was experimentally applied to domains of robotic navigation and manipulation. The outcomes of thorough simulations, which included comparative analyses, demonstrated the effectiveness of the proposed approach.

Organizations face numerous challenges posed by unexpected events such as energy price hikes, pandemic disruptions, terrorist attacks, and natural disasters, and the factors that contribute to organizational success in dealing with such disruptions often remain unclear. This paper analyzes the roles of top-down and bottom-up organizational structures in promoting organizational resilience. To do so, an agent-based model of stylized organizations is introduced that features learning, adaptation, different modes of organizing, and environmental disruptions. The results indicate that bottom-up designed organizations tend to have a higher ability to absorb the effects of environmental disruptions, and situations are identified in which either top-down or bottom-up designed organizations have an advantage in recovering from shocks.

A technique that allows a formation-enforcing control (FEC) derived from graph rigidity theory to interface with a realistic relative localization system onboard lightweight Unmanned Aerial Vehicles (UAVs) is proposed in this paper. The proposed methodology enables reliable real-world deployment of UAVs in tight formation using real relative localization systems burdened by non-negligible sensory noise, which is typically not fully taken into account in FEC algorithms. The proposed solution is based on decomposition of the gradient descent-based FEC command into interpretable elements, and then modifying these individually based on the estimated distribution of sensory noise, such that the resulting action limits the probability of overshooting the desired formation. The behavior of the system has been analyzed and the practicality of the proposed solution has been compared to pure gradient-descent in real-world experiments where it presented significantly better performance in terms of oscillations, deviation from the desired state and convergence time.