Multi-agent decision problems are typically solved via distributed iterative algorithms, where the agents only communicate between themselves on a peer-to-peer network. Each agent usually maintains a copy of each decision variable, while agreement among the local copies is enforced via consensus protocols. Yet, each agent is often directly influenced by a small portion of the decision variables only: neglecting this sparsity results in redundancy, poor scalability with the network size, communication and memory overhead. To address these challenges, we develop Estimation Network Design (END), a framework for the design and analysis of distributed algorithms, generalizing several recent approaches. END algorithms can be tuned to exploit problem-specific sparsity structures, by optimally allocating copies of each variable only to a subset of agents, to improve efficiency and minimize redundancy. We illustrate the END's potential by designing new algorithms for generalised Nash equilibrium (GNE) seeking under partial-decision information, that can leverage the sparsity in cost functions, constraints and aggregation values. Finally, we test numerically our methods on a unicast rate allocation problem, revealing greatly reduced communication and memory costs.

Self-supervised learning is the backbone of state of the art language modeling. It has been argued that training with predictive loss on a self-supervised dataset causes simulators: entities that internally represent possible configurations of real-world systems. Under this assumption, a mathematical model for simulators is built based in the Cartesian frames model of embedded agents, which is extended to multi-agent worlds through scaling a two-dimensional frame to arbitrary dimensions, where literature prior chooses to instead use operations on frames. This variant leveraging scaling dimensionality is named the Cartesian object, and is used to represent simulations (where individual simulacra are the agents and devices in that object). Around the Cartesian object, functions like token selection and simulation complexity are accounted for in formalizing the behavior of a simulator, and used to show (through the L\"obian obstacle) that a proof of alignment between simulacra by inspection of design is impossible in the simulator context. Following this, a scheme is proposed and termed Partial Simulation Extrapolation aimed at circumventing the L\"obian obstacle through the evaluation of low-complexity simulations.

Intelligent agents such as robots are increasingly deployed in real-world, safety-critical settings. It is vital that these agents are able to explain the reasoning behind their decisions to human counterparts; however, their behavior is often produced by uninterpretable models such as deep neural networks. We propose an approach to generate natural language explanations for an agent's behavior based only on observations of states and actions, thus making our method independent from the underlying model's representation. For such models, we first learn a behavior representation and subsequently use it to produce plausible explanations with minimal hallucination while affording user interaction with a pre-trained large language model. We evaluate our method in a multi-agent search-and-rescue environment and demonstrate the effectiveness of our explanations for agents executing various behaviors. Through user studies and empirical experiments, we show that our approach generates explanations as helpful as those produced by a human domain expert while enabling beneficial interactions such as clarification and counterfactual queries.

Robotic-assisted surgical systems have demonstrated significant potential in enhancing surgical precision and minimizing human errors. However, existing systems lack the ability to accommodate the unique preferences and requirements of individual surgeons. Additionally, they primarily focus on general surgeries (e.g., laparoscopy) and are not suitable for highly precise microsurgeries, such as ophthalmic procedures. Thus, we propose a simulation-based image-guided approach for surgeon-centered autonomous agents that can adapt to the individual surgeon's skill level and preferred surgical techniques during ophthalmic cataract surgery. Our approach utilizes a simulated environment to train reinforcement and imitation learning agents guided by image data to perform all tasks of the incision phase of cataract surgery. By integrating the surgeon's actions and preferences into the training process with the surgeon-in-the-loop, our approach enables the robot to implicitly learn and adapt to the individual surgeon's unique approach through demonstrations. This results in a more intuitive and personalized surgical experience for the surgeon. Simultaneously, it ensures consistent performance for the autonomous robotic apprentice. We define and evaluate the effectiveness of our approach using our proposed metrics; and highlight the trade-off between a generic agent and a surgeon-centered adapted agent. Moreover, our approach has the potential to extend to other ophthalmic surgical procedures, opening the door to a new generation of surgeon-in-the-loop autonomous surgical robots. We provide an open-source simulation framework for future development and reproducibility.

Motion planning is a computational problem that finds a sequence of valid trajectories, often based on surrounding agents' forecasting, environmental understanding, and historical and future contexts. It can also be viewed as a game in which agents continuously plan their next move according to other agents' intentions and the encountering environment, further achieving their ultimate goals through incremental actions. To model the dynamic planning and interaction process, we propose a novel framework, DeepEMplanner, which takes the stepwise interaction into account for fine-grained behavior learning. The ego vehicle maximizes each step motion to reach its eventual driving outcome based on the stepwise expectation from agents and its upcoming road conditions. On the other hand, the agents also follow the same philosophy to maximize their stepwise behavior under the encountering environment and the expectations from ego and other agents. Our DeepEMplanner models the interactions among ego, agents, and the dynamic environment in an autoregressive manner by interleaving the Expectation and Maximization processes. Further, we design ego-to-agents, ego-to-map, and ego-to-BEV interaction mechanisms with hierarchical dynamic key objects attention to better model the interactions. Experiments on the nuScenes benchmark show that our approach achieves state-of-the-art results.

In this paper, a pragmatic semantic communication framework that enables effective goal-oriented information sharing between two-intelligent agents is proposed. In particular, semantics is defined as the causal state that encapsulates the fundamental causal relationships and dependencies among different features extracted from data. The proposed framework leverages the emerging concept in machine learning (ML) called theory of mind (ToM). It employs a dynamic two-level (wireless and semantic) feedback mechanism to continuously fine-tune neural network components at the transmitter. Thanks to the ToM, the transmitter mimics the actual mental state of the receiver's reasoning neural network operating semantic interpretation. Then, the estimated mental state at the receiver is dynamically updated thanks to the proposed dynamic two-level feedback mechanism. At the lower level, conventional channel quality metrics are used to optimize the channel encoding process based on the wireless communication channel's quality, ensuring an efficient mapping of semantic representations to a finite constellation. Additionally, a semantic feedback level is introduced, providing information on the receiver's perceived semantic effectiveness with minimal overhead. Numerical evaluations demonstrate the framework's ability to achieve efficient communication with a reduced amount of bits while maintaining the same semantics, outperforming conventional systems that do not exploit the ToM-based reasoning.

In this paper, we introduce a novel swarm application, swarm synergy, where robots in a swarm intend to form communities. Each robot is considered to make independent decisions without any communication capability (silent agent). The proposed algorithm is based on parameters local to individual robots. Engaging scenarios are studied where the silent robots form communities without the preset conditions on the number of communities, community size, goal location of each community, and specific members in the community. Our approach allows silent robots to achieve this self-organized swarm behavior using only sensory inputs from the environment. The algorithm facilitates the formation of multiple swarm communities at arbitrary locations with unspecified goal locations. We further infer the behavior of swarm synergy to ensure the anonymity/untraceability of both robots and communities. The robots intend to form a community by sensing the neighbors, creating synergy in a bounded environment. The time to achieve synergy depends on the environment boundary and the onboard sensor's field of view. Compared to the state-of-art with similar objectives, the proposed communication-free swarm synergy shows comparative time to synergize with untraceability features.

Agent-based simulations, especially those including communication, are complex to model and execute. To help researchers deal with this complexity and to encourage modular and maintainable research software, the Python-based framework mango (modular python agent framework) has been developed. The framework enables users to quickly implement software agents with different communication protocols (e.g., TCP) and message codecs (e.g., JSON). Furthermore, mango provides various options for developing an integrated agent simulation. This includes a scheduler module, which can control the agents' tasks, a (distributed) clock mechanism for time synchronization, and a specific simulation component, which can be coupled with other (co-)simulation software. These features are complemented by modular implementation patterns and a well-evaluated performance with the ability to simulate across multiple processes to ensure scalability.

Recent advancements in large language models (LLMs) underscore their potential for responding to medical inquiries. However, ensuring that generative agents provide accurate and reliable answers remains an ongoing challenge. In this context, multi-agent debate (MAD) has emerged as a prominent strategy for enhancing the truthfulness of LLMs. In this work, we provide a comprehensive benchmark of MAD strategies for medical Q&A, along with open-source implementations. This explores the effective utilization of various strategies including the trade-offs between cost, time, and accuracy. We build upon these insights to provide a novel debate-prompting strategy based on agent agreement that outperforms previously published strategies on medical Q&A tasks.

Self-play is a technique for machine learning in multi-agent systems where a learning algorithm learns by interacting with copies of itself. Self-play is useful for generating large quantities of data for learning, but has the drawback that the agents the learner will face post-training may have dramatically different behavior than the learner came to expect by interacting with itself. For the special case of two-player constant-sum games, self-play that reaches Nash equilibrium is guaranteed to produce strategies that perform well against any post-training opponent; however, no such guarantee exists for multiplayer games. We show that in games that approximately decompose into a set of two-player constant-sum games (called constant-sum polymatrix games) where global $\epsilon$-Nash equilibria are boundedly far from Nash equilibria in each subgame (called subgame stability), any no-external-regret algorithm that learns by self-play will produce a strategy with bounded vulnerability. For the first time, our results identify a structural property of multiplayer games that enable performance guarantees for the strategies produced by a broad class of self-play algorithms. We demonstrate our findings through experiments on Leduc poker.