Self-interested behavior from individuals can collectively lead to poor societal outcomes. These outcomes can seemingly be improved through the actions of altruistic agents, which benefit other agents in the system. However, it is known in specific contexts that altruistic agents can actually induce worse outcomes compared to a fully selfish population -- a phenomenon we term altruistic perversity. This paper provides a holistic investigation into the necessary conditions that give rise to altruistic perversity. In particular, we study the class of two-strategy population games where one sub-population is altruistic and the other is selfish. We find that a population game can admit altruistic perversity only if the associated social welfare function is convex and the altruistic population is sufficiently large. Our results are a first step in establishing a connection between properties of nominal agent interactions and the potential impacts from altruistic behaviors.

In recent advancements in Multi-agent Reinforcement Learning (MARL), its application has extended to various safety-critical scenarios. However, most methods focus on online learning, which presents substantial risks when deployed in real-world settings. Addressing this challenge, we introduce an innovative framework integrating diffusion models within the MARL paradigm. This approach notably enhances the safety of actions taken by multiple agents through risk mitigation while modeling coordinated action. Our framework is grounded in the Centralized Training with Decentralized Execution (CTDE) architecture, augmented by a Diffusion Model for prediction trajectory generation. Additionally, we incorporate a specialized algorithm to further ensure operational safety. We evaluate our model against baselines on the DSRL benchmark. Experiment results demonstrate that our model not only adheres to stringent safety constraints but also achieves superior performance compared to existing methodologies. This underscores the potential of our approach in advancing the safety and efficacy of MARL in real-world applications.

We propose MToMnet - a Theory of Mind (ToM) neural network for predicting beliefs and their dynamics during human social interactions from multimodal input. ToM is key for effective nonverbal human communication and collaboration, yet, existing methods for belief modelling have not included explicit ToM modelling or have typically been limited to one or two modalities. MToMnet encodes contextual cues (scene videos and object locations) and integrates them with person-specific cues (human gaze and body language) in a separate MindNet for each person. Inspired by prior research on social cognition and computational ToM, we propose three different MToMnet variants: two involving fusion of latent representations and one involving re-ranking of classification scores. We evaluate our approach on two challenging real-world datasets, one focusing on belief prediction, while the other examining belief dynamics prediction. Our results demonstrate that MToMnet surpasses existing methods by a large margin while at the same time requiring a significantly smaller number of parameters. Taken together, our method opens up a highly promising direction for future work on artificial intelligent systems that can robustly predict human beliefs from their non-verbal behaviour and, as such, more effectively collaborate with humans.

The primary objective of Multi-Agent Pathfinding (MAPF) is to plan efficient and conflict-free paths for all agents. Traditional multi-agent path planning algorithms struggle to achieve efficient distributed path planning for multiple agents. In contrast, Multi-Agent Reinforcement Learning (MARL) has been demonstrated as an effective approach to achieve this objective. By modeling the MAPF problem as a MARL problem, agents can achieve efficient path planning and collision avoidance through distributed strategies under partial observation. However, MARL strategies often lack cooperation among agents due to the absence of global information, which subsequently leads to reduced MAPF efficiency. To address this challenge, this letter introduces a unique reward shaping technique based on Independent Q-Learning (IQL). The aim of this method is to evaluate the influence of one agent on its neighbors and integrate such an interaction into the reward function, leading to active cooperation among agents. This reward shaping method facilitates cooperation among agents while operating in a distributed manner. The proposed approach has been evaluated through experiments across various scenarios with different scales and agent counts. The results are compared with those from other state-of-the-art (SOTA) planners. The evidence suggests that the approach proposed in this letter parallels other planners in numerous aspects, and outperforms them in scenarios featuring a large number of agents.

Contemporary robots have become exceptionally skilled at achieving specific tasks in structured environments. However, they often fail when faced with the limitless permutations of real-world unstructured environments. This motivates robotics methods which learn from experience, rather than follow a pre-defined set of rules. In this thesis, we present a range of learning-based methods aimed at enabling robots, operating in dynamic and unstructured environments, to better understand their surroundings, anticipate the actions of others, and take informed actions accordingly. In the first part of the thesis, we investigate methods which leverage learning to represent the structure and motion in a robot's operating environment, in a continuous manner.

Software agents have emerged as promising tools for addressing complex software engineering tasks. Existing works, on the other hand, frequently oversimplify software development workflows, despite the fact that such workflows are typically more complex in the real world. Thus, we propose AgileCoder, a multi agent system that integrates Agile Methodology (AM) into the framework. This system assigns specific AM roles - such as Product Manager, Developer, and Tester to different agents, who then collaboratively develop software based on user inputs. AgileCoder enhances development efficiency by organizing work into sprints, focusing on incrementally developing software through sprints. Additionally, we introduce Dynamic Code Graph Generator, a module that creates a Code Dependency Graph dynamically as updates are made to the codebase. This allows agents to better comprehend the codebase, leading to more precise code generation and modifications throughout the software development process. AgileCoder surpasses existing benchmarks, like ChatDev and MetaGPT, establishing a new standard and showcasing the capabilities of multi agent systems in advanced software engineering environments.

We provide a distributed coordination paradigm that enables scalable and near-optimal joint motion planning among multiple robots. Our coordination paradigm contrasts with current paradigms that are either near-optimal but impractical for replanning times or real-time but offer no near-optimality guarantees. We are motivated by the future of collaborative mobile autonomy, where distributed teams of robots will coordinate via vehicle-to-vehicle (v2v) communication to execute information-heavy tasks like mapping, surveillance, and target tracking. To enable rapid distributed coordination, we must curtail the explosion of information-sharing across the network, thus limiting robot coordination. However, this can lead to suboptimal plans, causing overlapping trajectories instead of complementary ones. We make theoretical and algorithmic contributions to balance the trade-off between decision speed and optimality. We introduce tools for distributed submodular optimization, a diminishing returns property in information-gathering tasks. Theoretically, we analyze how local network topology affects near-optimality at the global level. Algorithmically, we provide a communication- and computation-efficient coordination algorithm for agents to balance the trade-off. Our algorithm is up to two orders faster than competitive near-optimal algorithms. In simulations of surveillance tasks with up to 45 robots, it enables real-time planning at the order of 1 Hz with superior coverage performance. To enable the simulations, we provide a high-fidelity simulator that extends AirSim by integrating a collaborative autonomy pipeline and simulating v2v communication delays.

Optimizing the fuel cycle cost through the optimization of nuclear reactor core loading patterns involves multiple objectives and constraints, leading to a vast number of candidate solutions that cannot be explicitly solved. To advance the state-of-the-art in core reload patterns, we have developed methods based on Deep Reinforcement Learning (DRL) for both single- and multi-objective optimization. Our previous research has laid the groundwork for these approaches and demonstrated their ability to discover high-quality patterns within a reasonable time frame. On the other hand, stochastic optimization (SO) approaches are commonly used in the literature, but there is no rigorous explanation that shows which approach is better in which scenario. In this paper, we demonstrate the advantage of our RL-based approach, specifically using Proximal Policy Optimization (PPO), against the most commonly used SO-based methods: Genetic Algorithm (GA), Parallel Simulated Annealing (PSA) with mixing of states, and Tabu Search (TS), as well as an ensemble-based method, Prioritized Replay Evolutionary and Swarm Algorithm (PESA). We found that the LP scenarios derived in this paper are amenable to a global search to identify promising research directions rapidly, but then need to transition into a local search to exploit these directions efficiently and prevent getting stuck in local optima. PPO adapts its search capability via a policy with learnable weights, allowing it to function as both a global and local search method. Subsequently, we compared all algorithms against PPO in long runs, which exacerbated the differences seen in the shorter cases. Overall, the work demonstrates the statistical superiority of PPO compared to the other considered algorithms.

The design of alloys is a multi-scale problem that requires a holistic approach that involves retrieving relevant knowledge, applying advanced computational methods, conducting experimental validations, and analyzing the results, a process that is typically reserved for human experts. Machine learning (ML) can help accelerate this process, for instance, through the use of deep surrogate models that connect structural features to material properties, or vice versa. However, existing data-driven models often target specific material objectives, offering limited flexibility to integrate out-of-domain knowledge and cannot adapt to new, unforeseen challenges. Here, we overcome these limitations by leveraging the distinct capabilities of multiple AI agents that collaborate autonomously within a dynamic environment to solve complex materials design tasks. The proposed physics-aware generative AI platform, AtomAgents, synergizes the intelligence of large language models (LLM) the dynamic collaboration among AI agents with expertise in various domains, including knowledge retrieval, multi-modal data integration, physics-based simulations, and comprehensive results analysis across modalities that includes numerical data and images of physical simulation results. The concerted effort of the multi-agent system allows for addressing complex materials design problems, as demonstrated by examples that include autonomously designing metallic alloys with enhanced properties compared to their pure counterparts. Our results enable accurate prediction of key characteristics across alloys and highlight the crucial role of solid solution alloying to steer the development of advanced metallic alloys. Our framework enhances the efficiency of complex multi-objective design tasks and opens new avenues in fields such as biomedical materials engineering, renewable energy, and environmental sustainability.

In various industrial fields of human social development, people have been exploring methods aimed at freeing human labor. Constructing LLM-based agents is considered to be one of the most effective tools to achieve this goal. Agent, as a kind of human-like intelligent entity with the ability of perception, planning, decision-making, and action, has created great production value in many fields. However, the bridge O\&M field shows a relatively low level of intelligence compared to other industries. Nevertheless, the bridge O\&M field has developed numerous intelligent inspection devices, machine learning algorithms, and autonomous evaluation and decision-making methods, which provide a feasible basis for breakthroughs in artificial intelligence in this field. The aim of this study is to explore the impact of AI bodies based on large-scale language models on the field of bridge O\&M and to analyze the potential challenges and opportunities it brings to the core tasks of bridge O\&M. Through in-depth research and analysis, this paper expects to provide a more comprehensive perspective for understanding the application of intelligentsia in this field.