Monetary markets serve as established resource allocation mechanisms, typically achieving efficient solutions with limited information. However, they are susceptible to market failures, particularly under the presence of public goods, externalities, or inequality of economic power. Moreover, in many resource allocating contexts, money faces social, ethical, and legal constraints. Consequently, research increasingly explores artificial currencies and non-monetary markets, with Karma emerging as a notable concept. Karma, a non-tradeable, resource-inherent currency for prosumer resources, operates on the principles of contribution and consumption of specific resources. It embodies fairness, near incentive compatibility, Pareto-efficiency, robustness to population heterogeneity, and can incentivize a reduction in resource scarcity. The literature on Karma is scattered across disciplines, varies in scope, and lacks of conceptual clarity and coherence. Thus, this study undertakes a comprehensive review of the Karma mechanism, systematically comparing its resource allocation applications and elucidating overlooked mechanism design elements. Through a systematic mapping study, this review situates Karma within its literature context, offers a structured design parameter framework, and develops a road-map for future research directions.

The study and development of AI agents have been boosted by large language models. AI agents can function as intelligent assistants and complete tasks on behalf of their users with access to tools and the ability to execute commands in their environments, Through studying and experiencing the workflow of typical AI agents, we have raised several concerns regarding their security. These potential vulnerabilities are not addressed by the frameworks used to build the agents, nor by research aimed at improving the agents. In this paper, we identify and describe these vulnerabilities in detail from a system security perspective, emphasizing their causes and severe effects. Furthermore, we introduce defense mechanisms corresponding to each vulnerability with meticulous design and experiments to evaluate their viability. Altogether, this paper contextualizes the security issues in the current development of AI agents and delineates methods to make AI agents safer and more reliable.

Ensuring fair and stable allocation of scarce resources is a fundamental challenge in a wide range of applications. Traditional literature assumes that information regarding agents' preferences, whether available centrally to the designer or held privately by the agents, is known before the allocation process (the mechanism). However, this assumption hinders application in practical settings where agents typically evaluate resources only after receiving or consuming them. Furthermore, such preference information is often noisy and expensive for the central designer to gather from all agents, thus complicating the implementation of traditional mechanisms. Examples of domains where these challenges manifest include applications where geographical and time constraints impede information collection, such as distributing resources to food banks and providing humanitarian aid to disaster areas and war zones [1, 6].

Most prior motion prediction endeavors in autonomous driving have inadequately encoded future scenarios, leading to predictions that may fail to accurately capture the diverse movements of agents (e.g., vehicles or pedestrians). To address this, we propose FutureNet, which explicitly integrates initially predicted trajectories into the future scenario and further encodes these future contexts to enhance subsequent forecasting. Additionally, most previous motion forecasting works have focused on predicting independent futures for each agent. However, safe and smooth autonomous driving requires accurately predicting the diverse future behaviors of numerous surrounding agents jointly in complex dynamic environments. Given that all agents occupy certain potential travel spaces and possess lane driving priority, we propose Lane Occupancy Field (LOF), a new representation with lane semantics for motion forecasting in autonomous driving. LOF can simultaneously capture the joint probability distribution of all road participants' future spatial-temporal positions. Due to the high compatibility between lane occupancy field prediction and trajectory prediction, we propose a novel network with future context encoding for the joint prediction of these two tasks.

The growing presence of artificially intelligent agents in everyday decision-making, from LLM assistants to autonomous vehicles, hints at a future in which conflicts may arise from each agent optimizing individual interests. In general-sum games these conflicts are apparent, where naive Reinforcement Learning agents get stuck in Pareto-suboptimal Nash equilibria. Consequently, opponent shaping has been introduced as a method with success at finding socially beneficial equilibria in social dilemmas. In this work, we introduce Advantage Alignment, a family of algorithms derived from first principles that perform opponent shaping efficiently and intuitively. This is achieved by aligning the advantages of conflicting agents in a given game by increasing the probability of mutually-benefiting actions. We prove that existing opponent shaping methods, including LOLA and LOQA, implicitly perform Advantage Alignment. Compared to these works, Advantage Alignment mathematically simplifies the formulation of opponent shaping and seamlessly works for continuous action domains. We also demonstrate the effectiveness of our algorithm in a wide range of social dilemmas, achieving state of the art results in each case, including a social dilemma version of the Negotiation Game.

From pedestrians to Kuramoto oscillators, interactions between agents govern how a multitude of dynamical systems evolve in space and time. Discovering how these agents relate to each other can improve our understanding of the often complex dynamics that underlie these systems. Recent works learn to categorize relationships between agents based on observations of their physical behavior. These approaches are limited in that the relationship categories are modelled as independent and mutually exclusive, when in real world systems categories are often interacting. In this work, we introduce a level of abstraction between the physical behavior of agents and the categories that define their behavior. To do this, we learn a mapping from the agents' states to their affinities for each category in a graph neural network. We integrate the physical proximity of agents and their affinities in a nonlinear opinion dynamics model which provides a mechanism to identify mutually exclusive categories, predict an agent's evolution in time, and control an agent's behavior. We demonstrate the utility of our model for learning interpretable categories for mechanical systems, and demonstrate its efficacy on several long-horizon trajectory prediction benchmarks where we consistently out perform existing methods.

Synthetic contact networks are useful for modeling epidemic spread and social transmission, but data to infer realistic contact patterns that take account of assortative connections at the geographic and economic levels is limited. We developed a method to generate synthetic contact networks for any region of the United States based on publicly available data. First, we generate a synthetic population of individuals within households from US census data using combinatorial optimization. Then, individuals are assigned to workplaces and schools using commute data, employment statistics, and school enrollment data. The resulting population is then connected into a realistic contact network using graph generation algorithms. We test the method on two census regions and show that the synthetic populations accurately reflect the source data. We further show that the contact networks have distinct properties compared to networks generated without a synthetic population, and that those differences affect the rate of disease transmission in an epidemiological simulation. We provide open-source software to generate a synthetic population and contact network for any area within the US.

Multi-agent reinforcement learning (MARL) tasks often utilize a centralized training with decentralized execution (CTDE) framework. QMIX is a successful CTDE method that learns a credit assignment function to derive local value functions from a global value function, defining a deterministic local policy. However, QMIX is hindered by its poor exploration strategy. While maximum entropy reinforcement learning (RL) promotes better exploration through stochastic policies, QMIX's process of credit assignment conflicts with the maximum entropy objective and the decentralized execution requirement, making it unsuitable for maximum entropy RL. In this paper, we propose an enhancement to QMIX by incorporating an additional local Q-value learning method within the maximum entropy RL framework. Our approach constrains the local Q-value estimates to maintain the correct ordering of all actions. Due to the monotonicity of the QMIX value function, these updates ensure that locally optimal actions align with globally optimal actions. We theoretically prove the monotonic improvement and convergence of our method to an optimal solution. Experimentally, we validate our algorithm in matrix games, Multi-Agent Particle Environment and demonstrate state-of-the-art performance in SMAC-v2.

AI agents aim to solve complex tasks by combining text-based reasoning with external tool calls. Unfortunately, AI agents are vulnerable to prompt injection attacks where data returned by external tools hijacks the agent to execute malicious tasks. To measure the adversarial robustness of AI agents, we introduce AgentDojo, an evaluation framework for agents that execute tools over untrusted data. To capture the evolving nature of attacks and defenses, AgentDojo is not a static test suite, but rather an extensible environment for designing and evaluating new agent tasks, defenses, and adaptive attacks. We populate the environment with 97 realistic tasks (e.g., managing an email client, navigating an e-banking website, or making travel bookings), 629 security test cases, and various attack and defense paradigms from the literature. We find that AgentDojo poses a challenge for both attacks and defenses: state-of-the-art LLMs fail at many tasks (even in the absence of attacks), and existing prompt injection attacks break some security properties but not all. We hope that AgentDojo can foster research on new design principles for AI agents that solve common tasks in a reliable and robust manner.

Existing LLMs exhibit remarkable performance on various NLP tasks, but still struggle with complex real-world tasks, even equipped with advanced strategies like CoT and ReAct. In this work, we propose the CoAct framework, which transfers the hierarchical planning and collaboration patterns in human society to LLM systems. Specifically, our CoAct framework involves two agents: (1) A global planning agent, to comprehend the problem scope, formulate macro-level plans and provide detailed sub-task descriptions to local execution agents, which serves as the initial rendition of a global plan. (2) A local execution agent, to operate within the multi-tier task execution structure, focusing on detailed execution and implementation of specific tasks within the global plan. Experimental results on the WebArena benchmark show that CoAct can re-arrange the process trajectory when facing failures, and achieves superior performance over baseline methods on long-horizon web tasks. Code is available at https://github.com/xmhou2002/CoAct.