This paper introduces a novel transfer learning framework for deep multi-agent reinforcement learning. The approach automatically combines goal-conditioned policies with temporal contrastive learning to discover meaningful sub-goals. The approach involves pre-training a goal-conditioned agent, finetuning it on the target domain, and using contrastive learning to construct a planning graph that guides the agent via sub-goals. Experiments on multi-agent coordination Overcooked tasks demonstrate improved sample efficiency, the ability to solve sparse-reward and long-horizon problems, and enhanced interpretability compared to baselines. The results highlight the effectiveness of integrating goal-conditioned policies with unsupervised temporal abstraction learning for complex multi-agent transfer learning. Compared to state-of-the-art baselines, our method achieves the same or better performances while requiring only 21.7% of the training samples.

Much work has been done to develop causal reasoning techniques across a number of domains, however the utilisation of causality within autonomous systems is still in its infancy. Autonomous systems would greatly benefit from the integration of causality through the use of representations such as structural causal models (SCMs). The system would be afforded a higher level of transparency, it would enable post-hoc explanations of outcomes, and assist in the online inference of exogenous variables. These qualities are either directly beneficial to the autonomous system or a valuable step in building public trust and informing regulation. To such an end we present a case study in which we describe a module-based autonomous driving system comprised of SCMs. Approaching this task requires considerations of a number of challenges when dealing with a system of great complexity and size, that must operate for extended periods of time by itself. Here we describe these challenges, and present solutions. The first of these is SCM contexts, with the remainder being three new variable categories -- two of which are based upon functional programming monads. Finally, we conclude by presenting an example application of the causal capabilities of the autonomous driving system. In this example, we aim to attribute culpability between vehicular agents in a hypothetical road collision incident.

The on-orbit intelligent planning of satellites swarm has attracted increasing attention from scholars. Especially in tasks such as the pursuit and attachment of non-cooperative satellites, satellites swarm must achieve coordinated cooperation with limited resources. The study proposes a reinforcement learning framework that integrates the transformer and expert networks. Firstly, under the constraints of incomplete information about non-cooperative satellites, an implicit multi-satellites cooperation strategy was designed using a communication sharing mechanism. Subsequently, for the characteristics of the pursuit-attachment tasks, the multi-agent reinforcement learning framework is improved by introducing transformers and expert networks inspired by transfer learning ideas. To address the issue of satellites swarm scalability, sequence modelling based on transformers is utilized to craft memory-augmented policy networks, meanwhile increasing the scalability of the swarm. By comparing the convergence curves with other algorithms, it is shown that the proposed method is qualified for pursuit-attachment tasks of satellites swarm. Additionally, simulations under different maneuvering strategies of non-cooperative satellites respectively demonstrate the robustness of the algorithm and the task efficiency of the swarm system. The success rate of pursuit-attachment tasks is analyzed through Monte Carlo simulations.

Input-output safeguards are used to detect anomalies in the traces produced by Large Language Models (LLMs) systems. These detectors are at the core of diverse safety-critical applications such as real-time monitoring, offline evaluation of traces, and content moderation. However, there is no widely recognized methodology to evaluate them. To fill this gap, we introduce the Benchmarks for the Evaluation of LLM Safeguards (BELLS), a structured collection of tests, organized into three categories: (1) established failure tests, based on already-existing benchmarks for well-defined failure modes, aiming to compare the performance of current input-output safeguards; (2) emerging failure tests, to measure generalization to never-seen-before failure modes and encourage the development of more general safeguards; (3) next-gen architecture tests, for more complex scaffolding (such as LLM-agents and multi-agent systems), aiming to foster the development of safeguards that could adapt to future applications for which no safeguard currently exists. Furthermore, we implement and share the first next-gen architecture test, using the MACHIAVELLI environment, along with an interactive visualization of the dataset.

In this paper, we investigate the dynamic emergence of traffic order in a distributed multi-agent system, aiming to minimize inefficiencies that stem from unnecessary structural impositions. We introduce a methodology for developing a dynamically-updating traffic pattern map of the airspace by leveraging information about the consistency and frequency of flow directions used by current as well as preceding traffic. Informed by this map, an agent can discern the degree to which it is advantageous to follow traffic by trading off utilities such as time and order. We show that for the traffic levels studied, for low degrees of traffic-following behavior, there is minimal penalty in terms of aircraft travel times while improving the overall orderliness of the airspace. On the other hand, heightened traffic-following behavior may result in increased aircraft travel times, while marginally reducing the overall entropy of the airspace. Ultimately, the methods and metrics presented in this paper can be used to optimally and dynamically adjust an agent's traffic-following behavior based on these trade-offs.

Autonomous agents that interact with an environment usually To alleviate this issue, one can consider methods that condition face tasks that comprise complex, entangled behaviors over the policy or the value function on the specification of long horizons. Conventional reinforcement learning (RL) the whole task (Schaul et al. 2015) and such approaches were methods have successfully addressed this. However, in cases recently also proposed for tasks with non-Markovian reward when the agent is meant to perform several tasks across similar functions (Vaezipoor et al. 2021). However, the methods that environments, training a policy for every task separately specify the whole task usually rely on a blackbox neural network can be time-consuming and requires a lot of data. In such for planning when determining which sub-goal to reach cases, the agent can utilize a method that has built-in generalization next. This makes it hard to interpret the plan to solve the task capabilities. One such method relies on the assumption and although they show promising results in practice, it is that reward functions of these tasks can be decomposed unclear whether and when these approaches will generalize into a linear combination of successor features (Barreto et al. to a new task.

We propose a simple model of protesters scattered throughout a city who want to gather into large and mobile groups. This model relies on random walkers on a street network that follow tactics built from a set of basic rules. Our goal is to identify the most important rules for fast and robust flocking of walkers. We explore a wide set of tactics and show the central importance of a specific rule based on alignment. Other rules alone perform poorly, but our experiments show that combining alignment with them enhances flocking, and that obtained groups are then remarkably robust.

In various applications, the optimal policy in a strategic decision-making problem depends both on the environmental configuration and exogenous events. For these settings, we introduce Bilevel Optimization with Contextual Markov Decision Processes (BO-CMDP), a stochastic bilevel decision-making model, where the lower level consists of solving a contextual Markov Decision Process (CMDP). BO-CMDP can be viewed as a Stackelberg Game where the leader and a random context beyond the leader's control together decide the setup of (many) MDPs that (potentially multiple) followers best respond to. This framework extends beyond traditional bilevel optimization and finds relevance in diverse fields such as model design for MDPs, tax design, reward shaping and dynamic mechanism design. We propose a stochastic Hyper Policy Gradient Descent (HPGD) algorithm to solve BO-CMDP, and demonstrate its convergence. Notably, HPGD only utilizes observations of the followers' trajectories. Therefore, it allows followers to use any training procedure and the leader to be agnostic of the specific algorithm used, which aligns with various real-world scenarios. We further consider the setting when the leader can influence the training of followers and propose an accelerated algorithm. We empirically demonstrate the performance of our algorithm.

LLM agents have become increasingly sophisticated, especially in the realm of cybersecurity. Researchers have shown that LLM agents can exploit real-world vulnerabilities when given a description of the vulnerability and toy capture-the-flag problems. However, these agents still perform poorly on real-world vulnerabilities that are unknown to the agent ahead of time (zero-day vulnerabilities). In this work, we show that teams of LLM agents can exploit real-world, zero-day vulnerabilities. Prior agents struggle with exploring many different vulnerabilities and long-range planning when used alone. To resolve this, we introduce HPTSA, a system of agents with a planning agent that can launch subagents. The planning agent explores the system and determines which subagents to call, resolving long-term planning issues when trying different vulnerabilities. We construct a benchmark of 15 real-world vulnerabilities and show that our team of agents improve over prior work by up to 4.5$\times$.

Due to their unprecedented ability to process and respond to various types of data, Multimodal Large Language Models (MLLMs) are constantly defining the new boundary of Artificial General Intelligence (AGI). As these advanced generative models increasingly form collaborative networks for complex tasks, the integrity and security of these systems are crucial. Our paper, ``The Wolf Within'', explores a novel vulnerability in MLLM societies - the indirect propagation of malicious content. Unlike direct harmful output generation for MLLMs, our research demonstrates how a single MLLM agent can be subtly influenced to generate prompts that, in turn, induce other MLLM agents in the society to output malicious content. Our findings reveal that, an MLLM agent, when manipulated to produce specific prompts or instructions, can effectively ``infect'' other agents within a society of MLLMs. This infection leads to the generation and circulation of harmful outputs, such as dangerous instructions or misinformation, across the society. We also show the transferability of these indirectly generated prompts, highlighting their possibility in propagating malice through inter-agent communication. This research provides a critical insight into a new dimension of threat posed by MLLMs, where a single agent can act as a catalyst for widespread malevolent influence. Our work underscores the urgent need for developing robust mechanisms to detect and mitigate such covert manipulations within MLLM societies, ensuring their safe and ethical utilization in societal applications.