This report provides an overview of the workshop titled Autonomy and Safety Assurance in the Early Development of Robotics and Autonomous Systems, hosted by the Centre for Robotic Autonomy in Demanding and Long-Lasting Environments (CRADLE) on September 2, 2024, at The University of Manchester, UK. The event brought together representatives from six regulatory and assurance bodies across diverse sectors to discuss challenges and evidence for ensuring the safety of autonomous and robotic systems, particularly autonomous inspection robots (AIR). The workshop featured six invited talks by the regulatory and assurance bodies. CRADLE aims to make assurance an integral part of engineering reliable, transparent, and trustworthy autonomous systems. Key discussions revolved around three research questions: (i) challenges in assuring safety for AIR; (ii) evidence for safety assurance; and (iii) how assurance cases need to differ for autonomous systems. Following the invited talks, the breakout groups further discussed the research questions using case studies from ground (rail), nuclear, underwater, and drone-based AIR. This workshop offered a valuable opportunity for representatives from industry, academia, and regulatory bodies to discuss challenges related to assured autonomy. Feedback from participants indicated a strong willingness to adopt a design-for-assurance process to ensure that robots are developed and verified to meet regulatory expectations.

We introduce Simulation Streams, a programming paradigm designed to efficiently control and leverage Large Language Models (LLMs) for complex, dynamic simulations and agentic workflows. Our primary goal is to create a minimally interfering framework that harnesses the agentic abilities of LLMs while addressing their limitations in maintaining consistency, selectively ignoring/including information, and enforcing strict world rules. Simulation Streams achieves this through a state-based approach where variables are modified in sequential steps by "operators," producing output on a recurring format and adhering to consistent rules for state variables. This approach focus the LLMs on defined tasks, while aiming to have the context stream remain "in-distribution". The approach incorporates an Entity-Component-System (ECS) architecture to write programs in a more intuitive manner, facilitating reuse of workflows across different components and entities. This ECS approach enhances the modularity of the output stream, allowing for complex, multi-entity simulations while maintaining format consistency, information control, and rule enforcement. It is supported by a custom editor that aids in creating, running, and analyzing simulations. We demonstrate the versatility of simulation streams through an illustrative example of an ongoing market economy simulation, a social simulation of three characters playing a game of catch in a park and a suite of classical reinforcement learning benchmark tasks. These examples showcase Simulation Streams' ability to handle complex, evolving scenarios over 100s-1000s of iterations, facilitate comparisons between different agent workflows and models, and maintain consistency and continued interesting developments in LLM-driven simulations.

Designing learning agents that explore efficiently in a complex environment has been widely recognized as a fundamental challenge in reinforcement learning. While a number of works have demonstrated the effectiveness of techniques based on randomized value functions on a single agent, it remains unclear, from a theoretical point of view, whether injecting randomization can help a society of agents {\it concurently} explore an environment. The theoretical results %that we established in this work tender an affirmative answer to this question. We adapt the concurrent learning framework to \textit{randomized least-squares value iteration} (RLSVI) with \textit{aggregated state representation}. We demonstrate polynomial worst-case regret bounds in both finite- and infinite-horizon environments. In both setups the per-agent regret decreases at an optimal rate of $\Theta\left(\frac{1}{\sqrt{N}}\right)$, highlighting the advantage of concurent learning. Our algorithm exhibits significantly lower space complexity compared to \cite{russo2019worst} and \cite{agrawal2021improved}. We reduce the space complexity by a factor of $K$ while incurring only a $\sqrt{K}$ increase in the worst-case regret bound, compared to \citep{agrawal2021improved,russo2019worst}. Additionally, we conduct numerical experiments to demonstrate our theoretical findings.

Autonomous systems are increasingly expected to operate in the presence of adversaries, though an adversary may infer sensitive information simply by observing a system, without even needing to interact with it. Therefore, in this work we present a deceptive decision-making framework that not only conceals sensitive information, but in fact actively misleads adversaries about it. We model autonomous systems as Markov decision processes, and we consider adversaries that attempt to infer their reward functions using inverse reinforcement learning. To counter such efforts, we present two regularization strategies for policy synthesis problems that actively deceive an adversary about a system's underlying rewards. The first form of deception is ``diversionary'', and it leads an adversary to draw any false conclusion about what the system's reward function is. The second form of deception is ``targeted'', and it leads an adversary to draw a specific false conclusion about what the system's reward function is. We then show how each form of deception can be implemented in policy optimization problems, and we analytically bound the loss in total accumulated reward that is induced by deception. Next, we evaluate these developments in a multi-agent sequential decision-making problem with one real agent and multiple decoys. We show that diversionary deception can cause the adversary to believe that the most important agent is the least important, while attaining a total accumulated reward that is $98.83\%$ of its optimal, non-deceptive value. Similarly, we show that targeted deception can make any decoy appear to be the most important agent, while still attaining a total accumulated reward that is $99.25\%$ of its optimal, non-deceptive value.

Modern science emerged from reasoning over repeatedly-observed planetary motions. We present Gravity-Bench-v1, an environment-based benchmark that challenges AI agents on tasks that parallel this historical development. Gravity-Bench-v1 evaluates agents on the discovery of physics concealed within a dynamic environment, using rigorous gravitational dynamics simulations. Gravity-Bench includes out-of-distribution cases, i.e. with physics that deviates from the real world, to evaluate true scientific generalization capabilities. Agents must plan to collect data within an experimental budget and must perform a dynamic form of data analysis and reasoning to solve tasks efficiently. Our benchmark admits an open-ended space of solutions. PhD-level solutions for each task are provided, to calibrate AI performance against human expertise. Technically at an upper-undergraduate level, our benchmark proves challenging to baseline AI agents. Gravity-Bench-v1 and planned extensions should help map out AI progress towards scientific discovery capabilities.

We introduce a novel framework for decentralized projection-free optimization, extending projection-free methods to a broader class of upper-linearizable functions. Our approach leverages decentralized optimization techniques with the flexibility of upper-linearizable function frameworks, effectively generalizing traditional DR-submodular function optimization. We obtain the regret of $O(T^{1-\theta/2})$ with communication complexity of $O(T^{\theta})$ and number of linear optimization oracle calls of $O(T^{2\theta})$ for decentralized upper-linearizable function optimization, for any $0\le \theta \le 1$. This approach allows for the first results for monotone up-concave optimization with general convex constraints and non-monotone up-concave optimization with general convex constraints. Further, the above results for first order feedback are extended to zeroth order, semi-bandit, and bandit feedback.

Tax evasion, usually the largest component of an informal economy, is a persistent challenge over history with significant socio-economic implications. Many socio-economic studies investigate its dynamics, including influencing factors, the role and influence of taxation policies, and the prediction of the tax evasion volume over time. These studies assumed such behavior is given, as observed in the real world, neglecting the "big bang" of such activity in a population. To this end, computational economy studies adopted developments in computer simulations, in general, and recent innovations in artificial intelligence (AI), in particular, to simulate and study informal economy appearance in various socio-economic settings. This study presents a novel computational framework to examine the dynamics of tax evasion and the emergence of informal economic activity. Employing an agent-based simulation powered by Large Language Models and Deep Reinforcement Learning, the framework is uniquely designed to allow informal economic behaviors to emerge organically, without presupposing their existence or explicitly signaling agents about the possibility of evasion. This provides a rigorous approach for exploring the socio-economic determinants of compliance behavior. The experimental design, comprising model validation and exploratory phases, demonstrates the framework's robustness in replicating theoretical economic behaviors. Findings indicate that individual personality traits, external narratives, enforcement probabilities, and the perceived efficiency of public goods provision significantly influence both the timing and extent of informal economic activity. The results underscore that efficient public goods provision and robust enforcement mechanisms are complementary; neither alone is sufficient to curtail informal activity effectively.

We present a hierarchical control scheme for large-scale systems whose components can exchange information through a data network. The main goal of the supervisory layer is to find the best compromise between control performance and communicational costs by actively modifying the network topology. The actions taken at the supervisory layer alter the control agents' knowledge of the complete system, and the set of agents with which they can communicate. Each group of linked subsystems, or coalition, is independently controlled based on a decentralized model predictive control (MPC) scheme, managed at the bottom layer. Hard constraints on the inputs are imposed, while soft constraints on the states are considered to avoid feasibility issues. The performance of the proposed control scheme is validated on a model of the Dez irrigation canal, implemented on the accurate simulator for water systems SOBEK. Finally, the results are compared with those obtained using a centralized MPC controller.

I am honoured to present the International AI Safety Report. It is the work of 96 international AI experts who collaborated in an unprecedented effort to establish an internationally shared scientific understanding of risks from advanced AI and methods for managing them. We embarked on this journey just over a year ago, shortly after the countries present at the Bletchley Park AI Safety Summit agreed to support the creation of this report. Since then, we published an Interim Report in May 2024, which was presented at the AI Seoul Summit. We are now pleased to publish the present, full report ahead of the AI Action Summit in Paris in February 2025. Since the Bletchley Summit, the capabilities of general-purpose AI, the type of AI this report focuses on, have increased further. For example, new models have shown markedly better performance at tests of Professor Yoshua Bengio programming and scientific reasoning.

As industries increasingly adopt large robotic fleets, there is a pressing need for computationally efficient, practical, and optimal conflict-free path planning for multiple robots. Conflict-Based Search (CBS) is a popular method for multi-agent path finding (MAPF) due to its completeness and optimality; however, it is often impractical for real-world applications, as it is computationally intensive to solve and relies on assumptions about agents and operating environments that are difficult to realize. This article proposes a solution to overcome computational challenges and practicality issues of CBS by utilizing structural-semantic topometric maps. Instead of running CBS over large grid-based maps, the proposed solution runs CBS over a sparse topometric map containing structural-semantic cells representing intersections, pathways, and dead ends. This approach significantly accelerates the MAPF process and reduces the number of conflict resolutions handled by CBS while operating in continuous time. In the proposed method, robots are assigned time ranges to move between topometric regions, departing from the traditional CBS assumption that a robot can move to any connected cell in a single time step. The approach is validated through real-world multi-robot path-finding experiments and benchmarking simulations. The results demonstrate that the proposed MAPF method can be applied to real-world non-holonomic robots and yields significant improvement in computational efficiency compared to traditional CBS methods while improving conflict detection and resolution in cases of corridor symmetries.