Increased healthcare demand is significantly straining European services. Digital solutions including advanced modelling techniques offer a promising solution to optimising patient flow without impacting day-to-day healthcare provision. In this work we outline an ongoing project that aims to optimise healthcare resources using agent-based simulations.

We develop a method that integrates the tree of thoughts and multi-agent framework to enhance the capability of pre-trained language models in solving complex, unfamiliar games. The method decomposes game-solving into four incremental tasks -- game summarization, area selection, action extraction, and action validation -- each assigned to a specific language-model agent. By constructing a tree of thoughts, the method simulates reasoning paths and allows agents to collaboratively distill game representations and tactics, mitigating the limitations of language models in reasoning and long-term memorization. Additionally, an automated fine-tuning process further optimizes the agents' performance by ranking query-response pairs based on game outcomes, e.g., winning or losing. We apply the method to a non-cooperative game and demonstrate a 65 percent winning rate against benchmark algorithms, with an additional 10 percent improvement after fine-tuning. In contrast to existing deep learning algorithms for game solving that require millions of training samples, the proposed method consumes approximately 1000 training samples, highlighting its efficiency and scalability.

We study a fair division model where indivisible items arrive sequentially, and must be allocated immediately and irrevocably. Previous work on online fair division has shown impossibility results in achieving approximate envy-freeness under these constraints. In contrast, we consider an informed setting where the algorithm has complete knowledge of future items, and aim to ensure that the cumulative allocation at each round satisfies approximate envy-freeness -- which we define as temporal envy-freeness up to one item (TEF1). We focus on settings where items can be exclusively goods or exclusively chores. For goods, while TEF1 allocations may not always exist, we identify several special cases where they do -- two agents, two item types, generalized binary valuations, unimodal preferences -- and provide polynomial-time algorithms for these cases. We also prove that determining the existence of a TEF1 allocation is NP-hard. For chores, we establish analogous results for the special cases, but present a slightly weaker intractability result. We also establish the incompatibility between TEF1 and Pareto-optimality, with the implication that it is intractable to find a TEF1 allocation that maximizes any $p$-mean welfare, even for two agents.

We conducted experiments comparing the effectiveness of using simpler versus more complex dataset in different stages of the post-training process to better understand the optimal post-training strategy for large language models. Here we conduct comparison experiment on two kinds of instructions: simple instructions and specialized instructions, denoted as type 1 and type 2. As showen in Table 10, we observe that performing SFT on simpler instructions helps the model to establish a foundational level of instruction-following ability. This is reflected in moderate performance on AlpacaEval 2 (LC 16.25%, WR 17.62%) but lower performance on the more challenging Arena-Hard benchmark (WR 10.7%). When the model is fine-tuned on more specialized and complex data, there is a marginal improvement (LC 14.70%, WR 16.01%, Arena-Hard WR 14.7%), and the significant performance gains are achieved when DPO is applied after SFT. For example, SFT followed by DPO with complex, specialized instructions yields substantial improvements (LC 21.64%, WR 30.06%,

Deep generative models are becoming increasingly used as tools for financial analysis. However, it is unclear how these models will influence financial markets, especially when they infer financial value in a semi-autonomous way. In this work, we explore the interplay between deep generative models and market dynamics. We develop a form of virtual traders that use deep generative models to make buy/sell decisions, which we term neuro-symbolic traders, and expose them to a virtual market. Under our framework, neuro-symbolic traders are agents that use vision-language models to discover a model of the fundamental value of an asset. Agents develop this model as a stochastic differential equation, calibrated to market data using gradient descent. We test our neuro-symbolic traders on both synthetic data and real financial time series, including an equity stock, commodity, and a foreign exchange pair. We then expose several groups of neuro-symbolic traders to a virtual market environment. This market environment allows for feedback between the traders belief of the underlying value to the observed price dynamics. We find that this leads to price suppression compared to the historical data, highlighting a future risk to market stability. Our work is a first step towards quantifying the effect of deep generative agents on markets dynamics and sets out some of the potential risks and benefits of this approach in the future.

Large language models (LLMs) are susceptible to persuasion, which can pose risks when models are faced with an adversarial interlocutor. We take a first step towards defending models against persuasion while also arguing that defense against adversarial (i.e. negative) persuasion is only half of the equation: models should also be able to accept beneficial (i.e. positive) persuasion to improve their answers. We show that optimizing models for only one side results in poor performance on the other. In order to balance positive and negative persuasion, we introduce Persuasion-Balanced Training (or PBT), which leverages multi-agent recursive dialogue trees to create data and trains models via preference optimization to accept persuasion when appropriate. PBT consistently improves resistance to misinformation and resilience to being challenged while also resulting in the best overall performance on holistic data containing both positive and negative persuasion. Crucially, we show that PBT models are better teammates in multi-agent debates. We find that without PBT, pairs of stronger and weaker models have unstable performance, with the order in which the models present their answers determining whether the team obtains the stronger or weaker model's performance. PBT leads to better and more stable results and less order dependence, with the stronger model consistently pulling the weaker one up.

CybORG++ is an advanced toolkit for reinforcement learning research focused on network defence. Building on the CAGE 2 CybORG environment, it introduces key improvements, including enhanced debugging capabilities, refined agent implementation support, and a streamlined environment that enables faster training and easier customisation. Along with addressing several software bugs from its predecessor, CybORG++ introduces MiniCAGE, a lightweight version of CAGE 2, which improves performance dramatically, up to 1000x faster execution in parallel iterations, without sacrificing accuracy or core functionality. CybORG++ serves as a robust platform for developing and evaluating defensive agents, making it a valuable resource for advancing enterprise network defence research.

Responsibility is one of the key notions in machine ethics and in the area of autonomous systems. It is a multi-faceted notion involving counterfactual reasoning about actions and strategies. In this paper, we study different variants of responsibility in a strategic setting based on LTLf. We show a connection with notions in reactive synthesis, including synthesis of winning, dominant, and best-effort strategies. This connection provides the building blocks for a computational grounding of responsibility including complexity characterizations and sound, complete, and optimal algorithms for attributing and anticipating responsibility.

In the last two decades, Alternating-time Temporal Logic (ATL) has been proved to be very useful in modeling strategic reasoning for Multi-Agent Systems (MAS). However, this logic struggles to capture the bounded rationality inherent in human decision-making processes. To overcome these limitations, Natural Alternating-time Temporal Logic (NatATL) has been recently introduced. As an extension of ATL, NatATL incorporates bounded memory constraints into agents' strategies, which allows to resemble human cognitive limitations. In this paper, we present a model checker tool for NatATL specifications - both for memoryless strategies and strategies with recall - integrated into VITAMIN, an open-source model checker designed specifically for MAS verification. By embedding NatATL into VITAMIN, we transform theoretical advancements into a practical verification framework, enabling comprehensive analysis and validation of strategic reasoning in complex multi-agent environments. Our novel tool paves the way for applications in areas such as explainable AI and human-in-the-loop systems, highlighting NatATL's substantial potential.

AI agents will be predictable in certain ways that traditional agents are not. Where and how can we leverage this predictability in order to improve social welfare? We study this question in a game-theoretic setting where one agent can pay a fixed cost to simulate the other in order to learn its mixed strategy. As a negative result, we prove that, in contrast to prior work on pure-strategy simulation, enabling mixed-strategy simulation may no longer lead to improved outcomes for both players in all so-called "generalised trust games". In fact, mixed-strategy simulation does not help in any game where the simulatee's action can depend on that of the simulator. We also show that, in general, deciding whether simulation introduces Pareto-improving Nash equilibria in a given game is NP-hard. As positive results, we establish that mixed-strategy simulation can improve social welfare if the simulator has the option to scale their level of trust, if the players face challenges with both trust and coordination, or if maintaining some level of privacy is essential for enabling cooperation.