We present ABIDES-MARL, a framework that combines a new multi-agent reinforcement learning (MARL) methodology with a new realistic limit-order-book (LOB) simulation system to study equilibrium behavior in complex financial market games. The system extends ABIDES-Gym by decoupling state collection from kernel interruption, enabling synchronized learning and decision-making for multiple adaptive agents while maintaining compatibility with standard RL libraries. It preserves key market features such as price-time priority and discrete tick sizes. Methodologically, we use MARL to approximate equilibrium-like behavior in multi-period trading games with a finite number of heterogeneous agents-an informed trader, a liquidity trader, noise traders, and competing market makers-all with individual price impacts. This setting bridges optimal execution and market microstructure by embedding the liquidity trader's optimization problem within a strategic trading environment. We validate the approach by solving an extended Kyle model within the simulation system, recovering the gradual price discovery phenomenon. We then extend the analysis to a liquidity trader's problem where market liquidity arises endogenously and show that, at equilibrium, execution strategies shape market-maker behavior and price dynamics. ABIDES-MARL provides a reproducible foundation for analyzing equilibrium and strategic adaptation in realistic markets and contributes toward building economically interpretable agentic AI systems for finance.

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.

As AI systems become more advanced, ensuring their alignment with a diverse range of individuals and societal values becomes increasingly critical. But how can we capture fundamental human values and assess the degree to which AI systems align with them? We introduce ValueCompass, a framework of fundamental values, grounded in psychological theory and a systematic review, to identify and evaluate human-AI alignment. We apply ValueCompass to measure the value alignment of humans and language models (LMs) across four real-world vignettes: collaborative writing, education, public sectors, and healthcare. Our findings uncover risky misalignment between humans and LMs, such as LMs agreeing with values like "Choose Own Goals", which are largely disagreed by humans. We also observe values vary across vignettes, underscoring the necessity for context-aware AI alignment strategies. This work provides insights into the design space of human-AI alignment, offering foundations for developing AI that responsibly reflects societal values and ethics.

We study how experience with asset price bubbles changes the trading strategies of reinforcement learning (RL) traders and ask whether the change in trading strategies helps to prevent future bubbles. We train the RL traders in a multi-agent market simulation platform, ABIDES, and compare the strategies of traders trained with and without bubble experience. We find that RL traders without bubble experience behave like short-term momentum traders, whereas traders with bubble experience behave like value traders. Therefore, RL traders without bubble experience amplify bubbles, whereas RL traders with bubble experience tend to suppress and sometimes prevent them. This finding suggests that learning from experience is a mechanism for a boom and bust cycle where the experience of a collapsing bubble makes future bubbles less likely for a period of time until the memory fades and bubbles become more likely to form again.

Conflict transformation and management are complex decision processes with extremely high stakes at hand and could greatly benefit from formal approaches to decision support. For this purpose we develop a general framework about how to use problem structuring methods for such purposes. More precisely we show how to transform cognitive maps to value trees in order to promote a more design-oriented approach to decision support aiming at constructing innovative solutions for conflict management purposes. We show that our findings have a much wider validity since they allow to move from a descriptive representation of a problem situation to a more prescriptive one using formal procedures and models.

Modern financial exchanges use an electronic limit order book (LOB) to store bid and ask orders for a specific financial asset. As the most fine-grained information depicting the demand and supply of an asset, LOB data is essential in understanding market dynamics. Therefore, realistic LOB simulations offer a valuable methodology for explaining empirical properties of markets. Mainstream simulation models include agent-based models (ABMs) and stochastic models (SMs). However, ABMs tend not to be grounded on real historical data, while SMs tend not to enable dynamic agent-interaction. To overcome these limitations, we propose a novel hybrid LOB simulation paradigm characterised by: (1) representing the aggregation of market events' logic by a neural stochastic background trader that is pre-trained on historical LOB data through a neural point process model; and (2) embedding the background trader in a multi-agent simulation with other trading agents. We instantiate this hybrid NS-ABM model using the ABIDES platform. We first run the background trader in isolation and show that the simulated LOB can recreate a comprehensive list of stylised facts that demonstrate realistic market behaviour. We then introduce a population of `trend' and `value' trading agents, which interact with the background trader. We show that the stylised facts remain and we demonstrate order flow impact and financial herding behaviours that are in accordance with empirical observations of real markets.

In electronic trading markets, limit order books (LOBs) provide information about pending buy/sell orders at various price levels for a given security. Recently, there has been a growing interest in using LOB data for resolving downstream machine learning tasks (e.g., forecasting). However, dealing with out-of-distribution (OOD) LOB data is challenging since distributional shifts are unlabeled in current publicly available LOB datasets. Therefore, it is critical to build a synthetic LOB dataset with labeled OOD samples serving as a testbed for developing models that generalize well to unseen scenarios. In this work, we utilize a multi-agent market simulator to build a synthetic LOB dataset, named DSLOB, with and without market stress scenarios, which allows for the design of controlled distributional shift benchmarking. Using the proposed synthetic dataset, we provide a holistic analysis on the forecasting performance of three different state-of-the-art forecasting methods. Our results reflect the need for increased researcher efforts to develop algorithms with robustness to distributional shifts in high-frequency time series data.

We develop a methodology for detecting asset bubbles using a neural network. We rely on the theory of local martingales in continuous-time and use a deep network to estimate the diffusion coefficient of the price process more accurately than the current estimator, obtaining an improved detection of bubbles. We show the outperformance of our algorithm over the existing statistical method in a laboratory created with simulated data. We then apply the network classification to real data and build a zero net exposure trading strategy that exploits the risky arbitrage emanating from the presence of bubbles in the US equity market from 2006 to 2008. The profitability of the strategy provides an estimation of the economical magnitude of bubbles as well as support for the theoretical assumptions relied on.

The scientific method has guided the development of science over the last four hundred years. The method involves carefully recording observations, formulating a meaningful hypothesis, and rigorously testing the hypothesis. Based on the outcomes of these tests, the hypothesis is refined over and over again till it can explain the observations. Scientists are taught correlation does not imply causation. For them, it is not enough to know that something happens; they need to understand the underlying mechanisms that cause it to happen.

Lack of trust: One of the biggest difficulty for AI or ML products is lack of trust. Millions of dollars have been spent on prototyping but with very little success in the real-world launches. Essentially, one of the most fundamental values of doing business and providing value to customers is trust, and Artificial Intelligence is the most-heavily debated technology when it comes to ethical concerns and related trust issues. Trust comes from involving different options and parties in the entire development phase, which is not done in the prototype phase. The complexity of a launch: Building a prototype is easy, but there are tens of other external entities that need to be considered when moving into the real world.