Why we think this paper is great for you:
This paper directly explores how multi-agent reinforcement learning can be used for price formation and execution. It offers a sophisticated approach to understanding and optimizing pricing strategies.

Abstract
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.

AI Summary

• It successfully validates its approach by recovering gradual price discovery in an extended Kyle model, demonstrating the ability to relax restrictive analytical assumptions such as perfect competition and linear policies. [3]
• ABIDES-MARL introduces a novel system architecture that decouples kernel interruption from state collection, enabling synchronized learning and decision-making for multiple adaptive agents within a limit-order-book (LOB) simulation. [2]
• The framework provides a new methodology using MARL to approximate equilibrium-like behavior in multi-period trading games with a finite number of heterogeneous agents, bridging market microstructure and optimal execution research. [2]
• The system enables the study of optimal execution where market liquidity arises endogenously from strategic interactions between trading and liquidity-provision sides, rather than being exogenously specified. [2]
• ABIDES-MARL offers a reproducible foundation for analyzing equilibrium and strategic adaptation in realistic financial markets, contributing to the development of economically interpretable agentic AI systems. [2]
• The inclusion of an informed trader is critical for restoring non-trivial equilibrium dynamics in the full game, preventing degenerate outcomes where market makers dominate price formation against liquidity traders. [2]
• A pro-rata order assignment mechanism is proposed, ensuring a unique, unanimous transaction price across all traders and establishing a zero-sum game structure among competing market makers. [2]
• ABIDES-MARL: A framework combining a multi-agent reinforcement learning (MARL) methodology with a realistic limit-order-book (LOB) simulation system to study equilibrium behavior in complex financial market games. [2]
• Pro-rata order assignment mechanism: A method where market orders are allocated among market makers proportionally to their market depth (inverse of their impact coefficient), ensuring a common VWAP and competitive quoting. [2]
• StopSignalAgent: A dedicated agent in ABIDES-MARL responsible for exclusively interrupting the simulation kernel, synchronizing all RL agents, and enforcing a configured order for their actions (sequential or simultaneous). [1]

Why we think this paper is great for you:
This research investigates the application of Large Language Models to improve supply chain processes, particularly focusing on green supply chains. It provides valuable insights into leveraging AI for complex supply chain challenges.

Abstract
Organizations increasingly use Large Language Models (LLMs) to improve supply chain processes and reduce environmental impacts. However, LLMs have been shown to reproduce biases regarding the prioritization of sustainable business strategies. Thus, it is important to identify underlying training data biases that LLMs pertain regarding the importance and role of sustainable business and supply chain practices. This study investigates how different LLMs respond to validated surveys about the role of ethics and responsibility for businesses, and the importance of sustainable practices and relations with suppliers and customers. Using standardized questionnaires, we systematically analyze responses generated by state-of-the-art LLMs to identify variations. We further evaluate whether differences are augmented by four organizational culture types, thereby evaluating the practical relevance of identified biases. The findings reveal significant systematic differences between models and demonstrate that organizational culture prompts substantially modify LLM responses. The study holds important implications for LLM-assisted decision-making in sustainability contexts.

Why we think this paper is great for you:
This paper analyzes how disruptions propagate through production networks, offering critical insights into supply chain resilience and structure. Understanding these dynamics is essential for robust supply chain management.

Abstract
We introduce a parsimonious multi-sector model of international production and use it to study the impact of a disruption in the production of some goods propagates to other goods and consumers, and how that impact depends on the goods' positions in, and overall structure of, the production network. We show that the short-run impact of a disruption can be dramatically larger than the long-run impact. The short-run disruption depends on the value of all of the final goods whose supply chains involve a disrupted good, while by contrast the long-run disruption depends only on the cost of the disrupted goods. We use the model to show how increased complexity of supply chains leads to increased fragility in terms of the probability and expected short-run size of a disruption. We also show how decreased transportation costs can lead to increased specialization in production, lowering the chances for disruption but increasing the impact conditional upon disruption. We use the model to characterize the power that a country has over others via diversions of its production as well as quotas on imports and exports.

Why we think this paper is great for you:
This research examines consumer decision-making based on price thresholds, which is fundamental to understanding demand and setting effective prices. It provides a behavioral perspective on pricing strategies.

Abstract
To choose between two discrete goods, a consumer pays attention to only those with prices below a threshold. From these, she chooses her most preferred good. We assume consumers in a population have the same preference but may have different thresholds. Similar models of bounded rationality have been studied in the empirical marketing literature. We fully characterize the model, and using observational choice data alone, we identify the welfare implications of a price change. The behavioral content of our model overlaps with an important class of random utility models, but the welfare implications are meaningfully different. The distribution of equivalent variation under our model first-order stochastically dominates that under the random utility model.

Why we think this paper is great for you:
This paper presents a method for finding optimal solutions to complex problems by training models to estimate subproblem values. This approach is highly relevant for developing advanced optimization techniques.

Abstract
The paper is about developing a solver for maximizing a real-valued function of binary variables. The solver relies on an algorithm that estimates the optimal objective-function value of instances from the underlying distribution of objectives and their respective sub-instances. The training of the estimator is based on an inequality that facilitates the use of the expected total deviation from optimality conditions as a loss function rather than the objective-function itself. Thus, it does not calculate values of policies, nor does it rely on solved instances.

Why we think this paper is great for you:
This paper introduces a novel metric for tracking global AI usage, offering a broad perspective on AI adoption. It provides valuable context for understanding the widespread impact of AI technologies.

Abstract
Measuring global AI diffusion remains challenging due to a lack of population-normalized, cross-country usage data. We introduce AI User Share, a novel indicator that estimates the share of each country's working-age population actively using AI tools. Built from anonymized Microsoft telemetry and adjusted for device access and mobile scaling, this metric spans 147 economies and provides consistent, real-time insight into global AI diffusion. We find wide variation in adoption, with a strong correlation between AI User Share and GDP. High uptake is concentrated in developed economies, though usage among internet-connected populations in lower-income countries reveals substantial latent demand. We also detect sharp increases in usage following major product launches, such as DeepSeek in early 2025. While the metric's reliance solely on Microsoft telemetry introduces potential biases related to this user base, it offers an important new lens into how AI is spreading globally. AI User Share enables timely benchmarking that can inform data-driven AI policy.

Why we think this paper is great for you:
This research explores how AI knowledge disseminates across firms and contributes to productivity gains. It offers insights into the organizational factors influencing AI's economic impact.

Abstract
Labor mobility is a critical source of technology acquisition for firms. This paper examines how artificial intelligence (AI) knowledge is disseminated across firms through labor mobility and identifies the organizational conditions that facilitate productive spillovers. Using a comprehensive dataset of over 460 million job records from Revelio Labs (2010 to 2023), we construct an inter-firm mobility network of AI workers among over 16,000 U.S. companies. Estimating a Cobb Douglas production function, we find that firms benefit substantially from the AI investments of other firms from which they hire AI talents, with productivity spillovers two to three times larger than those associated with traditional IT after accounting for labor scale. Importantly, these spillovers are contingent on organizational context: hiring from flatter and more lean startup method intensive firms generates significant productivity gains, whereas hiring from firms lacking these traits yields little benefit. Mechanism tests indicate that "flat and lean" organizations cultivate more versatile AI generalists who transfer richer knowledge across firms. These findings reveal that AI spillovers differ fundamentally from traditional IT spillovers: while IT spillovers primarily arise from scale and process standardization, AI spillovers critically depend on the experimental and integrative environments in which AI knowledge is produced. Together, these results underscore the importance of considering both labor mobility and organizational context in understanding the full impact of AI-driven productivity spillovers.