Multi-agent reinforcement learning faces fundamental challenges that conventional approaches have failed to overcome: exponentially growing joint action spaces, non-stationary environments where simultaneous learning creates moving targets, and partial observability that constrains coordination. Current methods remain reactive, employing stimulus-response mechanisms that fail when facing novel scenarios. We argue for a transformative paradigm shift from reactive to proactive multi-agent intelligence through generative AI-based reinforcement learning. This position advocates reconceptualizing agents not as isolated policy optimizers, but as sophisticated generative models capable of synthesizing complex multi-agent dynamics and making anticipatory decisions based on predictive understanding of future interactions. Rather than responding to immediate observations, generative-RL agents can model environment evolution, predict other agents' behaviors, generate coordinated action sequences, and engage in strategic reasoning accounting for long-term dynamics. This approach leverages pattern recognition and generation capabilities of generative AI to enable proactive decision-making, seamless coordination through enhanced communication, and dynamic adaptation to evolving scenarios. We envision this paradigm shift will unlock unprecedented possibilities for distributed intelligence, moving beyond individual optimization toward emergent collective behaviors representing genuine collaborative intelligence. The implications extend across autonomous systems, robotics, and human-AI collaboration, promising solutions to coordination challenges intractable under traditional reactive frameworks.

Social learning is a powerful mechanism through which agents learn about the world from others. However, humans don't always choose to observe others, since social learning can carry time and cognitive resource costs. How do people balance social and non-social learning? In this paper, we propose a rational mentalizing model of the decision to engage in social learning. This model estimates the utility of social learning by reasoning about the other agent's goal and the informativity of their future actions. It then weighs the utility of social learning against the utility of self-exploration (non-social learning). Using a multi-player treasure hunt game, we show that our model can quantitatively capture human trade-offs between social and non-social learning. Furthermore, our results indicate that these two components allow agents to flexibly apply social learning to achieve their goals more efficiently.

We present StockSim, an open-source simulation platform for systematic evaluation of large language models (LLMs) in realistic financial decision-making scenarios. Unlike previous toolkits that offer limited scope, StockSim delivers a comprehensive system that fully models market dynamics and supports diverse simulation modes of varying granularity. It incorporates critical real-world factors, such as latency, slippage, and order-book microstructure, that were previously neglected, enabling more faithful and insightful assessment of LLM-based trading agents. An extensible, role-based agent framework supports heterogeneous trading strategies and multi-agent coordination, making StockSim a uniquely capable testbed for NLP research on reasoning under uncertainty and sequential decision-making. We open-source all our code at https: //github.com/harrypapa2002/StockSim.

Developing autonomous agents that quickly explore an environment and adapt their behavior online is a canonical challenge in robotics and machine learning. While humans are able to achieve such fast online exploration and adaptation, often acquiring new information and skills in only a handful of interactions, existing algorithmic approaches tend to rely on random exploration and slow, gradient-based behavior updates. How can we endow autonomous agents with such capabilities on par with humans? Taking inspiration from recent progress on both in-context learning and large-scale behavioral cloning, in this work we propose behavioral exploration: training agents to internalize what it means to explore and adapt in-context over the space of ``expert'' behaviors. To achieve this, given access to a dataset of expert demonstrations, we train a long-context generative model to predict expert actions conditioned on a context of past observations and a measure of how ``exploratory'' the expert's behaviors are relative to this context. This enables the model to not only mimic the behavior of an expert, but also, by feeding its past history of interactions into its context, to select different expert behaviors than what have been previously selected, thereby allowing for fast online adaptation and targeted, ``expert-like'' exploration. We demonstrate the effectiveness of our method in both simulated locomotion and manipulation settings, as well as on real-world robotic manipulation tasks, illustrating its ability to learn adaptive, exploratory behavior.

The pharmaceutical industry faces unprecedented challenges in drug discovery, with traditional approaches struggling to meet modern therapeutic development demands. This paper introduces a novel AI framework, Tippy, that transforms laboratory automation through specialized AI agents operating within the Design-Make-Test-Analyze (DMTA) cycle. Our multi-agent system employs five specialized agents - Supervisor, Molecule, Lab, Analysis, and Report, with Safety Guardrail oversight - each designed to excel in specific phases of the drug discovery pipeline. Tippy represents the first production-ready implementation of specialized AI agents for automating the DMTA cycle, providing a concrete example of how AI can transform laboratory workflows. By leveraging autonomous AI agents that reason, plan, and collaborate, we demonstrate how Tippy accelerates DMTA cycles while maintaining scientific rigor essential for pharmaceutical research. The system shows significant improvements in workflow efficiency, decision-making speed, and cross-disciplinary coordination, offering a new paradigm for AI-assisted drug discovery.

Large Language Models (LLMs) have achieved strong performance on a wide range of complex reasoning tasks, yet further gains are often possible by leveraging the complementary strengths of multiple models. While multi-agent frameworks can improve solution quality by leveraging multiple LLMs, existing methods are often computationally expensive, both at training and inference time. In this work, we introduce a hierarchical multi-agent framework that addresses these challenges by training only a single leader LLM to coordinate a team of untrained peer agents. To this end, we propose Multi-agent guided Leader Policy \textbf{O}ptimization (MLPO), a novel approach which trains the leader to evaluate and synthesize agent responses without auxiliary value networks or explicit agent feedback. Leaders trained with MLPO exhibit improved performance not only when interacting with the agent team at inference time, but also enjoy improved performance when deployed in single-agent settings without the team. Empirical results on Big-Bench Hard (BBH), MATH, and MMLU demonstrate that our framework achieves substantial performance improvements over both single-agent and multi-agent baselines. Our results highlight the effectiveness and efficiency of training a single, flexible leader for collaborative reasoning in multi-agent LLM systems.

Large language model (LLM)-based multi-agent systems have demonstrated remarkable promise for tackling complex tasks by breaking them down into subtasks that are iteratively planned, executed, observed, and refined. Despite their effectiveness, these systems often incur high latency because real-world problems frequently demand multiple iterative cycles of reasoning steps. To address this challenge, we propose M1-Parallel, a framework that concurrently runs multiple multi-agent teams in parallel to uncover distinct solution paths. By leveraging an event-driven communication model with asynchronous messaging, M1-Parallel efficiently capitalizes on the inherent diversity of valid plans to either reduce end-to-end latency or boost task completion rates. Our experiments on complex tasks show that M1-Parallel with early termination achieves up to $2.2\times$ speedup while preserving accuracy, and that M1-Parallel with aggregation yields higher task completion rates. We further investigate strategies aimed at encouraging diverse execution plans but observe no additional performance gains over repeated sampling. Overall, these findings underscore the potential of parallel plan execution for optimizing multi-agent systems for real-world, high-complexity reasoning tasks.

Generative AI can be used in multi-actor environments with purposes ranging from social science modeling to interactive narrative and AI evaluation. Supporting this diversity of use cases -- which we classify as Simulationist, Dramatist, and Evaluationist -- demands a flexible scenario definition framework. We argue here that a good approach is to take inspiration from tabletop role-playing games (TTRPGs), where a Game Master (GM) is responsible for the environment and generates all parts of the story not directly determined by the voluntary actions of player characters. We argue that the Entity-Component architectural pattern is useful here. In such a system, the GM is not a hardcoded computer game but is itself a configurable entity, composed of components just like any other actor. By design, the approach allows for a separation between the underlying implementation details handled by an engineer, the creation of reusable components, and their composition and configuration managed by a designer who constructs entities from the components. This separation of concerns is instrumental for achieving rapid iteration, maintaining modularity, and ultimately to ensure scalability. We describe the ongoing evolution of the Concordia library in terms of this philosophy, demonstrating how it allows users to effectively configure scenarios that align with their specific goals.

We present a visualization infrastructure that maps data elements to agents, which have behaviors parameterized by those elements. Dynamic visualizations emerge as the agents change position, alter appearance and respond to one other. Agents move to minimize the difference between displayed agent-to-agent distances, and an input matrix of ideal distances. Our current application is visualization of streaming text. Each agent represents a significant word, visualizing it by displaying the word itself, centered in a circle sized by the frequency of word occurrence. We derive the ideal distance matrix from word cooccurrence, mapping higher co-occurrence to lower distance. To depict co-occurrence in its textual context, the ratio of intersection to circle area approximates the ratio of word co-occurrence to frequency. A networked backend process gathers articles from news feeds, blogs, Digg or Twitter, exploiting online search APIs to focus on user-chosen topics. Resulting visuals reveal the primary topics in text streams as clusters, with agent-based layout moving without instability as data streams change dynamically.

Next-Generation Travel Demand Modeling with a Generative Framework for Household Activity Coordination Xishun Liao 1, Haoxuan Ma 1, Yifan Liu 1, Y uxiang Wei 1, Brian Y ueshuai He 2, Chris Stanford 3, and Jiaqi Ma* 1 Abstract -- Travel demand models are critical tools for planning, policy, and mobility system design. Traditional activity-based models (ABMs), although grounded in behavioral theories, often rely on simplified rules and assumptions, and are costly to develop and difficult to adapt across different regions. This paper presents a learning-based travel demand modeling framework that synthesizes household-coordinated daily activity patterns based on a household's socio-demographic profiles. The whole framework integrates population synthesis, coordinated activity generation, location assignment, and large-scale microscopic traffic simulation into a unified system. It is fully generative, data-driven, scalable, and transferable to other regions. A full-pipeline implementation is conducted in Los Angeles with a 10 million population. Comprehensive validation shows that the model closely replicates real-world mobility patterns and matches the performance of legacy ABMs with significantly reduced modeling cost and greater scalability. With respect to the SCAG ABM benchmark, the origin-destination matrix achieves a cosine similarity of 0.97, and the daily vehicle miles traveled (VMT) in the network yields a 0.006 Jensen-Shannon Divergence (JSD) and a 9.8% mean absolute percentage error (MAPE).