This paper presents our ongoing work toward developing an enterprise-ready Computer Using Generalist Agent (CUGA) system. Our research highlights the evolutionary nature of building agentic systems suitable for enterprise environments. By integrating state-of-the-art agentic AI techniques with a systematic approach to iterative evaluation, analysis, and refinement, we have achieved rapid and cost-effective performance gains, notably reaching a new state-of-the-art performance on the WebArena benchmark. We detail our development roadmap, the methodology and tools that facilitated rapid learning from failures and continuous system refinement, and discuss key lessons learned and future challenges for enterprise adoption.

Fairness constraints applied to machine learning (ML) models in static contexts have been shown to potentially produce adverse outcomes among demographic groups over time. To address this issue, emerging research focuses on creating fair solutions that persist over time. While many approaches treat this as a single-agent decision-making problem, real-world systems often consist of multiple interacting entities that influence outcomes. Explicitly modeling these entities as agents enables more flexible analysis of their interventions and the effects they have on a system's underlying dynamics. A significant challenge in conducting research on multi-agent systems is the lack of realistic environments that leverage the limited real-world data available for analysis. To address this gap, we introduce the concept of a Multi-Agent Fair Environment (MAFE) and present and analyze three MAFEs that model distinct social systems. Experimental results demonstrate the utility of our MAFEs as testbeds for developing multi-agent fair algorithms.

The past few years have witnessed a rapid growth of the deployment of automated vehicles (AVs). Clearly, AVs and human-driven vehicles (HVs) will co-exist for many years, and AVs will have to operate around HVs, pedestrians, cyclists, and more, calling for fundamental breakthroughs in AI designed for mixed traffic to achieve mixed autonomy. Thus motivated, we study heterogeneous decision making by AVs and HVs in a mixed traffic environment, aiming to capture the interactions between human and machine decision-making and develop an AI foundation that enables vehicles to operate safely and efficiently. There are a number of challenges to achieve mixed autonomy, including 1) humans drivers make driving decisions with bounded rationality, and it remains open to develop accurate models for HVs' decision making; and 2) uncertainty-aware planning plays a critical role for AVs to take safety maneuvers in response to the human behavior. In this paper, we introduce a formulation of AV-HV interaction, where the HV makes decisions with bounded rationality and the AV employs uncertainty-aware planning based on the prediction on HV's future actions. We conduct a comprehensive analysis on AV and HV's learning regret to answer the questions: 1) {How does the learning performance depend on HV's bounded rationality and AV's planning}; 2) {How do different decision making strategies impact the overall learning performance}? Our findings reveal some intriguing phenomena, such as Goodhart's Law in AV's learning performance and compounding effects in HV's decision making process. By examining the dynamics of the regrets, we gain insights into the interplay between human and machine decision making.

Recent advancements in software engineering (SWE) agents have largely followed a $\textit{tool-based paradigm}$, where agents interact with hand-engineered tool APIs to perform specific tasks. While effective for specialized tasks, these methods fundamentally lack generalization, as they require predefined tools for each task and do not scale across programming languages and domains. We introduce $\texttt{Programming with Pixels}$ (PwP), an agent environment that unifies software development tasks by enabling $\textit{computer-use agents}$-agents that operate directly within an IDE through visual perception, typing, and clicking, rather than relying on predefined tool APIs. To systematically evaluate these agents, we propose $\texttt{PwP-Bench}$, a benchmark that unifies existing SWE benchmarks spanning tasks across multiple programming languages, modalities, and domains under a task-agnostic state and action space. Our experiments demonstrate that general-purpose computer-use agents can approach or even surpass specialized tool-based agents on a variety of SWE tasks without the need for hand-engineered tools. However, our analysis shows that current models suffer from limited visual grounding and fail to exploit many IDE tools that could simplify their tasks. When agents can directly access IDE tools, without visual interaction, they show significant performance improvements, highlighting the untapped potential of leveraging built-in IDE capabilities. Our results establish PwP as a scalable testbed for building and evaluating the next wave of software engineering agents. We release code and data at https://programmingwithpixels.com

Coaches are vital for effective collaboration, but cost and resource constraints often limit their availability during real-world tasks. This limitation poses serious challenges in life-critical domains that rely on effective teamwork, such as healthcare and disaster response. To address this gap, we propose and realize an innovative application of AI: task-time team coaching. Specifically, we introduce Socratic, a novel AI system that complements human coaches by providing real-time guidance during task execution. Socratic monitors team behavior, detects misalignments in team members' shared understanding, and delivers automated interventions to improve team performance. We validated Socratic through two human subject experiments involving dyadic collaboration. The results demonstrate that the system significantly enhances team performance with minimal interventions. Participants also perceived Socratic as helpful and trustworthy, supporting its potential for adoption. Our findings also suggest promising directions both for AI research and its practical applications to enhance human teamwork.

Large-scale social digital twinning projects are complex with multiple objectives. For example, a social digital twinning platform for innovative last-mile delivery solutions may aim to assess consumer delivery method choices within their social environment. However, no single tool can achieve all objectives. Different simulators exist for consumer behavior and freight transport. Therefore, we propose a high-level architecture and present a blueprint for a generic modelling framework. This includes defining modules, input/output data, and interconnections, while addressing data suitability and compatibility risks. We demonstrate the framework's effectiveness with two real-world case studies.

Successful collaboration requires team members to stay aligned, especially in complex sequential tasks. Team members must dynamically coordinate which subtasks to perform and in what order. However, real-world constraints like partial observability and limited communication bandwidth often lead to suboptimal collaboration. Even among expert teams, the same task can be executed in multiple ways. To develop multi-agent systems and human-AI teams for such tasks, we are interested in data-driven learning of multimodal team behaviors. Multi-Agent Imitation Learning (MAIL) provides a promising framework for data-driven learning of team behavior from demonstrations, but existing methods struggle with heterogeneous demonstrations, as they assume that all demonstrations originate from a single team policy. Hence, in this work, we introduce DTIL: a hierarchical MAIL algorithm designed to learn multimodal team behaviors in complex sequential tasks. DTIL represents each team member with a hierarchical policy and learns these policies from heterogeneous team demonstrations in a factored manner. By employing a distribution-matching approach, DTIL mitigates compounding errors and scales effectively to long horizons and continuous state representations. Experimental results show that DTIL outperforms MAIL baselines and accurately models team behavior across a variety of collaborative scenarios.

To develop generalizable models in multi-agent reinforcement learning, recent approaches have been devoted to discovering task-independent skills for each agent, which generalize across tasks and facilitate agents' cooperation. However, particularly in partially observed settings, such approaches struggle with sample efficiency and generalization capabilities due to two primary challenges: (a) How to incorporate global states into coordinating the skills of different agents? (b) How to learn generalizable and consistent skill semantics when each agent only receives partial observations? To address these challenges, we propose a framework called \textbf{M}asked \textbf{A}utoencoders for \textbf{M}ulti-\textbf{A}gent \textbf{R}einforcement \textbf{L}earning (MA2RL), which encourages agents to infer unobserved entities by reconstructing entity-states from the entity perspective. The entity perspective helps MA2RL generalize to diverse tasks with varying agent numbers and action spaces. Specifically, we treat local entity-observations as masked contexts of the global entity-states, and MA2RL can infer the latent representation of dynamically masked entities, facilitating the assignment of task-independent skills and the learning of skill semantics. Extensive experiments demonstrate that MA2RL achieves significant improvements relative to state-of-the-art approaches, demonstrating extraordinary performance, remarkable zero-shot generalization capabilities and advantageous transferability.

We first evaluate five LLMs' economic decision-making capabilities in solving two-period consumption allocation problems under two distinct scenarios: with explicit utility functions and based on intuitive reasoning. While previous research has often simulated heterogeneity by solely varying prompts, our approach harnesses the inherent variations in analytical capabilities across different LLMs to model agents with diverse cognitive traits. Building on these findings, we construct a Multi-LLM-Agent-Based (MLAB) framework by mapping these LLMs to specific educational groups and corresponding income brackets. Using interest-income taxation as a case study, we demonstrate how the MLAB framework can simulate policy impacts across heterogeneous agents, offering a promising new direction for economic and public policy analysis by leveraging LLMs' human-like reasoning capabilities and computational power.

Recent work, spanning from autonomous vehicle coordination to in-space assembly, has shown the importance of learning collaborative behavior for enabling robots to achieve shared goals. A common approach for learning this cooperative behavior is to utilize the centralized-training decentralized-execution paradigm. However, this approach also introduces a new challenge: how do we evaluate the contributions of each agent's actions to the overall success or failure of the team. This credit assignment problem has remained open, and has been extensively studied in the Multi-Agent Reinforcement Learning literature. In fact, humans manually inspecting agent behavior often generate better credit evaluations than existing methods. We combine this observation with recent works which show Large Language Models demonstrate human-level performance at many pattern recognition tasks. Our key idea is to reformulate credit assignment to the two pattern recognition problems of sequence improvement and attribution, which motivates our novel LLM-MCA method. Our approach utilizes a centralized LLM reward-critic which numerically decomposes the environment reward based on the individualized contribution of each agent in the scenario. We then update the agents' policy networks based on this feedback. We also propose an extension LLM-TACA where our LLM critic performs explicit task assignment by passing an intermediary goal directly to each agent policy in the scenario. Both our methods far outperform the state-of-the-art on a variety of benchmarks, including Level-Based Foraging, Robotic Warehouse, and our new Spaceworld benchmark which incorporates collision-related safety constraints. As an artifact of our methods, we generate large trajectory datasets with each timestep annotated with per-agent reward information, as sampled from our LLM critics.