Multi-strategy hedge funds face a fundamental organizational choice: should analysts generating trading strategies communicate, and if so, how? We investigate this using 5-agent LLM-based trading systems across 450 experiments spanning 21 months, comparing five organizational structures from isolated baseline to collaborative and competitive conversation. We show that communication improves performance, but optimal communication design depends on market characteristics. Competitive conversation excels in volatile technology stocks, while collaborative conversation dominates stable general stocks. Finance stocks resist all communication interventions. Surprisingly, all structures, including isolated agents, converge to similar strategy alignments, challenging assumptions that transparency causes harmful diversity loss. Performance differences stem from behavioral mechanisms: competitive agents focus on stock-level allocation while collaborative agents develop technical frameworks. Conversation quality scores show zero correlation with returns. These findings demonstrate that optimal communication design must match market volatility characteristics, and sophisticated discussions don't guarantee better performance.

Documenting tacit knowledge in organizations can be a challenging task due to incomplete initial information, difficulty in identifying knowledgeable individuals, the interplay of formal hierarchies and informal networks, and the need to ask the right questions. To address this, we propose an agent-based framework leveraging large language models (LLMs) to iteratively reconstruct dataset descriptions through interactions with employees. Modeling knowledge dissemination as a Susceptible-Infectious (SI) process with waning infectivity, we conduct 864 simulations across various synthetic company structures and different dissemination parameters. Our results show that the agent achieves 94.9% full-knowledge recall, with self-critical feedback scores strongly correlating with external literature critic scores. We analyze how each simulation parameter affects the knowledge retrieval process for the agent. In particular, we find that our approach is able to recover information without needing to access directly the only domain specialist. These findings highlight the agent's ability to navigate organizational complexity and capture fragmented knowledge that would otherwise remain inaccessible.

Ever since the invention of the org chart in the 1850s, company structures have changed very little--they are hierarchical and consist of multiple layers of managers and decisionmakers. That is because we have been bound by the limits of human intelligence and attention to manage and control the flow of work. In large language models (LLMs), we have a new, alien form of intelligence, but one that has primarily worked as an assistant at the individual level. In 2025, we will start to see the first organizations to build around the combination of humans and AIs working together. This shift represents a fundamental change in how we structure and operate our businesses and institutions.

Holacracy is an innovative management model proposed by Brian Robertson, the founder of the software company. It is a democratic and open organizational structure with shared governance for all, aiming at the decentralized management of an organization by breaking the authoritarianism of the leadership through the assumption of work by roles[1]. Such a management model is better to give employees the freedom to be more creative; however, at the same time, it also creates conflicts between roles and teams, resulting in many organizational practices ending in failure [2]. Although some static influence mechanisms have been explored in the past [3, 4], the dynamic operation of the system, like autority delegation, is not well understood. In this paper, based on the simulation capacity of Large Language Model (LLM) [5, 6], we built CareerAgent, an organizational behavior simulation framework based on LLM Agents, as shown in Figure 1, to simulate the operation of organizations under the holacracy framework, and found some interesting phenomena. One of the characteristics of the holacracy is that the leaders delegate their authority to the employees at the lower level.

Large Language Models (LLMs) have emerged as integral tools for reasoning, planning, and decision-making, drawing upon their extensive world knowledge and proficiency in language-related tasks. LLMs thus hold tremendous potential for natural language interaction within multi-agent systems to foster cooperation. However, LLM agents tend to over-report and comply with any instruction, which may result in information redundancy and confusion in multi-agent cooperation. Inspired by human organizations, this paper introduces a framework that imposes prompt-based organization structures on LLM agents to mitigate these problems. Through a series of experiments with embodied LLM agents and human-agent collaboration, our results highlight the impact of designated leadership on team efficiency, shedding light on the leadership qualities displayed by LLM agents and their spontaneous cooperative behaviors. Further, we harness the potential of LLMs to propose enhanced organizational prompts, via a Criticize-Reflect process, resulting in novel organization structures that reduce communication costs and enhance team efficiency.

Agent organization is a group of agents with a certain structure cooperating for shared goals. During their collaborative process, they autonomously orchestrated workflows without fixed steps by humans. Leveraging large language models (LLMs), autonomous agents have significantly improved, gaining the ability to handle a variety of tasks. In open-ended settings, optimizing collaboration for efficiency and effectiveness demands flexible adjustments. Despite this, current research mainly emphasizes fixed, task-oriented workflows and overlooks agent-centric organizational structures. Drawing inspiration from human organizational behavior, we introduce a self-organizing agent system (S-Agents) with a "tree of agents" structure for dynamic workflow, an "hourglass agent architecture" for balancing information priorities, and a "nonobstructive collaboration" method to allow asynchronous task execution among agents. This structure can autonomously coordinate a group of agents, efficiently addressing the challenges of an open and dynamic environment without human intervention. Our experiments demonstrate that S-Agents proficiently execute collaborative building tasks and resource collection in the Minecraft environment, validating their effectiveness. These authors contributed equally to this work. Li Zhang (lizhangfd@fudan.edu.cn) is the corresponding author with School of Data Science, Fudan University. The fundamental objective of artificial intelligence has long been the development of intelligent autonomous agents with the capacity to operate proficiently in open-ended environments (Weinbaum & Veitas, 2017; Fujita, 2009).

Research interest in autonomous agents is on the rise as an emerging topic. The notable achievements of Large Language Models (LLMs) have demonstrated the considerable potential to attain human-like intelligence in autonomous agents. However, the challenge lies in enabling these agents to learn, reason, and navigate uncertainties in dynamic environments. Context awareness emerges as a pivotal element in fortifying multi-agent systems when dealing with dynamic situations. Despite existing research focusing on both context-aware systems and multi-agent systems, there is a lack of comprehensive surveys outlining techniques for integrating context-aware systems with multi-agent systems. To address this gap, this survey provides a comprehensive overview of state-of-the-art context-aware multi-agent systems. First, we outline the properties of both context-aware systems and multi-agent systems that facilitate integration between these systems. Subsequently, we propose a general process for context-aware systems, with each phase of the process encompassing diverse approaches drawn from various application domains such as collision avoidance in autonomous driving, disaster relief management, utility management, supply chain management, human-AI interaction, and others. Finally, we discuss the existing challenges of context-aware multi-agent systems and provide future research directions in this field.

Leon Gordon is a leader in data analytics, a current Microsoft MVP based in the U.K. and a partner at Pomerol Partners. The digital revolution has set off near-panic among executives as they seek to find ways to use data and analytics to enhance their decision-making ability. The end result of data transformation is the creation of a digital core, a set of capabilities that are used to power the entire organization. Companies seeking to transform themselves with AI must establish a strategic plan for using analytics and insights derived from data. Organizational structure is important when considering an AI strategy because it can help ensure data are properly transferred and secure as they move through their lifecycle.

An ability to coordinate cross-functional projects and/or prior project management experience. Strong analytical skills and an ability to synthesize information across a broad ecosystem to diagnose problems and devise solutions. Comfortable with ambiguity; able to thrive with minimal oversight and process, while keeping leadership informed on progress against deadlines. A passion to serve the needs of Production within the Netflix organization. Ability to thrive in a fast-paced collaborative environment, possess an abundance of intellectual curiosity, focus on generating results, and exhibit the highest personal and professional standards of integrity.

The disparity between digital transformation leaders and laggards stems from a complex web of overlapping factors -- which often speak more to organizational issues than technical difficulties. Considerations in play include corporate history, IT philosophy, the ability to deliver on customer experience and a product vs. project mindset. A particularly important element separating a successful digital business from its competitors is a knack for translating small successes into enterprise-wide benefits. Indeed, overcoming digital transformation challenges at scale is crucial for realizing the promise of technology-infused business models, according to CIOs and industry analysts. Companies playing catch-up in the digital race must first focus on the essentials, such as customer experience, before moving on to more innovative pursuits.