







In the name of efficiency, organizations and governments around the world are increasingly trimming redundancy---personnel or overlapping capabilities beyond what routine operations require. Drawing on distributed computing and cognitive science, we challenge this view. Using queueing simulations and a preregistered multiplayer experiment (N = 832 in 187 teams of 3–6), we show that redundancy improves performance through two distinct routes. Adding collaborators to a team improves resilience, with larger teams completing more tasks when members became temporarily unable to contribute. Giving team members overlapping capabilities also improved efficiency, with teams in which collaborators could perform multiple roles completing substantially more work. These findings suggest that efforts to improve short-term efficiency by reducing redundancy may come at a cost, quietly eroding a team’s capacity to withstand unexpected failures.
The Task Space: An Integrative Framework for Team Research
Research on teams spans many contexts, but integrating knowledge from heterogeneous sources is challenging because studies typically examine different tasks that cannot be directly compared. Most investigations involve teams working on just one or a handful of tasks, and researchers lack principled ways to quantify how similar or different these tasks are from one another. We address this challenge by introducing the “Task Space,” a multidimensional space in which tasks—and the distances between them—can be represented formally, and use it to create a “Task Map” of 102 crowd-annotated tasks from the published experimental literature. We then demonstrate the Task Space’s utility by performing an integrative experiment that addresses a fundamental question in team research: when do interacting groups outperform individuals? Our experiment samples 20 diverse tasks from the Task Map at three complexity levels and recruits 1,231 participants to work either individually or in groups of three or six (180 experimental conditions). We find striking heterogeneity in group advantage, with groups performing anywhere from three times worse to 60% better than the best individual working alone, depending on the task context. Critically, the Task Space makes this heterogeneity predictable: it significantly outperforms traditional typologies in predicting group advantage on unseen tasks. Our models also reveal theoretically meaningful interactions between task features; for example, group advantage on creative tasks depends on whether the answers are objectively verifiable. We conclude by arguing that the Task Space enables researchers to integrate findings across different experiments, thereby building cumulative knowledge about team performance. This paper was accepted by Sameer Srivastava, organizations. Funding: The authors thank the Alfred P. Sloan Foundation [Grant #202-13924] and the MIT Wade Fund for their generous support of this research. Supplemental Material: The online appendix and data files are available at https://doi.org/10.1287/mnsc.2023.03544 .

Habits of High-Functioning Teams
I often struggle to explain what it means to be part of a high-functioning software team. Sure, there are mountains of literature, and an entire genre of LinkedIn thought leadership that professes all kinds of guidelines and heuristics about what makes teams work, but in my experience, it’s hard to internalize these ideas and follow someone else’s model if you’ve never seen what good looks like.
Friends Don’t Let Friends Agent Alone by Ben Brandt
The speaker delves into code editor development, emphasizing collaboration between humans and AI. Discussions revolve around adapting to technological changes while facing persistent cognitive limitations. Balancing cognitive load in software development is crucial for optimal task completion. Focus and alignment in software development are essential for effective problem-solving. Addressing challenges of team alignment in AI-driven environments is crucial to avoid creating legacy code bases. Pair programming enhances collaboration, accountability, and learning within development teams. Valuing collaboration, trust, and autonomy fosters speed and efficiency in software development. Leadership strategies focus on promoting autonomy, mastery, and purpose while addressing burnout. AI impact on productivity and collaborative coding practices are reflected upon, emphasizing the benefits of pair programming. Effective onboarding and encouraging pair programming adoption contribute to better problem-solving and team collaboration.
Scaling Discovery through Test-Time Communication
Science advances not in isolation but through collaboration, yet existing agentic systems capture little of this. Whether communicating agents help remains an open question with mixed prior results. We show that test-time communication can substantially outperform independent parallel attempts on challenging tasks, where sharing a breakthrough can push the whole group forward. We first study the effect of scaling multi-agent test-time communication, where agents have no predefined roles and communicate via a shared directory, on ARC-AGI-3, a benchmark requiring novel problem solving. We find that a team of $k$ communicating agents, team@$k$, matches the success rate of $4k$ independent agents, and this advantage grows with $k$, suggesting gains compound with scale. The effect is not merely efficiency: a task that no single agent can solve, a team of agents can solve reliably. Furthermore, these gains transfer to research-oriented tasks, given sufficient compute. On polyomino packing, communicating agents outperform best@$k$ and exceed the prior best-known score. On MNIST classifier compression, communication surpasses the best-known human solution. A team of four agents produced a 1,957-byte classifier submission achieving 99.4% test accuracy, smaller than both the best-known human solution and the best single-agent result. These gains are not unconditional. Independent agents may outperform communication when compute is limited or when a clear measure of progress is absent. However, under sufficient compute and clear feedback, multi-agent communication consistently yields stronger results.

The New Science of Building Great Teams
Why do some teams consistently deliver high performance while other, seemingly identical teams struggle? Led by Sandy Pentland, researchers at MIT’s Human Dynamics Laboratory set out to solve that puzzle. Hoping to decode the “It factor” that made groups click, they equipped teams from a broad variety of projects and industries (comprising 2,500 individuals in total) with wearable electronic sensors that collected data on their social behavior for weeks at a time. With remarkable consistency, the data showed that the most important predictor of a team’s success was its communication patterns. Those patterns were as significant as all other factors—intelligence, personality, talent—combined. In fact, the researchers could foretell which teams would outperform simply by looking at the data on their communication, without even meeting their members. In this article Pentland shares the secrets of his findings and shows how anyone can engineer a great team. He has identified three key communication dynamics that affect performance: energy, engagement, and exploration. Drawing from the data, he has precisely quantified the ideal team patterns for each. Even more significant, he has seen that when teams map their own communication behavior over time and then make adjustments that move it closer to the ideal, they can dramatically improve their performance.

The New Science of Building Great Teams
Why do some teams consistently deliver high performance while other, seemingly identical teams struggle? Led by Sandy Pentland, researchers at MIT’s Human Dynamics Laboratory set out to solve that puzzle. Hoping to decode the “It factor” that made groups click, they equipped teams from a broad variety of projects and industries (comprising 2,500 individuals in total) with wearable electronic sensors that collected data on their social behavior for weeks at a time. With remarkable consistency, the data showed that the most important predictor of a team’s success was its communication patterns. Those patterns were as significant as all other factors—intelligence, personality, talent—combined. In fact, the researchers could foretell which teams would outperform simply by looking at the data on their communication, without even meeting their members. In this article Pentland shares the secrets of his findings and shows how anyone can engineer a great team. He has identified three key communication dynamics that affect performance: energy, engagement, and exploration. Drawing from the data, he has precisely quantified the ideal team patterns for each. Even more significant, he has seen that when teams map their own communication behavior over time and then make adjustments that move it closer to the ideal, they can dramatically improve their performance.

Improving the Efficiency of Language Agent Teams with Adaptive Task Graphs
Large language models (LLMs) are increasingly deployed in teams, yet existing coordination approaches often occupy two extremes. Highly structured methods rely on fixed roles, pipelines, or task decompositions assigned a priori. In contrast, fully unstructured teams enable adaptability and exploration but suffer from inefficiencies such as error propagation, inter-agent conflicts, and wasted resources (measured in time, tokens, or file operations). We introduce Language Agent Teams for Task Evolution (LATTE), a framework for coordinating LLM teams inspired by distributed systems, where processors must operate under partial observability and communication constraints. In LATTE, a team of agents collaboratively construct and maintain a shared, evolving coordination graph which encodes sub-task dependencies, individual agent assignment, and the current state of sub-task progress. This protocol maintains consistency while empowering agents to dynamically allocate work, adapt coordination, and discover new tasks. Across multiple collaborative tasks and a variety of base models, we demonstrate how LATTE reduces token usage, wall-clock time, communication, and coordination failures (e.g. file conflicts and redundant outputs) while matching or exceeding the accuracy of standard designs including MetaGPT, decentralized teams, top-down Leader-Worker hierarchies, and static decompositions.

The Strength of the Strongest Ties in Collaborative Problem Solving
Complex problem solving in science, engineering and business has become a highly collaborative endeavor. Teams of scientists or engineers collaborate on projects using their social networks to gather new ideas and feedback. Here we bridge the literature on team performance and information networks by studying teams' problem solving abilities as a function of both their within-team networks and their members' extended networks. We show that, while an assigned team's performance is strongly correlated with its networks of expressive and instrumental ties, only the strongest ties in both networks have an effect on performance. Both networks of strong ties explain more of the variance than other factors, such as measured or self-evaluated technical competencies, or the personalities of the team members. In fact, the inclusion of the network of strong ties renders these factors non-significant in the statistical analysis. Our results have consequences for the organization of teams of scientists, engineers and other knowledge workers tackling today's most complex problems.

The Strength of the Strongest Ties in Collaborative Problem Solving
Complex problem solving in science, engineering and business has become a highly collaborative endeavor. Teams of scientists or engineers collaborate on projects using their social networks to gather new ideas and feedback. Here we bridge the literature on team performance and information networks by studying teams' problem solving abilities as a function of both their within-team networks and their members' extended networks. We show that, while an assigned team's performance is strongly correlated with its networks of expressive and instrumental ties, only the strongest ties in both networks have an effect on performance. Both networks of strong ties explain more of the variance than other factors, such as measured or self-evaluated technical competencies, or the personalities of the team members. In fact, the inclusion of the network of strong ties renders these factors non-significant in the statistical analysis. Our results have consequences for the organization of teams of scientists, engineers and other knowledge workers tackling today's most complex problems.

Reaching Peak Meeting Efficiency
Meetings are undeniably the most important tool for build a high-performance team with shared values

The Boundaryless Era: the Time for Distributed Teams
Standout startups like Stripe, InVision, and Github exploit a competitive edge every startup should leverage. The boundaryless era of distributed teams.

Lunar Logic Blog | Effective Collaboration: You Don’t Need Superstar Developers
The surprising truth about what makes high performing teams. I'll give you a hint, it's not tech skills.
This Is How We Manage Projects on a Fully Remote Team
These are the lessons we've learned managing cross-functional projects on a team of 60 people spread across 23 countries.
This Is How We Manage Projects on a Fully Remote Team
These are the lessons we've learned managing cross-functional projects on a team of 60 people spread across 23 countries.
10 More (Leadership!) Lessons from 10 Years Working in a Fully-Distributed and Remote Company
To make a distributed team work in the long-term it takes deliberate planning and thoughtfulness about your culture, leadership, strategic planning, and team-building.
