Chinese AI startup Manus has unveiled a new feature called Wide Research, designed to handle large-scale, high-volume tasks by simultaneously deploying over 100 AI agents. This approach contrasts with "Deep Research" methods used by competitors, which conduct extensive research sequentially. Wide Research breaks down complex tasks into numerous sub-tasks executed in parallel, enabling rapid analysis of large datasets or concurrent generation of diverse creative outputs. For example, Manus demonstrated Wide Research analyzing 100 sneaker models simultaneously for design, pricing, and availability, compiling the results into a sortable matrix within minutes. The feature also showcased creative applications, like generating 50 different poster designs concurrently. This advancement is made possible by Manus's system-level architecture, which facilitates agent-to-agent communication and optimized virtualization, scaling compute power significantly. Wide Research activates automatically for tasks requiring broad analysis, without manual configuration. The feature is currently available to users on the Manus Pro plan, with a phased rollout to Plus and Basic subscribers planned. Manus offers several subscription tiers: Free ($0/month), Basic ($19/month), Plus ($39/month), and Pro ($199/month), with discounts for annual payments. Manus’s platform operates each user session on a dedicated virtual machine, providing orchestrated cloud compute accessible via natural language. Unlike traditional multi-agent systems with specialized roles, each Wide Research subagent is a fully capable Manus instance, capable of performing any general task independently. This design prioritizes flexibility and scalability. The primary advantage of Wide Research over Deep Research lies in its speed and variety of outputs, moving beyond traditional research reports. However, Manus has yet to provide benchmarks to definitively prove the efficiency of spawning hundreds of agents versus a single high-capacity agent working sequentially, leaving questions about resource usage and coordination complexity. The broader AI ecosystem has encountered challenges with subagent approaches, with users reporting issues like slow performance, high token consumption, and debugging difficulties. Manus acknowledges that Wide Research is experimental and may evolve with further limitations. Manus is pushing the boundaries of AI agent orchestration, exploring the potential of generalized, fully capable agent instances for seamless multi-threaded AI collaboration, with plans for this infrastructure to support future innovations. Industry observers will be keen to see if Manus's architecture can overcome multi-agent system challenges and deliver tangible benefits in speed, accuracy, and scalability.

FAQ

Platform and Features

Q: What is Manus's Wide Research feature? A: Wide Research is a new feature from Manus that utilizes parallelized AI agents to tackle large-scale, high-volume tasks by running over 100 AI agents simultaneously. Q: How does Wide Research differ from competitor AI research tools? A: Unlike "Deep Research" tools that conduct research sequentially, Wide Research performs tasks in parallel by dividing them into numerous sub-tasks handled concurrently by multiple AI agents. Q: What are some practical applications of Wide Research? A: It can be used for tasks like analyzing large datasets (e.g., comparing 100 sneaker models for design, pricing, and availability) or generating diverse creative outputs (e.g., creating 50 different poster designs simultaneously). Q: Does Wide Research require manual configuration? A: No, Wide Research activates automatically for tasks requiring broad analysis, eliminating the need for manual setup.

Availability and Pricing

Q: Which Manus subscription plans include Wide Research? A: Wide Research is currently available to Manus Pro plan users and will be gradually rolled out to Plus and Basic subscribers. Q: What are the different Manus subscription tiers? A: Manus offers Free ($0/month), Basic ($19/month), Plus ($39/month), and Pro ($199/month) plans, with discounts for annual payments.

Technical Aspects and Challenges

Q: What is the technical advantage of Wide Research? A: It leverages parallelized AI agents and Manus’s system-level architecture, which supports agent-to-agent communication and optimized virtualization, allowing for significant scaling of compute power. Q: What are the potential challenges with Wide Research or similar multi-agent systems? A: While promising for speed and variety, there are questions about resource usage, coordination complexity, and the lack of detailed benchmarks comparing it to single high-capacity agents. Other multi-agent systems have faced issues with performance, token consumption, and transparency.

Crypto Market AI's Take

Manus's introduction of Wide Research signals a significant shift in how AI agents can be leveraged for complex, data-intensive tasks. This parallel processing approach could dramatically accelerate research, analysis, and creative generation compared to sequential methods. For users in the cryptocurrency space, this could translate to faster market trend analysis, more comprehensive sentiment monitoring, and quicker identification of trading opportunities across a vast number of assets. Our platform emphasizes the power of AI in navigating the complexities of the crypto market, and features like Wide Research align with our mission to provide cutting-edge tools for intelligent decision-making. Explore our insights on how AI agents are transforming crypto analysis for a deeper understanding of these advancements.

You’ve heard of AI ‘Deep Research’ tools…now Manus is launching ‘Wide Research’ that spins up 100+ agents to scour the web for you

Platform and Features

Availability and Pricing

Technical Aspects and Challenges

Crypto Market AI's Take

More to Read: