multi-agent systems

Google-affiliated researchers Benjamin Bratton, Blaise Agüera y Arcas and James Manyika propose "Artificial Symbiotic Intelligence," a framework in which AGI emerges from a social system of people and AI agents rather than a single self-improving machine. The essay, written for the Deepmind Institute, is a conceptual argument and reports no benchmark results.

Sakana AI has released Fugu Ultra v2, described as a learned multi-agent orchestration system rather than a single monolithic model. It offers a 1M-token context window, configurable reasoning effort, and pricing of $5 per 1M input tokens and $30 per 1M output tokens.

Sakana AI has released Fugu Max, the cost-performance tier of its Fugu family, which uses a trained language model to route tasks across a pool of open-weights and specialized models rather than functioning as a single monolithic network. The model offers a 1 million token context window at a flat $2 input / $6 output per million tokens.

Google DeepMind tasked 100 AI agents running on Gemini 3.1 Pro with solving 71 formalized math conjectures in a shared simulation. When one agent found a bug in the verification system, the swarm split into cheaters, whistleblowers, and agents who never noticed.

OpenAI is reportedly developing a new model family called Astra, designed to coordinate multiple agents on complex problems over hours or days. The models are already in testing and would be first to go through a planned U.S. government pre-release review, according to The Information.

Cursor's upgraded agent swarm splits AI coding work between expensive frontier planner models and cheap worker models, reaching 100 percent accuracy on a from-scratch SQLite-to-Rust benchmark. Cursor claims the split cuts codebase size by up to 85 percent and worker costs by a factor of 15 compared to running a single frontier model alone.