We are open-sourcing Runtime AI Scientist, the code behind our paper on Runtime Agent Coordination (RAC). Instead of a fixed workflow, the agent that just finished picks who acts next from the live state of the research. Runtime selection had the highest mean score on all three AI-scientist hosts we tested.
Systemind Team · 2026-10-03Muse is Meta's bet that people will hand an AI agent real authority over their accounts, money and time. This teardown covers the product decisions that make delegation workable, and the architecture underneath: a VM per user, a single permission authority called Sentinel, credentials the model never sees, and kernel-level taint tracking.
Yu Chen · 2026-10-02Making individual agents more capable does not make them better at working together. We are building adaptive agent networks that form around a task, revise their division of labour, and carry verified experience into future work.
Xisen Wang · 2026-09-13A research agenda for coordinating capable, tool-using agents across information, ownership, and control boundaries.
Systemind Team · 2026-08-22We exported one 63-hour coding session and had other agents answer 100 pre-registered questions about it. Raw transcripts scored 22/30 on the questions that matter. A 1,200-line compiled layer scored 30/30. Here is the format, the experiments, and the two things it does not fix.
Eason · 2026-08-13