Tag
Yohei Nakajima announces his first arXiv paper on event-sourced reactive graphs for auditable, forkable agentic systems, connecting graphRAG, DAG workflows, and log/trace graphs.
ActiveGraph is an event sourcing runtime that treats the append-only event log as the agent itself. It achieves deterministic replay, forking experiments, and end-to-end traceability through graph projection, providing a new architecture for long-running, auditable agent systems.
Yohei Nakajima will present ActiveGraph, an event-sourced graph runtime for building auditable agents, at the AI Engineer conference.
This paper introduces Regimes, an auditable, held-out-gated improvement loop built on the ActiveGraph runtime for self-improving agents. It demonstrates modest improvements on the LongMemEval dataset by autonomously discovering prompt repairs that pass static checks, sandbox execution, and held-out validation.
Regimes is an auditable, held-out-gated improvement loop built on the ActiveGraph event-sourced runtime. It diagnoses failures in AI agents, proposes repairs, and promotes them only after passing multiple gates, improving accuracy on LongMemEval by up to +0.10.
Yohei Nakajima published his first arXiv paper, "The Log is the Agent: Event-Sourced Reactive Graphs for Auditable, Forkable Agentic Systems", introducing a method for agents to coordinate through persistent replayable state.
Yohei Nakajima open-sources Active Graph, an event-sourced reactive graph runtime for long-running agents that provides persistent state, fork-and-diff agent runs, and full auditability, representing a new paradigm in agent architecture.