4 papers
Passing Coarse Marginal Checks Can Be Cheap: Persona Mixtures and Imprecise Treatment-Response Estimates in an LLM Persona Panel
Yohei Nakajima
Large language models are increasingly used as synthetic research participants and are often validated by whether their marginal responses resemble human data. We study a fixed pan…
The Shared Discovery Paradox: How a One-Answer Rule Turns Better Information into Worse Search
Yohei Nakajima
Organizations often pool dispersed information into one ranking and then allow many agents to act on that shared view. In a discovery problem, this can improve beliefs while reduci…
Regimes: An Auditable, Held-Out-Gated Improvement Loop Demonstrated on LongMemEval with ActiveGraph
Yohei Nakajima
Autonomous improvement loops are hard to trust because the improvement process is usually external scaffolding bolted onto the agent: failures go unlogged, diagnoses cannot be repl…
The Log is the Agent: Event-Sourced Reactive Graphs for Auditable, Forkable Agentic Systems
Yohei Nakajima
Most agent frameworks are built around the language model: a conversation loop comes first, then tools, then rules, and finally a logging layer bolted on for observability, with st…