Tag
This paper introduces a statistically defined decision layer for continual-learning systems, allowing expert pools to decide whether to reuse existing models, spawn new ones, or defer based on accumulated evidence, with theoretical guarantees and system contributions for managing nonstationary data streams.
Introduces Spice, an open-source decision layer that acts as a 'brain' above execution agents like Claude Code and Codex, enabling context-aware task delegation and structured decision-making.
Spice is an open-source runtime that acts as a decision layer above AI agents, observing context, simulating options, and dispatching tasks to agents before execution.