Search papers, labs, and topics across Lattice.
This paper introduces Metis, a multi-provider runtime that transforms provider streams into typed events, enhancing the management of software agents that interact with various external systems. By implementing a four-class mediation approach, the authors demonstrate a significant reduction in median elapsed time for operations, achieving a decrease from 25.958 ms to 14.146 ms across 30 matched real-I/O pairs. The findings highlight the effectiveness of Metis in making permission decisions and lifecycle transitions explicit, while also identifying limitations in fault handling and unauthorized effects.
Mediation with Metis slashes operation time by over 45%, making software agents more efficient in managing external interactions.
Software agents connect probabilistic model output to operations that change repositories, processes, networks, and graphical applications. We present Metis, a multi-provider runtime that converts provider streams into typed events before admitted calls reach external effects. Its execution path makes permission decisions, interference classes, terminal results, and lifecycle transitions explicit and inspectable. We evaluate these mechanisms on frozen source artifacts. Across 30 matched real-I/O pairs, four-class mediation reduced median elapsed time from 25.958 ms under forced serialization to 14.146 ms. The mean paired difference was -12.295 ms (95% bootstrap interval [-12.968, -11.694]), with mediation faster in all pairs. A ten-case fault matrix exposed duplicate-identifier and rollback limits. In a child-boundary ablation, the full gate-plus-registry condition blocked the declared unauthorized effect and hid all five escape tools. Removing both protections reversed both observations. A decision-only permission oracle matched all ten declared cases across five invocation routes. Five model conditions also completed a fixed Read-marker protocol in 3/3 trials each. These results support bounded claims about dispatch, permission routing, child authority, and provider-valid trace closure. They do not establish model competence, semantic safety, rollback, or superiority over another runtime.
