TL;DR
TransForm is presented, a control/data-plane split in which MCP returns a small envelope plus a machine-readable descriptor, and large payloads are delivered over stream-able HTTP as JSON, Parquet, or Arrow IPC (blob or chunk stream).
MCP-GRANITE is presented, an open-source extensible benchmark framework that treats tool-interface granularity as a controlled variable for MCP-based agents, evaluated under edge and IoT scenarios and identifies tool-interface granularity as a key design parameter for MCP-based agents.
It is argued that context assembly in ContextPipe is structurally isomorphic to query execution in a relational database: both execute under a hard budget, exploit a tiered cache, and leverage statistics.
Git4Data is presented, a database-native version-control layer for agentic workflows that sheds light on how relational databases can better support AI agents through efficient versioning.
This work proposes control-data flow separation, where execution-critical control is represented as typed, validated program objects, while task-relevant language remains the optimizable data flow for agent communication.
AgentWeave is introduced, a deterministic pre-inference routing layer that constructs a bounded model-visible action space using eligibility, requirement, capability, and routing signals and shows lower mean local-model latency.
A reproducible benchmark and reference-gateway design, evaluated on synthetic data, for what controls at that boundary can and cannot do, and quantifying why value-level detection must be a backstop, not the primary control.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
