Surveys the relevant slice of the 2026-Q2 agentic-AI literature (long-horizon
agents, agent-memory discipline, self-improving/continual learning, the ESP32
mesh-as-a-swarm framing, the "agent harness on the MCU" pattern, retrieval/
quantization incl. the CoDEQ verdict, agentic verification) and the related
RF/WiFi-sensing SOTA (CSI foundation models — the 1.3M-sample MAE scaling study
showing data > capacity, AM-FM, CIG-MAE amplitude+phase MAE; source-free domain
adaptation; the DensePose-from-WiFi lineage; multistatic fusion; mmWave+WiFi
vitals; adversarial/privacy; through-wall). Maps every finding to a RuView ADR
with impact/effort/horizon. Headline recommendation: re-scope MERIDIAN (ADR-027)
as a heterogeneous-CSI MAE pre-train -> small task head.
Lives under docs/research/sota/ alongside 2026-Q2-rf-sensing-and-edge-rust.md.
Co-Authored-By: claude-flow <ruv@ruv.net>
8b2a2d94e8