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>
Three exploratory research documents under docs/research/:
- architecture/three-tier-rust-node.md (3,382 words) — exploration of a
dual-ESP32-S3 + Pi Zero 2W node architecture with BQ24074 power-path,
ESP-WIFI-MESH + LoRa fallback + QUIC backhaul, and an esp-hal/Embassy
vs esp-idf-svc Rust toolchain split. Status: Exploratory — not adopted.
- sota/2026-Q2-rf-sensing-and-edge-rust.md (3,757 words) — twelve-section
state-of-the-art survey covering WiFi CSI through-wall pose, IEEE 802.11bf
(ratified 2025-09-26), edge ML on ESP32-class hardware, embedded Rust
ecosystem maturity (esp-hal 1.x, esp-radio rename, embassy-executor
ISR-safety on esp-idf-svc), LoRa for sensor mesh fallback, QUIC for IoT
backhaul, solar power-path management beyond BQ24074, mesh routing
alternatives, and Pi Zero 2W secure-boot reality.
- architecture/decision-tree.md (1,461 words) — Mermaid decision tree
mapping each load-bearing decision in the three-tier proposal to its
dependencies, evidence-for-yes/no, and prospective ADR slot.
No production code, firmware, or ADRs touched. Research-only.
Co-Authored-By: claude-flow <ruv@ruv.net>
ruv