SVAF

Two-Level Coupling

The Mesh Memory Protocol evaluates signals at two levels. Both are necessary. Neither is sufficient alone.

Claude Code → sym_remember("user sedentary 2hrs, exhausted")
  → CMBEncoder decomposes into 7 fields
  → broadcast to mesh peers

MeloMove receives:
  → peer drift: 1.05 (coding ≠ fitness — rejected at peer level)
  → SVAF per-field evaluation:
      mood: "exhausted, low energy"     → relevant (high gate)
      issue: "sedentary 2 hours"        → relevant (high gate)
      focus: "debugging auth module"    → irrelevant (low gate)
  → content ACCEPTED — field-level relevance overrides peer rejection
  → fusion produces NEW CMB for MeloMove's local memory
  → MeloMove synthesizes recovery workout recommendation

Without two-level coupling, the fitness agent either accepts everything from the coding agent (noise) or rejects everything (misses critical health signals). SVAF makes the distinction that scalar evaluation cannot.

Why Scalar Evaluation Fails

A signal with highly relevant mood but irrelevant focus produces a moderate cosine similarity score. The score may or may not cross the threshold — depending on incidental vector interactions, not semantic relevance. The decision is brittle and uninterpretable: the agent cannot explain which dimensions drove acceptance or rejection.

How SVAF Works

SVAF operates on Cognitive Memory Blocks — each memory signal decomposed into 7 typed semantic fields (CAT7 schema). The evaluation pipeline has four stages:

The gate values provide per-field interpretability: for any fusion event, you can inspect which fields were absorbed from the incoming signal and which were replaced by local context. This is the auditability that scalar evaluation cannot provide.

Per-Agent Temporal Drift

The same signal has different temporal relevance depending on the receiver. SVAF conditions the fusion gate on a per-agent temporal freshness factor:

A coding agent’s “user exhausted after 8 hours” is relevant to the music agent for 30 minutes (adjust the playlist) but relevant to the fitness agent for 3 hours (sedentary pattern detection). Same signal, same content drift, but different temporal drift based on the receiver’s domain needs.

Cross-Domain Relevance

Not all CMB fields carry equal value across domain boundaries. SVAF encodes a minimal hypothesis: mood (affective state) has higher cross-domain relevance than other fields. A fitness agent, a music agent, and a coding agent all benefit from knowing the user’s emotional state. Domain-specific fields (what exactly the user is coding) stay sovereign.

The fusion gate is trained with a soft ordering constraint — for accepted signals, the mood gate should exceed the mean of other field gates. This is the only supervision on gate values. The specific gate magnitudes and the relative ordering of other fields emerge from the decision and drift objectives alone.

Where SVAF Fits the Stack

Layer 7  APPLICATION     Domain Agents
─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─
Layer 6  xMesh           Per-agent LNN (coupled CfC)  ┐
Layer 5  SYM             Synthetic Memory             ├ Mesh Cognition
Layer 4  COUPLING        Drift · SVAF ← you are here  ┘
─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─
Layer 3  MEMORY          L0 · L1 · L2
Layer 2  CONNECTION      Handshake · Gossip
Layer 1  TRANSPORT       IPC · TCP · WS · Push
Layer 0  IDENTITY        nodeId · keypair

OUTBOUND (agent → mesh):
  Agent observation → CMBEncoder (7 CAT7 fields) → CMB
  → broadcast via MMP (Layer 1–2)
  → stored as L1 memory (Layer 3)

INBOUND (mesh → agent):
  → SVAF evaluates per field (Layer 4)
    → per-field drift: which fields are relevant?
    → fusion gate: how much of each field to accept?
    → decision: aligned / guarded / rejected
  → if accepted: fusion produces NEW synthesised CMB

BOTH flows feed agent’s own xMesh LNN (Layer 6):
  → SYM encodes CMBs → CfC hidden state (Layer 5)
  → agent’s CfC evolves cognitive state from own + mesh CMBs
  → h1, h2 broadcast to peers (state-sync)
  → agent acts → remember() → new outbound CMB → loop

SVAF is the gatekeeper. Nothing enters xMesh without passing per-field evaluation. This is by design: the quality of collective intelligence depends entirely on the quality of what enters the collective.

Training

SVAF is trained end-to-end on LLM-authored multi-agent narrative scenarios — temporal stories capturing realistic interaction patterns across 20 agent types in 8 domains. Each narrative is a sequence of timestamped signals from different agents, telling a coherent causal story about a user’s state evolution.

Per-field drift ground truth comes from independently annotated field relevance scores — not computed from the model’s input embeddings. Gate values emerge from the decision and drift objectives with minimal supervision. Full training methodology in the forthcoming paper.

Related

Intellectual Property

SVAF is original work by Hongwei Xu and SYM.BOT Ltd. The following remain proprietary: trained neural models and training procedures, field encoder architecture, fusion gate internals, production configurations, and domain-specific product integrations.

Academic citation of this work is permitted and encouraged.

For partnership inquiries: info@sym.bot