Executive Summary
Paper XIX established that minimal fixed priming (15 tokens + reset) achieves CE 0.733. A natural question is whether an adaptive agent — a "shepherd" that monitors the receiver and dynamically adjusts its priming — could do even better. This paper tests three shepherd strategies: storyteller (narrative framing), provocateur (challenge-based prompting), and director (explicit instruction).
The results are unambiguous: adaptive priming is not just unnecessary, it is actively harmful. All bare shepherd strategies perform worse than the no-coordination baseline: storyteller degrades by -12.3%, provocateur by -26.7%, and director by -37.1%. The more directive the shepherd, the worse the outcome. When reset is added before shepherd intervention, all three strategies converge to the performance of reset alone — the shepherd content contributes nothing beyond what the reset already provides.
The ratio tells the story clearly: reset accounts for 22:1 of benefit relative to the best shepherd content. The optimal coordination protocol remains the one discovered in Paper XIX — reset followed by fixed minimal priming (CE 0.733). No adaptive strategy tested in this paper improves upon it. This result is consistent with the interference framework: any content added to the receiver's context beyond the minimum needed for mode switching introduces interference that degrades coordination rather than enhancing it.
Key Findings
- All bare shepherds worse than baseline: Storyteller -12.3%, provocateur -26.7%, director -37.1% — more directive = more harmful
- Reset dominates: With reset, all shepherd strategies converge to reset-alone performance — shepherd content contributes nothing
- 22:1 reset-to-content ratio: Reset accounts for 22x more benefit than the best shepherd content
- Best condition unchanged: Reset + fixed priming (CE 0.733) from Paper XIX remains optimal
- Interference framework confirmed: Additional context beyond minimum mode-switching requirements introduces interference
Key References
- McEntire (2026) — Ritual Shape: 15 tokens + reset as optimal protocol (Paper XIX)
- McEntire (2026) — Ensemble Gravity: priming selection vs other strategies (Paper XVIII)
- McEntire (2026) — The Coordination Problem Is Interference: synthesis (Paper XXI)
- McEntire (2026) — Context Fences: mode switching, not garbage collection (Paper XXII)