Bench v2 Ablation Study

The v1 benchmark measured throughput only (runs/min). It did not capture retrieval quality, routing convergence speed, or memory compaction ratio — making it impossible to evaluate improvements to SmartRetrieval or Thompson Sampling.

Bench v2 adds four dimensions: (A) retrieval quality (MRR@5, Recall@10 on held-out queries), (B) routing convergence (runs until p(win) ≥0.7 for optimal agent), (C) compaction ratio (bytes/trajectory after archival), (D) token efficiency (output tokens / task complexity score). Ablation sweeps test each component in isolation.

Full regression detection on retrieval and routing changes. Suite adds 45s to CI on standard hardware. Baseline established: MRR@5=0.74, convergence=12 runs, compaction=0.38, efficiency=1.24.