QARSA is a multi-agent quantitative trading research platform. It mines patterns, trains models, and stages a structured debate between six specialised agents — then writes a single, auditable decision per symbol, per cycle.
Three uncorrelated lines of evidence. A structured debate. One auditable output.
Most automated trading systems pick a method — rules, models, or narrative — and live with its failure mode. QARSA runs all three in parallel and only acts when they agree.
Track 1 is inductive: mine the price tape for rules that historically worked. Track 2 is deductive: train statistical and ML models to forecast the next move. Track 3 is narrative: read structured opinions from a stack of LLM-driven analyst agents.
Their failure modes are uncorrelated. When one is wrong, the other two usually disagree. That is the entire reason this system exists.
Enumerate a 120-rule grammar per symbol — entry × regime × hold. Walk-forward each one. Survivors must beat a 200-permutation random benchmark at Bonferroni α/120, clear a Sharpe > 1.0 risk gate, and produce at least ten trades.
Thirteen active model classes — six statistical, seven ML — trained under a strict walk-forward harness: 6mo train, 5d embargo, 3mo test, ~7 folds. Best fold by Sharpe is refit on its training window and joblib-dumped as a production artifact.
A separate stack of V4 analyst agents — regime, risk, behavioral, pattern librarian — each emit structured opinions into a shared memory graph. The V5 layer reads the latest meta-synthesis label and maps it to a long-or-flat vote.
The three are uncorrelated in their failure modes. That is what makes the consensus design valuable.
Stage 1 votes independently. Stage 2 argues both sides. Stage 3 scores a five-dimension rubric and emits the final decision. Latency p50 is under three seconds for the LLM voices.
Reads strategy_candidates under a rolling 365-day window with point-in-time integrity. Proposes long entries from rule-mined survivors.
Reads the walk_forward_runs survivor pool. Picks the highest-Sharpe model by regime and emits a long-or-flat vote.
Reads agent_memory_nodes for the latest V4 Meta-Synthesis or Stock Intelligence label and maps BULLISH/BEARISH to long-or-flat.
Sees the three stage-1 votes. Builds the strongest possible long case using LLM reasoning over the stack. Structurally optimistic by design.
Provides downside risk, sentiment, macro context. Holds a hard veto that fires when trailing 60-day drawdown is ≤ −15%.
Sees all five non-arbiter votes. Scores a five-dimension rubric and emits the final ConsensusDecision with Kelly-from-edge position sizing.
Weighted score is compared against the 0.55 entry threshold. Above it, the same number feeds Kelly-from-edge sizing — capped at 25% Kelly and 10% per name.
Higher historical returns demand stronger agreement. Returns above 100% per year require unanimity and a non-veto from the Bear — because returns that large are usually too good to be true.
Page 22 is six tabs — Today, Decisions, Agents, Strategies, Models, Trace. Every chart carries a plain-English LLM-written explanation. Routing to a brokerage stays gated until the operator explicitly arms it.
Three symbols cleared the gate this cycle — NVDA, AVGO and AMD — at tier B+ with at least 4 of 5 long votes. The Bear vetoed TSLA on a 60-day drawdown breach.
Agent D forces no_enter when the symbol's trailing 60-day drawdown breaches the −15% floor. Cannot be disabled.
Position size is computed Kelly-from-edge, clamped at 25% of full Kelly and 10% of portfolio NAV per name. Enforced before the decision is written.
The brokerage route is off by default. ConsensusDecisions are logged and stop. There is no path to a real order without an explicit arming flip in Page 21.
Post-close, the calibration engine joins ConsensusDecisions with realised outcomes and proposes per-symbol threshold overrides for the V4 agent stack. Only symbols with at least ten trades are adjusted — the floor that keeps the loop from chasing noise.
Today the loop calibrates V4 thresholds. V6 ConsensusDecision outcomes feed in next.