Autonomous Decision Loop

The meta-loop: research, hypothesize, backtest, deploy, monitor, improve.

The Autonomous Decision Loop is the brain of the system - the continuous cycle where the LLM researches markets, forms hypotheses, tests them, deploys strategies, monitors results, and learns from outcomes.

The Loop

1. Research

   Scan markets, aggregate signals from LLM forecasts, oracles, wallet consensus, and technical indicators.

2. Hypothesize

   Form a thesis: “Market X is mispriced because Y.” Score confidence.

3. Backtest

   Run automated backtest with robustness checks (permutation, walk-forward, CPCV).

4. Deploy

   Start in staging (paper mode), then promote to live if performance holds.

5. Monitor

   Track P&L, health, edge decay, and execution quality in real time.

6. Improve

   Adjust parameters, retire losers, scale winners. Loop back to Research.

Each iteration of this loop is logged with full reasoning for audit.

Research Pipeline

The LLM periodically scans the market universe for opportunities.

# Scan for opportunities via MCP
opportunities = research.scan(
    universe=fund.market_universe,
    signals=["llm_forecast", "oracle", "wallet_consensus"],
    min_edge=0.05,
    min_liquidity=1000,
)
# Returns ranked opportunities with evidence

Signal Aggregation

Multiple signal sources are combined:

Signal	Source	Weight
LLM Forecast	llm_forecast()	Primary
Oracle Edge	scan_edges()	Secondary
Wallet Consensus	compute_consensus()	Confirming
Technical	regime_signal, momentum	Timing
Sentiment	llm_scan() with news	Confirming

Automated Backtest-to-Deploy

When the LLM identifies an opportunity, it constructs a strategy, backtests it, and deploys if it passes checks.

Deploy Decision Criteria

Criterion	Threshold	Rationale
Sharpe ratio	> 1.0	Minimum risk-adjusted return
Total trades	> 30	Statistical significance
Robustness p-value	< 0.05	Not due to luck
Walk-forward consistency	> 60% OOS windows positive	Not overfit
Max drawdown	< 20%	Acceptable worst case

# Backtest-to-deploy flow
hypothesis = research.best_opportunity()
result = backtest(hypothesis.to_strategy(), data=historical_data)

if result.passes_criteria(min_sharpe=1.0, min_trades=30, max_drawdown=0.20):
    robustness = robustness_test(result)
    if robustness.combined_p_value < 0.05:
        controller.deploy(hypothesis.to_strategy(), mode="staging")

Memory & Learning

The LLM has persistent memory across sessions to avoid repeating mistakes.

What Gets Stored

Memory Type	Example
Strategy performance	”MM on crypto markets averaged Sharpe 1.8 in Q1”
Market-type models	”Political markets are mean-reverting before elections”
Regime mappings	”High-vol regime: widen spreads, reduce directional”
Edge decay	”Wallet copy-trading edge decayed from 15% to 3% over 60 days”
Failure reasons	”Directional on sports markets failed due to resolution timing”

Learning Feedback

After monitoring for N days, the system diagnoses and records outcomes:

Profitable

Record the success pattern and scale up capital allocation.

Regime Changed

Record regime sensitivity. Adjust strategy for new conditions.

Liquidity Dried Up

Record minimum liquidity requirement for this market type.

Edge Was Spurious

Record false positive. Tighten backtest criteria for similar markets.

Execution Was Poor

Adjust execution parameters (spread, size, timing).

Continuous Improvement

The loop isn’t just deploy-and-forget. Active strategies are continuously monitored and adjusted.

Action	Trigger
Re-optimize parameters	Weekly, or when performance drops
Mutate strategy	Try small variations on successful strategies
Prune dead strategies	No edge detected for N consecutive days
Rebalance capital	Shift from fading strategies to growing ones
Update models	New market resolution provides calibration data

MCP Tools

Tool	Description
backtest_hypothesis	Backtest a strategy idea, return results + robustness
decision_log	View recent autonomous decisions with reasoning
learning_summary	What the system has learned (successful patterns, failures)
improvement_suggestions	Recommended parameter changes based on recent performance