Evolution Swarm

A population of virtual trading agents evolving through natural selection. Each generation, the weakest die and the strongest reproduce with mutations. The strategy isn't designed — it's discovered.

Generation
1
Cycle
26 / 48
Population
12
Alive
12
Generations Completed
2
Generation 1 progress 54%
Current Champion
ec9327dc
+0.000 TAO
Fitness: 0
Trades: 0
Win Rate: 0%
Drawdown: 0%
Open: 0
DNA
survivor from gen 0 (fitness=-5.0)

Population

AgentGenPnLTradesWin %FitnessDrawdownPortfolioStatus
ec9327dc ← 68981+0.00000%00%10 τalive
8e063979 ← d7801+0.00000%00%10 τalive
633d6518 ← fc271+0.00000%00%10 τalive
a165c334 ← eb171+0.00000%00%10 τalive
1c5e9d5a ← b4de1+0.00000%00%10 τalive
2f0a7962 ← d3f21+0.00000%00%10 τalive
02bb1eb2 ← eb171+0.00000%00%10 τalive
86c060c5 ← d3f21+0.00000%00%10 τalive
632ab00c ← fc271+0.00000%00%10 τalive
a6a0f528 ← eb171+0.00000%00.8%9.9288 τalive
416bc00c ← b4de1+0.00000%00%10 τalive
04d2d615 1+0.00000%02.5%9.7564 τalive

Generation History

GenBest FitnessAvg FitnessChampionTime
0-5-5.5689849482026-03-26T08:18
0-5-5.5689849482026-03-26T08:35

How Evolution Works

1. Spawn — 12 virtual agents are created, each with randomly mutated strategy weights and risk parameters. One agent is seeded from TensorQ's learned weights.

2. Trade — Every cycle (30min), all agents paper-trade against real Bittensor subnet data. Same signals, same prices — different strategies.

3. Evaluate — After 48 cycles (24h), each agent gets a fitness score based on returns, win rate, and drawdown.

4. Select — Bottom 50% die. Survivors reproduce with random mutations to their weights and risk parameters.

5. Repeat — Each generation discovers better strategies. One wild card (fully random) agent maintains genetic diversity.

QLLM Training Integration

The swarm generates 12x more trading data than a single agent. Every virtual agent's decisions — entries, exits, signal weightings, and outcomes — feed into the QLLM training pipeline.

This creates a powerful feedback loop:

  • Evolved strategies → diverse training signals that a single agent would never explore
  • Failed mutations → negative examples teaching the model what doesn't work
  • Champion DNA → the winning weight configuration directly informs the local model's architecture
  • Cross-generation learning → the model sees strategy evolution over time, not just point-in-time decisions

Combined with TensorQ's main agent data (68K+ history rows, 240+ training pairs), the swarm dramatically accelerates QLLM convergence.