Multi-Agent Team All architectures
v8 · architecture

Self-Consistency

sample in parallel, judge the best

Self-Consistency architecture

v8 self-consistency

The same task is sampled several times independently and in parallel; a judge then either selects the strongest answer or merges the candidates into a consensus. Best for questions where a single attempt is unreliable but agreement across attempts signals a good answer.

Sampler
Judge

sample in parallel, judge the best

How it works
  1. 1The task is sent to N sampler agents that run independently and in parallel.
  2. 2Each produces its own complete answer, unaware of the others.
  3. 3A judge reads all N candidates.
  4. 4The judge selects the strongest, or merges complementary answers into one.
When to use

Questions where one attempt is noisy but agreement across attempts signals quality.

Trade-off

N parallel samples cost N× the tokens of a single attempt for the sampling step.

Agents
SamplerProduces one independent attempt (×N in parallel)
JudgeSelects the best sample or merges a consensus
Note

Cheap reliability boost on reasoning-heavy questions: sample a few times, let a judge reconcile. The judge’s merge step is where a lot of the value is — it’s not just a vote.