CouncilEx.Rounds.WeightedSynthesis (CouncilEx v0.1.0)

Copy Markdown View Source

Chair synthesis round that exposes per-member weights to the chair prompt.

Used by CouncilEx.Councils.WeightedConsensus. Behaves like CouncilEx.Rounds.Synthesis but attaches a :weight to each member's digest so the chair (or downstream code) can weight contributions by reliability.

Weight resolution order, per member:

  1. Static :weight opt declared on the member
  2. :confidence field on the %MemberResult{} (if populated)
  3. Equal weight 1.0 / N as fallback

Weights are normalized to sum to 1.0 across members with :ok status.

Inspired by Wu et al. Council Mode (arXiv:2604.02923).

Round opts

  • :expose_confidence — boolean (default true). When false, the raw :confidence field is hidden from the chair's input; only the normalized :weight is surfaced. Set to false to test the finding from Wu et al. Can LLM Agents Really Debate? (arXiv:2511.07784) that visible peer confidence biases downstream reasoning toward conformity. The chair is terminal (not a peer that can capitulate to a majority), so the default keeps confidence visible — but the option exists so callers can audit sensitivity to this signal.

Wu 2025 alignment for OTHER rounds

This is the only built-in round that ever exposes confidence/weight to a downstream prompt. Rounds.{PeerReview, Critique, AnonymizedPeerReview} only surface parsed content / response text to peers — no per-member confidence numbers, no running vote tallies. That makes the existing peer-visibility rounds Wu-2025-safe by default: agents see what others said, but not "X others agreed" or "peer Y was 90% confident", which the paper identifies as the conformity trigger.

See docs/RELATED_WORK.md for the broader analysis.