SWISwarm Intelligence
SWIBiology atlas
Research snapshot ·

Bacterial communities / Threshold-triggered action

When is there enough evidence to trigger an expensive next step?

Vibrio harveyi · 3 linked studies · Sources checked: 06.09.2026

What happens in nature?

Vibrio harveyi's quorum-sensing circuit detects chemical signals called autoinducers and regulates gene expression. Mok, Wingreen and Bassler investigated the joint processing of two signal channels and its relationship to target genes.

Transfer boundaryChemical signal accumulation is not a truth counter. An agent adaptation must explicitly check signal independence, provenance and age.

From mechanism to protocol

TestSourceReviewGateNext stage
  1. Test, source and review signals
  2. Verify independence · check the threshold
  3. Advance when requirements are satisfied
SWI adaptation · conceptual communication diagram
In biologyA counterpart to test in your agents
Autoinducer channelTyped validation signal: test, source or review
Signal accumulationEvidence record with expiry and source identity
Conditional responseNext stage gated by a predefined rule

How can you use it in your swarm?

Open the next work stage when independent, valid inputs are ready.

  1. Derive the threshold

    Specify prerequisites up front, such as one passing test and a separate source review. Agreement by three agents is not sufficient by itself.

  2. Track signal origin

    Attach evidence_id, origin_id and expires_at. Do not count agents copying one source as separate support.

  3. Combine valid inputs

    Check every required signal type. Do not override a failing test by collecting more positive votes.

  4. Record the transition

    Preserve the signal IDs used in a transition. If conditions fail, report an explicit waiting reason or timeout.

Configure the recipe with your task, agent count and budget

Start with an experiment

Compare a fixed majority threshold with a gate checking source, age and type. Include duplicate and stale signals.

What happens if you remove the mechanism?
Disable source deduplication. Pass the same wrong report through five agents and measure false gate openings.
Primary failure risk
Duplicate reports can create false sufficiency. An old passing test does not validate a new artifact version; bind signals to versions.

Evidence and related studies

Read biological evidence and agent research separately. The engineering interpretations below are SWI synthesis.

2003 · Journal paperThe EMBO Journal 22(4), 870–881

Vibrio harveyi quorum sensing: a coincidence detector for two autoinducers controls gene expression

V. harveyi integrates signals from two autoinducer channels in a circuit regulating gene expression.

What can I use? Interpretation, limits and provenance

SWI engineering interpretation

Combine multiple independent signals before triggering an expensive action.

Limitation

Chemical concentration is not a confidence score; copied agent reports are not independent evidence.

Source record

Kenny C. Mok, Ned S. Wingreen, Bonnie L. Bassler
Publication: 2003 · exact day not verified
Abstract review · Checked: 2026-09-06

2025 · arXiv versionarXiv:2503.13657v3

Why Do Multi-Agent LLM Systems Fail?

Version 3 presents a dataset of over 1,600 traces and 14 failure modes grouped into design, inter-agent misalignment and verification.

What can I use? Interpretation, limits and provenance

SWI engineering interpretation

Log failure causes such as wrong tasks, broken handoffs and premature termination alongside outcomes.

Limitation

The taxonomy is a substantial starting point, not a claim to cover every failure in all systems.

Source record

Mert Cemri et al.
Publication: 2025-03-17
Reviewed revision: 2025-10-26
Abstract review · Checked: 2026-09-06

2025 · arXiv versionarXiv:2512.08296v3

Towards a Science of Scaling Agent Systems

Version 3 compares 260 configurations across six benchmarks; coordination benefits depend on task structure and communication overhead.

What can I use? Interpretation, limits and provenance

SWI engineering interpretation

Compare single-agent, independent parallel and coordinated teams at the same aggregate budget.

Limitation

Reported counts changed between versions; this entry uses v3. Findings are not a universal scaling law.

Source record

Yubin Kim et al.
Publication: 2025-12-09
Reviewed revision: 2026-04-08
Abstract review · Checked: 2026-09-06