SWISwarm Intelligence
SWIBiology atlas
Research snapshot ·

Termites / Building with local rules

How can many agents build one product without conflicting work?

Isoptera · TERMES · 6 linked studies · Sources checked: 06.09.2026

What happens in nature?

Stigmergy is the idea of environment-mediated coordination originating in termite construction. TERMES used this inspiration to demonstrate collective construction with rules derived from a target structure and robots using local sensing.

Transfer boundaryTERMES construction guarantees are limited to its specified physical structures and rules. Code or document agents have no equivalent guarantee; dependencies and acceptance tests must be explicit.

From mechanism to protocol

TargetTask ATask BIntegrationPrerequisite
  1. Target and task prerequisites
  2. Independent artifacts with explicit owners
  3. Acceptance test → integration
SWI adaptation · conceptual communication diagram
In biologyA counterpart to test in your agents
Partial structureVersioned repository, document or task graph
Local construction conditionReadiness condition for a task with completed dependencies
Placing a blockSmall testable change with one owner
Structural feedbackRecorded test outcome and artifact contract

How can you use it in your swarm?

Produce in parallel with visible task ownership and intermediate artifacts.

  1. Specify the artifact

    Write acceptance criteria and module interfaces. Assign file or section ownership to tasks.

  2. Select ready work

    Start a task only after its prerequisite outputs are verified. Include expiry and version in the ownership record.

  3. Produce a small change

    Deliver in the expected format; include the input version, checks performed and remaining uncertainty.

  4. Integrate and unblock

    The integrator runs acceptance checks and unblocks dependent tasks on success. Do not feed failed artifacts to the next agent.

Configure the recipe with your task, agent count and budget

Start with an experiment

Build the same small product with a sequential agent, a free-chat team and a dependency-graph team. Match hidden acceptance tests and aggregate budget.

What happens if you remove the mechanism?
Change an intermediate artifact format. Count downstream failures with and without interface checking.
Primary failure risk
Local checks can pass while the integrated product breaks. Check interface drift, stale writes and conflicting file ownership.

Evidence and related studies

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

1999 · Historical reviewArtificial Life 5(2), 97–116

A Brief History of Stigmergy

Stigmergy describes coordination through environmental modifications that stimulate subsequent actions.

What can I use? Interpretation, limits and provenance

SWI engineering interpretation

Define the shared artifact agents read and modify before designing messaging.

Limitation

A historical review, not a performance experiment for a particular agent architecture.

Source record

Guy Theraulaz, Eric Bonabeau
Publication: 1999 · exact day not verified
Publication record review · Checked: 2026-09-06

2014 · Journal paperScience 343(6172), 754–758

Designing Collective Behavior in a Termite-Inspired Robot Construction Team

TERMES derived local rules from a target structure and demonstrated construction by three autonomous robots coordinating through the shared environment.

What can I use? Interpretation, limits and provenance

SWI engineering interpretation

Define prerequisites, ownership and completion contracts for each task.

Limitation

Robotics evidence applies under constrained construction rules; free-form code generation has no equivalent guarantee.

Source record

Justin Werfel, Kirstin Petersen, Radhika Nagpal
Publication: 2014 · exact day not verified
Abstract review · Checked: 2026-09-06

2023 · arXiv versionarXiv:2308.00352v7 · ICLR 2024

MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework

MetaGPT combines standardized workflows and specialist roles in a software production pipeline with intermediate verification.

What can I use? Interpretation, limits and provenance

SWI engineering interpretation

Tie handoffs to inspectable intermediate artifacts and contracts.

Limitation

Standardization alone is not correctness; evaluate integration and test outcomes separately.

Source record

Sirui Hong et al.
Publication: 2023-08-01
Reviewed revision: 2024-11-01
Abstract review · Checked: 2026-09-06

2023 · arXiv versionarXiv:2308.08155 · COLM 2024

AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation

AutoGen combines models, tools and human input in customizable agent conversation patterns.

What can I use? Interpretation, limits and provenance

SWI engineering interpretation

Specify message schemas, round limits and completion independently of the framework.

Limitation

A framework's capabilities do not establish superiority of a particular swarm topology.

Source record

Qingyun Wu et al.
Publication: 2023-08-16
Abstract review · Checked: 2026-09-06

2024 · arXiv versionarXiv:2407.01489

Agentless: Demystifying LLM-based Software Engineering Agents

Agentless evaluates a simple approach split into localization, repair and patch validation.

What can I use? Interpretation, limits and provenance

SWI engineering interpretation

Include a simple fixed workflow when evaluating a swarm.

Limitation

The 2024 benchmark and model conditions are not a current product ranking.

Source record

Chunqiu Steven Xia, Yinlin Deng, Soren Dunn, Lingming Zhang
Publication: 2024-07-01
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