SWISwarm Intelligence
SWIBiology atlas
Research snapshot ·

Physarum / Adaptive networks

How should a swarm's communication graph change with experience?

Physarum polycephalum · 4 linked studies · Sources checked: 06.09.2026

What happens in nature?

In Tero and colleagues' experiment, Physarum formed transport networks between food locations. A comparison with Tokyo rail infrastructure examined trade-offs among network cost, transport efficiency and fault tolerance.

Transfer boundaryThis organism is a multinucleate single-celled life form, not a swarm of independent individuals. The agent adaptation is a network-design hypothesis, not biological equivalence.

From mechanism to protocol

123456
  1. Initial communication network
  2. Verified contribution per connection
  3. Update weight · preserve a fallback path
SWI adaptation · conceptual communication diagram
In biologyA counterpart to test in your agents
Flow-carrying tubeCommunication edge with recorded output consumption
Network costMessage tokens, latency and routing overhead
AdaptationEdge-weight updates from verified experiment results
Alternative routeFallback handoff for critical information

How can you use it in your swarm?

Update communication paths using measured contribution and monitor single-link dependence.

  1. Freeze the initial graph

    Record a fixed graph for initial evaluation. Define each edge's information payload and cost unit.

  2. Measure contribution

    Link each handoff to information actually used and the final test outcome. Message count is not success.

  3. Update under control

    Update only between evaluation rounds. Change few edges per round so the effect remains traceable.

  4. Test the fallback

    Remove one strong connection and rerun the task. Report savings alongside quality loss after interruption.

Configure the recipe with your task, agent count and budget

Start with an experiment

Compare fixed and utility-updated graphs on the same task sequence; keep final evaluation questions outside the update loop.

What happens if you remove the mechanism?
Remove fallback links, then make one specialist unavailable. Show cost savings and recovery loss together.
Primary failure risk
Rewarding frequently used routes can create an echo chamber. Monitor access to rare expertise and distribution shifts.

Evidence and related studies

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

2010 · Journal paperScience 327(5964), 439–442

Rules for biologically inspired adaptive network design

Physarum networks achieved comparable trade-offs in efficiency, cost and fault tolerance in a Tokyo rail-network example.

What can I use? Interpretation, limits and provenance

SWI engineering interpretation

Retain communication edges for utility relative to cost, not frequency alone.

Limitation

Physarum is a multinucleate single-celled organism, not a colony of independent LLM agents.

Source record

Atsushi Tero et al.
Publication: 2010-01-22
Abstract review · Checked: 2026-09-06

1998 · Journal paperJAIR 9, 317–365

AntNet: Distributed Stigmergetic Control for Communications Networks

Distributed mobile agents adapt routing tables through indirect, asynchronous information exchange mediated by the network.

What can I use? Interpretation, limits and provenance

SWI engineering interpretation

Update task routing from observed results rather than fixed role titles.

Limitation

Network packet costs are measurable; LLM correctness requires an additional external evaluator.

Source record

Gianni Di Caro, Marco Dorigo
Publication: 1998-12-01
Abstract review · Checked: 2026-09-06

2025 · arXiv versionarXiv:2510.10047v1

SwarmSys: Decentralized Swarm-Inspired Agents for Scalable and Adaptive Reasoning

SwarmSys combines explorer, worker and validator roles with adaptive matching and pheromone-inspired reinforcement.

What can I use? Interpretation, limits and provenance

SWI engineering interpretation

Tie trail strength to verified task outcomes rather than an agent's self-reported confidence.

Limitation

Preprint results belong to the authors' experiments; this app has not reproduced that performance.

Source record

Ruohao Li et al.
Publication: 2025-10-11
Abstract review · Checked: 2026-09-06

2026 · arXiv versionarXiv:2605.29790v1

Evolve as a Team: Collaborative Self-Evolution for LLM-based Multi-Agent Systems

Meta-Team preserves execution context and uses post-task communication to improve agent behavior, coordination and team organization.

What can I use? Interpretation, limits and provenance

SWI engineering interpretation

Turn retrospectives into small protocol changes to evaluate in the next version.

Limitation

A 2026 preprint; distinguish learning from execution from adaptation to test data.

Source record

Zhezheng Hao et al.
Publication: 2026-05-28
Abstract review · Checked: 2026-09-06