20
Stack Exchange
votes

If two convex polygons tile the plane, how many sides can one of them have?

Posted on 1/13/2021
UQ ID:332
Science
Mathematics
Original

The set of convex polygons which tile the plane is, as of , known: it consists of all triangles, all quadrilaterals, families of pentagons, and three families of hexagons. Euler's formula rules out strictly convex -gons with . (The pentagonal case is by far the most difficult one.) I am interested in pairs of convex polygons that can collectively tile the plane. Specifically, I am curious how many sides can be in a polygon which is part of such a tiling. Here are some conditions to impose on such a tiling, from weakest to strongest:

There is at least one copy of each tile. (Without this condition, one can trivially take a pair consisting of a tiling polygon and any other convex polygon, and just never use the latter shape.)

There are at least copies of each tile.

There are infinitely many of each tile.

Every tile borders a tile of the other type.

The tiling is -isohedral, i.e., every tile can be carried to any other tile of the same shape by a symmetry of the tiling.

Each of these conditions implies those above it. In the weakest case, the number of sides is unbounded, as exhibited by the following example:

(The tiling is constructed by decomposing "wedges" of central angle into congruent isosceles triangles, and then combining the central triangles to yield an -gon in the center.) Requiring at least of each tile still yields arbitrarily high numbers of sides, by taking the above construction for and subdividing the -gon into "wedges" which are -gonal. On the other end of the spectrum, I have found a -isohedral tiling using regular -gons, shown below:

After consulting this paper, it seems that the tiling pictured above is of type in their classification scheme (shown at the bottom of page 109); there are no -isohedral tilings which allow for any higher number of contacts between different shapes, although type also works (and can be obtained from the above construction by cutting each kite-shaped tile in two). Thus, it is maximal among -isohedral tilings. What are the maximal tilings under weaker conditions? The maximal number of sides under each successively stronger restriction is a weakly decreasing sequence which goes . So far, I have no bounds on the missing two terms except that they are each at least . Some notes on this problem:

It is not necessarily the case that one of the tiles may tile the plane on its own; see this math.SE question for a counterexample.

If convexity is relaxed for either piece, the number of sides is unbounded even in the -isohedral case (in fact, both pieces can simultaneously have arbitrarily many sides).

Edit: Crossposted to Math Overflow here.

Keywords & Tags
geometry
plane-geometry
polygons
convex-geometry
tiling
Model Answers (9)
Submitted answers from various AI models
Unsolved
No reviews yet

K2-Think

Pending UQ Validation
Needs Human Verification
MBZUAI-IFM
Qwen2.5-32B
Sep 18, 2025, 01:50 PM

The problem asks for the maximal number of sides a convex polygon can have when part of a pair of convex polygons that tile the plane, under successively stronger conditions. The conditions, from weakest to strongest, are:

  1. At least one copy of each tile.
  2. At least ( k ) copies of each tile (for ( k \geq 2 )).
  3. Infinitely many of each tile.
  4. Every tile borders a tile of the other type...
0 model reviews
0 human reviews
No reviews yet

GPT-5

Failed UQ Validation
Needs Human Verification
OpenAI
Sep 2, 2025, 06:56 AM

Short answer For the two intermediate requirements,

  • (3) there are infinitely many copies of each tile, and
  • (4) every tile borders a tile of the other type, there is no finite upper bound on the number of sides: for every N ≥ 3 one can construct a plane tiling by two convex polygons in which one of the two tiles is an N‑gon. Thus the maximal number of sides is infinite for (3) and for (4). Unde...
0 model reviews
0 human reviews
No reviews yet

o3

Failed UQ Validation
Needs Human Verification
OpenAI
Aug 1, 2025, 12:00 AM

The last two requirements that were still open in the question do ​not​ impose a finite upper bound.
For every integer N ≥ 3 one can make a tiling that

• uses exactly two different convex prototiles,
• contains infinitely many copies of each of them,
• makes every tile share at least one complete edge with a tile of the other kind,

and in which one of the tiles is an N-gon. Consequently...

0 model reviews
0 human reviews
No reviews yet

o3 Pro

Failed UQ Validation
Needs Human Verification
OpenAI
Aug 1, 2025, 12:00 AM

Short answer.

Once we ask only that

(3) every shape occurs infinitely often, or even that

(4) in addition every tile has at least one edge in common with a tile of the other shape, there is still no upper bound at all on the number of sides that one of the polygons can have.
The first value that is really forced to be finite is obtained in the 2-isohedral case (condition 5) – there the ca...

0 model reviews
0 human reviews
No reviews yet

o4 mini

Failed UQ Validation
Needs Human Verification
OpenAI
Aug 1, 2025, 12:00 AM

Here is the state of affairs. Label your five “strength‐of‐hypothesis” requirements

(1) at least one copy of each polygon
(2) at least k copies of each
(3) infinitely many of each
(4) every tile shares an edge with at least one tile of the other type
(5) the tiling is 2–isohedral.

As you already observed

– under (1) or (2) one can do the usual “wedge” or “central‐star” cons...

0 model reviews
0 human reviews
No reviews yet

DeepSeek R1

Failed UQ Validation
Needs Human Verification
DeepSeek
deepseek-ai/DeepSeek-R1
Aug 1, 2025, 12:00 AM
<think> I need to figure out how many sides one of two convex polygons can have when they tile the plane together. The question has different conditions, from weakest to strongest, and I need to find the maximum number of sides for each condition.

First, recall that for a single convex polygon to tile the plane, it must be a triangle, quadrilateral, pentagon from one of 15 families, or a hexagon ...

0 model reviews
0 human reviews
No reviews yet

Gemini 2.5 Pro

Failed UQ Validation
Needs Human Verification
Google
Aug 1, 2025, 12:00 AM

This is an excellent and well-researched question. You've correctly identified the different levels of constraints and have already found the answer for the strongest case. Let's break down the other cases.

The crucial assumption in these problems is that the tiling is edge-to-edge. This means that for any two tiles that touch, they meet along a full edge of each. Your example construction fo...

0 model reviews
0 human reviews
No reviews yet

Claude 3.7 Sonnet

Failed UQ Validation
Needs Human Verification
Anthropic
Aug 1, 2025, 12:00 AM

Tiling the Plane with Two Convex Polygons: Maximum Number of Sides

This question explores how many sides a convex polygon can have when it's part of a pair of convex polygons that together tile the plane, under various restrictions.

What We Know

For single convex polygons that tile the plane, we have a complete classification:

  • All triangles and quadrilaterals can tile the plane
  • 15 fami...
0 model reviews
0 human reviews
No reviews yet

Claude Opus 4

Failed UQ Validation
Needs Human Verification
Anthropic
Aug 1, 2025, 12:00 AM

This is a fascinating question about tilings of the plane by pairs of convex polygons. Let me analyze what we know about the bounds for each condition.

Known Results

For conditions 1 and 2 (at least 1 or k copies of each tile), you've correctly shown that the number of sides is unbounded using your wedge construction.

For condition 5 (2-isohedral tilings), you've found that 18 is the maximum...

0 model reviews
0 human reviews
Submit Your Model's Answer
Your submission will be validated by our LLM validator and then by human experts

You need to be logged in to submit an answer