A central question in life history theory is how individuals allocate resources into maintenance and reproduction to maximize evolutionary fitness [1, 2]. As resources are typically finite, individuals must find a balance between investment in reproduction and maintenance. Allocation of resources into maintenance can be measured only indirectly, but the underlying trade-off causes a negative correlation between reproductive effort and lifespan, which is commonly observed throughout the animal kingdom [3].

Eusocial animals are special because their reproductives are unusually long-lived and highly fertile at the same time [4,5]. Workers have considerable shorter lifespan and forego reproduction [4,6] even though both castes develop from the same genome and live in the same environment [7]. Long queen lifespan has been connected to extrinsic mortality rate [8] or in case of the worker to lower costs due to efficiency gains by the division of labor [6,9].

In social insects selection acts simultaneously on the individual and the colony level [6,10]. Considering an insect colony as a “superorganism” [11], the colony workers are equivalent to the soma [sensu 12], whereas the queen takes the role as the germ line [13]. Investment into workers can therefore be budgeted as maintenance costs, whereas the production of sexual offspring represents investment into reproduction [6]. Hence, insect colonies offer the unique opportunity to directly quantify the life history traits maintenance (in this case equal to colony growth), reproduction, and lifespan, and therefore represent an ideal system to follow the shifting allocation of resources over the lifetime of the colony (e.g. [14]). In addition, it is also possible to measure individual-level trade-offs with reproduction as a direct measure, and lifespan as an indirect measure of maintenance., (e.g., [15,16]).

Here, we study investment into maintenance and reproduction both on the individual and the colony level in the ant Cardiocondyla obscurior. Building on an earlier study with experimentally manipulated colonies [15] we followed the natural growth of experimental colonies until the death of their queen and quantified the number of sexuals and workers produced. To our knowledge, this is the first study on perennial social insects (see [17] for annual bumble bees) with complete data of investment into offspring, as we counted actual brood size and composition, as well as the number of live individuals during the lifespan of a colony in close intervals. For analyses on the individual level we used queen lifetime reproductive effort as a measure of investment into reproduction and queen longevity as an indirect measure of investment into maintenance [6]. On the colony level we used the total number and the biomass of workers produced as a measure of investment into maintenance, and the number and biomass of sexuals (queens and males) as a measure of investment into reproduction.

Furthermore, we compared two distinct populations of C. obscurior (from Brazil and Japan) to study whether traits such as queen longevity and reproductive output are fixed within species. This is of special interest as colonies of the two populations differ in several aspects such as body size and queen/worker ratio [18, this study].

Our comparison of the investment of colonies of Cardiocondyla obscurior into sexuals and workers allows assessing whether a trade-offs exists between maintenance and reproduction on the level of the individual queen and the level of the whole colony. Our data clearly show that maintenance and reproduction are positively correlated on both levels and that—at least under laboratory conditions with food provided ad libitum—a trade-off is not visible. This confirms the results of a similar study on the related species C. kagutsuchi, which, however, did only record the number of workers present at the time of the queen’s death instead of the total number of workers produced [16]. Furthermore, our results also do not substantiate an individual-level trade-off between maintenance and reproduction for individual queens and thus corroborates earlier studies [15,16].

While the absence of a trade-off on the level of the individual queen might be explained by the costs of reproduction being in part borne by the workers, the absence of the trade-off on the colony level is unexpected. Kramer and Schaible [5] hypothesized that trade-offs in insect colonies could be moved to the colony level. Hence, colonies with only a finite amount of resources available face the decision on how to allocate these limited resources between maintenance and reproduction—i.e., the investment into workers or sexuals. Trade-offs are hard to detect if resource levels vary among individuals or, in our case, colonies [28]. The production of new workers by the queen increases colony size as well as the number of individuals that can retrieve resources from the environment [29]. These additional resources can then be utilized by the colony to further increase colony growth or reproduction, setting off a self-reinforcing feedback loop that continually leads to an increase in resources available for the colony while defying the trade-off on the colony level. When resources are provided ad libitum and neither predation nor density-dependent effects exist—as in laboratory conditions—investment in reproduction and maintenance may be positively correlated (Fig 4). For example, similar “benign” conditions have been suggested to explain the absence of a trade-off between reproduction and longevity in zoo animals [30].

Several studies revealed that existing trade-offs may not be detectable by an observer if individuals differ in their capability of resource acquisition (e.g. [31]). In our study, some colonies could not make full use of the surplus resources available despite the ad libitum feeding- regime in the laboratory, probably because their workforce was insufficient. This invariably led to strong heterogeneity among colonies in the level of resources that were available. In addition, variations among queens with respect to egg-laying / resource-level reaction norms might have been exacerbated by the above mentioned positive feedback loop. Consequently, lifespan and reproductive output of queens were extremely variable among colonies, even if queens only differed a little in their ability to utilize continually increasing resources.

In most insect colonies studied so far productivity levels off with increasing colony size [32,33] an effect that we also found in our study (Fig 5). This translates into a decrease in per-capita productivity (Fig 6), also known as ‘Michener’s paradox’ [34,], which is accompanied by a typical decrease in the variance of per-capita productivity with increasing colony size [32,35,36]. It is striking that we found a similar pattern also in our ad libitum fed colonies. The decreasing variance in per-capita productivity hasso far has been understood as being caused by an increasing chance to find and retrieve food items from the environment as forager numbers increase[32]. As the colony continues to grow negative density dependent effects caused by increasing foraging distances, and a higher chance of competition with other conspecific colonies should ultimately lead to a leveling off of colony productivity. However, in our study we find the same pattern in the laboratory without resource limitation [32,36,37]. Hence, colony-level productivity does not seem to be limited by the amount of resources available (which can be ruled out in our study) but rather by worker number, which determines the resources that can be used by the colony. The high variance in productivity at small colony sizes in the absence of resource limitation points to organizational constraints within the workforce of the respective colonies. However, as long as the amount of resources that can be efficiently utilized by the colony increases (despite the above-mentioned diminishing returns with increasing colony size), longer lifespan will be correlated with increased reproductive output. Therefore, the positive relationship of maintenance and reproduction may not only be a result of ad libitum feeding regimes in the laboratory, but may be also found under natural conditions.

To be able to follow the lifespan and egg-laying of individual queens, we had to remove sexual brood. Under natural conditions, sexual offspring would eventually stay in the nest and contribute to offspring production, which would generate potentially immortal colonies, where trade-offs are hard to measure. Under these conditions, the lower productivity of some queens may be compensated by the performance of more productive offspring queens, and it remains to be investigated whether trade-offs on the colony level change when colonies are allowed to form polygynous colonies. In any case, it was striking that all colonies initiated sexual production at a certain time point regardless of colony size. This contrasts with the expectation of an optimal threshold colony size. However, C. obscurior and other species with facultative polygyny, mating in the nest, and the ability to form new colonies by fragmentation (budding) appear to be adapted to unpredictable and disturbed habitats [38]. Thus, as in other r-strategists, there is a strong selective advantage to produce sexual offspring early and independent of worker number, and to quickly increase colony size after a colonization event [39,40]. At least in laboratory colonies of C. obscurior, queen number is much more important for colony growth than worker number, as more queens contribute to a higher egg number [41].

Although egg-laying rate and lifespan were positively correlated in both populations, the strength of the association differed. Hence, the association between these two life history traits appears not to be fixed across populations but seems to be adaptable to specific environmental parameters such as the size and stability of natural nest cavities etc. In the field, colonies nest in in rolled leaves of lemon trees and aborted fruits of coconuts in Brazil (Heinze et al. 2006), while they can be found in bark cavities in coral trees in Japan. Queen number under natural conditions is larger in Japanese colonies (Schrader et al. 2014), but it is unclear whether this is a result of relaxed selection on competitive abilities and a lower egg-laying rate in Japanese queens, or whether a lower egg-laying rate promotes more queens staying together. Japanese queens are larger than Brazilian queens (Schrader et al. 2014), and, generally, lifespan and fecundity seem to be independent of body size in C. obscurior, as confirmed in the intra-population comparisons. This matches observations in some animals, but not in others [42–46].

In both populations, egg-laying rate increased after egg-laying started, but then either remained on a plateau (Japan population) or further increased with age (Brazil population) and decreased sharply short before the queen’s death, regardless of her age (Fig 3). This is different to what has been shown in solitary insects [47,48] or captive mammal and bird species, in which fertility increases for some time after sexual maturity, but then decreases at ages where more than 60% of the initial cohort are still alive [49]. Constant or even increasing fertility over age is rare and can only be found in organisms with infinite growth, such as some species of trees, fish, mollusks, crocodiles, and turtles [50]). Common to all these organisms is a prolonged growth period where large size is associated with higher fitness, such as a reduction in mortality risk at large sizes, or an increase in the capability for acquiring resources. When a C. obscurior colony is treated as a superorganism their life history stunningly resembles that of the above-mentioned organisms with indeterminate growth. Interestingly, the observed decline immediately before death in our study stands in contrast to what has been shown previously [15] and might be attributed to early costs of reproduction, which did not exist in the former study in which colony size was restricted. However, since the decline in egg-laying is immediately followed by the death of the queen, it may also be a sign of physiological senescence as a result of biochemical deterioration of the organism. Future studies under strong resource limitation could show how colonies allocate finite resources into reproduction and maintenance, and whether this causes a similar trade-off in individual queens as well as colonies.