We should distinguish two types of plasticity here: flexibility in forming representations, and flexibility in acting on them. The former involves using multiple cues to identify properties in the world. We can identify an object not only by how it looks, but also how it smells, sounds, and so forth. There can even be multiple cues within a single sensory modality: if I see a realistic-looking plastic fish, but also see that my cat has no interest in it, then this latter (still visual!) cue might lead me to doubt whether it really was a fish. To adopt Sterelny's terminology, "robust tracking" occurs when internal representations are sensitive to a wide range of diverse stimuli. The benefits of robust tracking are clear: it helps us to identify properties more reliably and thus form more accurate representations (true beliefs).
In addition to robust tracking, another form of plasticity is found in the breadth of responses open to an organism once an identification has occurred. I might have a million different ways of spotting danger, but one would question my cognitive capabilities if all I ever did in response was to run away as fast as I could. More flexible (=intelligent) organisms can tailor their responses to fit the specifics of the situation. They might flee, hide, prepare to fight, or call for help, etc. They are not bound by the "tyranny of the stimulus", unlike the infamous Sphex wasp:
When the time comes for egg laying, the wasp Sphex builds a burrow for the purpose and seeks out a cricket which she stings in such a way as to paralyze but not kill it. She drags the cricket into the burrow, lays her eggs alongside, closes the burrow, then flies away, never to return. In due course, the eggs hatch and the wasp grubs feed off the paralyzed cricket, which has not decayed, having been kept in the wasp equivalent of deep freeze. To the human mind, such an elaborately organized and seemingly purposeful routine conveys a convincing flavor of logic and thoughtfulness -- until more details are examined. For example, the Wasp's routine is to bring the paralyzed cricket to the burrow, leave it on the threshold, go inside to see that all is well, emerge, and then drag the cricket in. If the cricket is moved a few inches away while the wasp is inside making her preliminary inspection, the wasp, on emerging from the burrow, will bring the cricket back to the threshold, but not inside, and will then repeat the preparatory procedure of entering the burrow to see that everything is all right. If again the cricket is removed a few inchies while the wasp is inside, once again she will move the cricket up to the threshold and re-enter the burrow for a final check. The wasp never thinks of pulling the cricket straight in. On one occasion this procedure was repeated forty times, always with the same result. (Woodridge, 1963, p. 82)
Response breadth thus reflects versatility in action, whereas robust tracking reflects versatility in perception (broadly understood). So far as I can tell, these two types of 'intelligence' are completely independent of each other (at least conceptually; there could be some overlap in their implementation - best ask a psychologist). It reminds me of the distinction between theoretical and practical rationality (i.e. beliefs vs. actions), though I'm not sure exactly how strong the analogy is.
Next up: what, if anything, the two types of plasticity can tell us about the intentional content of a representation...