Zero-Shot Coordination in Text Optimisation: Do Independently Optimised Agents Work Together?

Text optimisation improves an agent by letting a language model repeatedly rewrite text artefacts, such as policy code, action tables, or instructions, against a score. These methods are judged almost entirely by that score. In cooperative tasks this hides a problem known from multi-agent reinforcement learning as zero-shot coordination: agents optimised separately may each perform well, yet fail when paired, because every run settles on its own conventions. We study zero-shot coordination in text optimisation. We run independent optimisation processes across language models and optimisation methods, and pair the resulting agents with partners they never met. A small, exactly solvable signalling game reveals the conventions each run adopts, and a cooperative cooking game tests the same question in a larger domain. We find that optimisation replaces shared focal points with conventions tied to each run's presentation of the task. Scoring candidates against independent samples of the unoptimised model preserves compatibility when those samples agree, and rejecting proposals that are not invariant under the game's symmetries preserves it when they disagree. We argue that partner generalisation should be reported alongside the score.