One Task, Many Interfaces: Simple Cross-Interface Consistency Training Improves LLM Agent Robustness
Post-training binds the competence of an LLM agent to the interface it was trained on. Semantics-preserving perturbations of that interface, such as renaming an action or changing the notation, leave the underlying task unchanged yet make the agent worse at it. Scoring each sample independently means interface randomization only broadens this dependence from a single interface to the training…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
