Action Conditioned Bisimulation For GUI Agent Memory

The paper introduces an action‑conditioned bisimulation rule for merging states in a GUI agent’s memory, replacing observation‑based similarity with a requirement that shared actions produce identical outcomes and successor blocks. This rule is applied to the empirical predictive state graph built by a frozen agent during interaction. Experiments on MiniWoB++ show that the new merge rule improves success rates compared to a memoryless baseline, while controls that omit action conditioning or use the previous successor‑representation merge show no improvement.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• agents