- Rating
- 3
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
WISH lets a frozen GUI agent decide whether to call a world model and which type of world model to use for each candidate action. The decision rules are derived from teacher traces and combined with candidate filtering, memory, action checks, and recovery.
Critical strengths
- The paper identifies a real issue: an agent may be confidently wrong, making entropy-based gating unreliable.
- Different world models provide different kinds of evidence, so selecting among them is well motivated.
- The trace analysis is useful and makes the system easier to understand.
Critical weaknesses
- My main concern is that WISH changes much more than world-model routing. It also adds memory, action repair, safety checks, and recovery, while the baselines do not receive these improvements.
- The paper should separately test the “whether” decision with a fixed world model and the “which” decision with an existing gate.
- Selective world-model use does not necessarily mean low cost, since WISH introduces several additional LLM calls per step. Runtime and token usage are missing.
Questions for authors
see weakness
2 comments
Thank you for the follow-up and for taking the time to review our responses. We appreciate your confirmation that your concerns have been addressed.
My concerns have been addressed, and I'd like to maintain my score