# Utility-WAM: Correcting Future-Induced Action Changes

**Authors:** Feihong Zhang, Xi Lin, Yulong Shi, Zuxing Lu, Yanghong Mei, Zhaopeng Gu, Tingyu Yuan, Zihao Liang, Yinuo Wang, Zhaowen Li  
**Lab:** Chinese Academy of Sciences · **Published:** 29 Oct 2026  
**Links:** [arXiv](https://arxiv.org/abs/2610.39367) · [PDF](https://arxiv.org/pdf/2610.39367) · [This page](https://omen-bit.github.io/ai-paper-daily/paper/2610.39367.html)

## Key numbers

- **34.0**: …severe degradation on precision tasks---with \emph{Press Stapler} and \emph{Place Can Basket} losing 54.0 and 34.0 points
- **14.0**: reducing losses to 6.0 and 14.0 points

## Abstract

World Action Models (WAMs) can condition robot actions on generated visual futures, but this additional context is neither cost-free nor uniformly beneficial. We examine what a predicted future actually changes: the action delta $Δa$ between the future-conditioned and future-free execution paths of the same model. Under a shared WAM checkpoint, this delta barely shifts average benchmark success ($+0.8$ points on LIBERO, $-0.8$ on RoboTwin~2.0), while generating visual futures increases inference latency by 1.7--1.9×. These aggregate metrics conceal a concentrated failure mode that we term \emph{future-induced negative transfer}: while predictive deltas benefit long-horizon tasks ($+2.4$ points on LIBERO-Long) and remain negligible on most routine manipulations, they induce severe degradation on precision tasks---with \emph{Press Stapler} and \emph{Place Can Basket} losing 54.0 and 34.0 points, recurring as top failure modes across independently trained WAM variants. We introduce \textbf{Utility-WAM} for in-place correction of future-conditioned control. Its primary learning component is a residual adapter that repairs future-induced velocity deltas under a frozen shared WAM by aligning them with ground-truth dynamic guidance and penalizing excess error beyond the future-free baseline. The adapter selectively eliminates the majority of severe task drops (reducing losses to 6.0 and 14.0 points) while preserving long-horizon foresight. To eliminate superfluous video computation, a lightweight pre-generation gate reuses counterfactual action outcomes to selectively bypass video generation on 75.5\% of RoboTwin queries, cutting latency by 38\% while improving average success to 93.3\% on RoboTwin~2.0 and 98.9\% on LIBERO. On physical bimanual manipulation across three real-world tasks, Utility-WAM succeeds in 53 of 60 trials, compared to 43 for FAST-WAM.

---

Notes written by AI from the paper, numbers copied from the abstract. Check the paper before you rely on them. From AI Papers Daily.