Metraipolis › archive › dc_ef62c08e4cb2
HarnessWAM: Bridging Prediction and Deliberation in World Action Models — arXiv:2608.09516
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.09516
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T09:12:50.210Z
- SHA-256 of the archived text
b5ffe4634ab15f051364b6108a0f51e6f6b6f5264ba4641df1a3c329637663c4- Stable URL of this page
https://metraipolis.com/documento/dc_ef62c08e4cb2
How to cite
HarnessWAM: Bridging Prediction and Deliberation in World Action Models — arXiv:2608.09516 — arXiv (en), https://arxiv.org/abs/2608.09516 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ef62c08e4cb2 (Metraipolis archive dc_ef62c08e4cb2, sha256 b5ffe4634ab15f051364b6108a0f51e6f6b6f5264ba4641df1a3c329637663c4)
BibTeX
@misc{dcef62c08e4cb2,
title = {HarnessWAM: Bridging Prediction and Deliberation in World Action Models — arXiv:2608.09516},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.09516},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ef62c08e4cb2; sha256 b5ffe4634ab15f051364b6108a0f51e6f6b6f5264ba4641df1a3c329637663c4},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.09516. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
World Action Models~(WAMs) jointly learn environmental dynamics and robot actions, introducing priors over physical evolution into embodied control. However, finite-horizon prediction and action generation are insufficient for complex embodied tasks that require global planning, cross-stage state maintenance, execution verification, and failure recovery. We refer to this mismatch as the prediction-deliberation gap. To address this gap, we propose HarnessWAM, an agentic framework for WAMs. HarnessWAM employs a vision-language-model-based Task Manager to maintain an evidence-grounded scene belief and organize the global instruction into a structured task graph. Capability-conditioned executable-space projection then compiles the graph into WAM-supported skill sequences that satisfy task dependencies and embodiment-state constraints. During execution, HarnessWAM couples a lightweight progress estimator with event-triggered Task Manager deliberation. The estimator supplies frequent execution cues, while the Task Manager uses observations, task state, and interaction history to verify outcomes and decide whether to advance, acquire evidence, revise the plan, or recover. Local recovery preserves acquired scene knowledge so that execution can resume after failure. HarnessWAM achieves state-of-the-art average performance on RoboMemArena, with full-task and subtask success rates of 64.4% and 76.8%, respectively, and reaches 23.7% success on RoboCerebra Ideal. On a physical UR3 arm, full-task success reaches 95% for shape-conditioned tabletop tidying and 90% for memory-dependent box exploration. These results demonstrate the effectiveness of model-external agentic orchestration in bridging the prediction-deliberation gap for complex embodied tasks. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-11 in cs.RO). Categorie arXiv: Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2608.09516 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-19T09:11:58.789Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).