Abstract
Physical changes or sensing errors can invalidate embodied agents' task-relevant beliefs. AquaMend compares re-probing, rollback, and supported continuation on a probe-belief-action graph under an expected-loss objective covering sensing, physical recovery, and uncorrected failures. A joint posterior guides a one-step policy with conditional detection-power screening. The per-belief three-way optimum requires independence, separability, and fully resolving probes; the general policy has no global optimality guarantee. Across 32 paired scenarios in a self-constructed simulation benchmark, AquaMend recovers in 28/32 cases and reduces mean complete loss by 21.6% versus restart. Its paired loss difference from decision-theoretic troubleshooting (DTT) is not statistically significant after Holm correction. Against the all-candidate ablation, online decision time decreases by 12.3% overall but increases by 3.4% in the uncovered late stage.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Liu, Y., Luo, S., Liu, Y., Jia, H., Han, F., Li, Q., Li, C., Yang, Y., Zhang, C., Zheng, H., Xu, K., & Chong, B. (2026). AquaMend: Minimal Re-probing and Conditional Rollback for Latent-Belief Failures in Embodied Agents. https://omanscience.com/en/articles/aquamend-minimal-re-probing-and-conditional-rollback-for-latent-belief-failures-in-embodied-agents
MLA 9
Liu, Yufan, et al. "AquaMend: Minimal Re-probing and Conditional Rollback for Latent-Belief Failures in Embodied Agents." https://omanscience.com/en/articles/aquamend-minimal-re-probing-and-conditional-rollback-for-latent-belief-failures-in-embodied-agents.
Chicago (author–date)
Liu, Yufan, Shang Luo, Yang Liu, Haoxuan Jia, Feiyu Han, Qian Li, Chen Li, Yingguang Yang, Chongyang Zhang, Hao Zheng, Kefu Xu, and Bin Chong. 2026. "AquaMend: Minimal Re-probing and Conditional Rollback for Latent-Belief Failures in Embodied Agents." https://omanscience.com/en/articles/aquamend-minimal-re-probing-and-conditional-rollback-for-latent-belief-failures-in-embodied-agents.
Harvard
Liu, Y., Luo, S., Liu, Y., Jia, H., Han, F., Li, Q., Li, C., Yang, Y., Zhang, C., Zheng, H., Xu, K. and Chong, B. (2026) 'AquaMend: Minimal Re-probing and Conditional Rollback for Latent-Belief Failures in Embodied Agents', Available at: https://omanscience.com/en/articles/aquamend-minimal-re-probing-and-conditional-rollback-for-latent-belief-failures-in-embodied-agents.
Vancouver
Liu Y, Luo S, Liu Y, Jia H, Han F, Li Q, et al. AquaMend: Minimal Re-probing and Conditional Rollback for Latent-Belief Failures in Embodied Agents. https://omanscience.com/en/articles/aquamend-minimal-re-probing-and-conditional-rollback-for-latent-belief-failures-in-embodied-agents
IEEE
Y. Liu, S. Luo, Y. Liu, H. Jia, F. Han, Q. Li, C. Li, Y. Yang, C. Zhang, H. Zheng, K. Xu, and B. Chong, "AquaMend: Minimal Re-probing and Conditional Rollback for Latent-Belief Failures in Embodied Agents," https://omanscience.com/en/articles/aquamend-minimal-re-probing-and-conditional-rollback-for-latent-belief-failures-in-embodied-agents.