This work tests an assumption that whether an agent follows an injection is settled when the injection is read, and shows that the decision forms gradually as the agent reasons, which lowers the attack success rate of Qwen3 but raises it for two other models.
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, and its paired loss difference from decision-theoretic troubleshooting (DTT) is not statistically significant after Holm correction.
Yu-Fan Liu, Shang Luo, Yang Liu et al.· 0 citations
Hindsight Memory-PRM exploits this audit trail twice: offline to train an operation-conditioned memory-utility critic, and online, where retrievals, citations, and one controlled deletion-and-reanswer per probe settle an intervention-calibrated entry-level presence credit.
H. Jia, Yang Liu, Ying-Guang Yang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.