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.
SAHG (Sector-Anisotropic Hyperbolic Graph) learns a direction-dependent curvature field $\gamma(u)$ that adapts geometric resolution across structural directions, and uses sector prototypes to convert angular concentration and alignment into classifier-readable features.
Han-Ning Lu, Ying-Guang Yang, Jinwei Su et al.· arXiv.org· 1 citation
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
It is argued that the right resolution is state-dependent, and GACA, a critic-free estimator whose granularity follows an uncertainty-based criticality proxy is proposed, improves task success over GRPO and GiGPO at both 1.5B and 7B scales.
Tao Liang, Yang Liu, Shang Luo et al.· 3 citations
This work introduces HackProbe, a monitor that attaches to an arbitrary self-evolving loop through two black-box hooks, with no access to weights or activations, and proves a detectability bound that converts a target error rate into an explicit probe-size budget, and delimit what probe rotation does and does not buy.
Rong-Xin Yang, Yang Liu, Shang Luo et al.· 2 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
LoopHarness is presented, which restores a persistent, non-decaying safety state at the loop level at the loop level, and gives a complete evaluation protocol on native Agent-SafetyBench tasks with paired clean and attacked episodes, an outer-state attack suite whose decisive evidence exists only across iterations, per...
Chenmin Wu, H. Jia, Yang Liu 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.