Across benchmarks, transferred and target-derived playbooks both require target-side validation of success, termination, protocol compatibility, and cost, and Frozen transfer is therefore a conditional cold-start option, not a reuse-by-default strategy or a universally preferable alternative to target-side redistillati...
Wei-Hong Lin, Lin Sun, Xiangzheng Zhang· 0 citations
This work presents SkillSentry, a dynamic safety-testing framework based on adaptive honey worlds, which infers the intended capability boundary of a skill, constructs an LLM-simulated environment with controlled decoy resources, and adaptively generates tasks to explore its behavioral states.
Nizhang Li, Zong-Hao Ying, Xiang-Fan Wu et al.· 0 citations
This work introduces ArborMem, an online memory framework that represents a long-running conversation as a navigable forest of interaction states that outperforms the strongest baselines on three established benchmarks and introduces BranchMemEval, a controlled diagnostic benchmark for interleaved and resumable interac...
Zongwei Lv, Yue-Meng Xu, Yilun Yao et al.· 0 citations
SafeFlow is proposed, a defense framework for multi-agent systems that formalizes malicious cross-agent propagation as a semantic information-flow problem and reduces attack success rates compared to undefended baselines and external defenses while retaining high benign task completion and a high paired safe--harm succ...
Haowen Dai, Zonghao Ying, Wenfeng Li et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
