HINTBench: Horizon-agent Intrinsic Non-attack Trajectory Benchmark
arXiv:2604.13954v2 Announce Type: replace-cross Abstract: Existing agent-safety evaluation has focused mainly on externally induced risks. Yet agents may still enter unsafe trajectories under benign conditions. We study this complementary but…
Read the full story at arXiv cs.AI ↗
ImpactNotable 45/100
Why it mattersRule-based estimate: event keywords (+18); trust 6/10.
RegionsGlobal
Published3 d ago (Thu, 17 Sep 2026 04:00:00 GMT)
RetrievedThu, 17 Sep 2026 15:30:40 GMT via rss
ClassifiedThu, 17 Sep 2026 15:30:51 GMT by heuristic
AuthorJiacheng Wang, Jinchang Hou, Fabian Wang, Ping Jian, Chenfu Bao, Zhonghou Lv