Preprint · 2026

Beyond pass@1: A Reliability Science Framework for Long-Horizon LLM Agents

Aaditya Khanal, Yangyang Tao, Junxiu Zhou

VenuearXiv
URLhttps://arxiv.org/abs/2603.29231
TopicsReplicHAI / Agent & LLM run-to-run variability
Tagsreplichai
archiveIDarXiv:2603.29231
citationKeykhanal2026beyondpass
libraryCatalogbackground/bib/bib-q1q2.bib

BibTeX

@misc{khanal2026beyondpass,
	title = {Beyond pass@1: {A} {Reliability} {Science} {Framework} for {Long}-{Horizon} {LLM} {Agents}},
	url = {https://arxiv.org/abs/2603.29231},
	publisher = {arXiv},
	author = {Khanal, Aaditya and Tao, Yangyang and Zhou, Junxiu},
	year = {2026},
	keywords = {replichai},
}