# Learning to Report Unsafe Tasks in a Multi-Agent Game

> Полный текст доступен на английском

**Published:** 8 октября 2026 г.
**Author:** Avyay M. Casheekar, Hariganesh Tangirala
**Source:** arXiv — cs.AI
**Language:** en-US
**HTML:** https://aiqazaqstan.com/ru/articles/learning-to-report-unsafe-tasks-in-a-multi-agent-game

When agents share a reward for completed tasks, reporting unsafe work can reduce the reporter's reward by stopping a task. Audits can make reporting optimal without ensuring that further training teaches a silent team to report. We study this learning problem in a game where any…

> Материал агрегирован из первоисточника: **arXiv — cs.AI**
> [Читать полностью в arXiv — cs.AI](https://arxiv.org/abs/2610.09002)

**Теги:** #arXiv

---

*AI Qazaqstan — non-commercial informational portal about AI in Kazakhstan. Machine translations and summaries are AI-generated.*