# Feedback That Backfires in Games: Do LLM Players Repeat the Move They Just Watched Fail?

**Published:** October 23, 2026
**Author:** Esmail Gumaan
**Source:** arXiv — cs.AI
**Language:** en-US
**HTML:** https://aiqazaqstan.com/en/articles/feedback-that-backfires-in-games-do-llm-players-repeat-the-move-they-jus

arXiv:2610.30205v1 Announce Type: new Abstract: When an LLM agent's move fails, the harness writes the move and the failure message into the transcript and asks again. In tool calling, this record makes small models more likely to repeat the failed action. We test whether the…

> From the original source: **arXiv — cs.AI**
> [Read full article at arXiv — cs.AI](https://arxiv.org/abs/2610.30205)

**Tags:** #arXiv #GPU & Суперкомпьютеры

---

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