Feedback That Backfires in Games: Do LLM Players Repeat the Move They Just Watched Fail?
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...
Read more: https://arxiv.org/abs/2610.30205
Scan with your phone
Scan with your phone