Results from my AI negotiation harness
I built an agent harness where two LLMs (one seller, one buyer) bargain for an indivisible good, with alternating offers. Both have private valuations and discounting rates. Cheap talk is allowed; private reasoning never crosses between agents. The harness code is available in https://github.com/CarlosGIbanez/negotiation-harness The result's data from the experiment...
Sep 61