Varied Magnitude Favor Exchange in Human-Agent Negotiation

Abstract

Agents that interact with humans in complex, social tasks need the ability to comprehend as well as employ common social strategies. In negotiation, there is ample evidence of such techniques being used efficaciously in human interchanges. In this work, we demonstrate a new design for socially aware agents that employ one such technique-favor exchange-in order to gain value when playing against humans. In an online study of a robust, simulated social negotiation task, we show that these agents are effective against real human participants. In particular, we show that agents that ask for favors during the course of a repeated set of negotiations are more successful than those that do not. Additionally, previous work has demonstrated that humans can detect when agents betray them by failing to return favors that were previously promised. By contrast, this work indicates that these betrayal techniques may go largely undetected in complex scenarios.

Customizing virtual interpersonal skills training applications may not improve trainee performance

“…Participants interacted with one of the IAGO agents (from 45 ) that are provided with the platform itself. The agent is fundamentally dynamic and adaptive in its design.…”

“…This agent looks for a moderately-sized positive margin over the user. However, adverse events (such as offer rejections) will reduce this margin over time (details can be found in 45 ). Based on this policy, the agent decides if it wants to accept, reject, or ignore the offer, as well as what it should say (e.g.…”

“…"Yes, that offer sounds good to me!" or show an emoji; see 45 , for how these policies are crafted).…”

“…Participants then interacted the IAGO agent above 45 . Upon completion of the negotiation, participants were then thanked and granted credit for their participation in the academy's online research credit tracking system.…”

The Case for Negotiation Robots in simulated workplace negotiations A Theoretical Approach

“…These AI negotiations aim to simulate authentic interactions between humans in the workplace. Negotiation frameworks like IAGO (Mell & Gratch, 2017). simulate negotiations using a menu-based interface between a human participant and a virtual agent (Figure 1).…”