In this work, we aim to develop LLM agents to mitigate social norm violations in negotiations in a multi-agent setting. We simulate real-world negotiations by letting two large Language Models (LLMs) play the roles of two negotiators in each conversation. A third LLM acts as a remediation agent to rewrite utterances violating norms for improving negotiation outcomes. As it is a novel task, no manually constructed data is available. To address this limitation, we introduce a value impact based In-Context Learning (ICL) method to identify high-quality ICL examples for the LLM-based remediation agents, where the value impact function measures the quality of negotiation outcomes. We show the connection of this method to policy learning and provide rich empirical evidence to demonstrate its effectiveness in negotiations across three different topics: product sale, housing price, and salary negotiation. The source code and the generated dataset will be publicly available upon acceptance.

AI capabilities are rapidly maturing. More and more industrial products executives are actively determining where and how to leverage AI. But executives are also more discriminating about their organizational priorities for AI and how these leading-edge technologies are rolled out. These CxOs are highly focused on select priority business functions and value drivers for their AI investments. These areas emphasize revenue growth and the customer.

The industrial products industry is awash with data. Instrumentation, sensors, machinery, automation systems, production and operation, maintenance records, and health and safety applications collectively produce a constant flow of data. Industrial products enterprises need technology that supports the vertical delivery of insightful data throughout the organization, both to meet consumer needs and to aim for continuous process improvement. To address operating and market concerns – and deliver on the promise of Industry 4.0 – a small group of financial outperformers is using artificial intelligence (AI)/cognitive to do things differently. Here, they share their AI successes.