Insert-expansions for Tool-enabled Conversational Agents
This addresses a specific interaction problem for developers of conversational AI agents, though it appears incremental in scope.
The paper tackles the problem of tool-enabled conversational agents getting sidetracked by additional context from tools, which diverts from user intents. It explores a 'user-as-a-tool' approach where users provide details to refine requests, finding benefits in the recommendation domain through empirical studies.
This paper delves into an advanced implementation of Chain-of-Thought-Prompting in Large Language Models, focusing on the use of tools (or "plug-ins") within the explicit reasoning paths generated by this prompting method. We find that tool-enabled conversational agents often become sidetracked, as additional context from tools like search engines or calculators diverts from original user intents. To address this, we explore a concept wherein the user becomes the tool, providing necessary details and refining their requests. Through Conversation Analysis, we characterize this interaction as insert-expansion - an intermediary conversation designed to facilitate the preferred response. We explore possibilities arising from this 'user-as-a-tool' approach in two empirical studies using direct comparison, and find benefits in the recommendation domain.