English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Task assignment and scheduling algorithms are powerful tools for autonomouslycoordinating large teams of robotic or AI agents. However, the decisions thesesystem make often rely on components designed by domain experts, which can bedifficult for non-technical end-users to understand or modify to their ownends. In this paper we propose a preliminary design for a flexible naturallanguage interface for a task assignment system. The goal of our approach isboth to grant users more control over a task assignment system's decisionprocess, as well as render these decisions more transparent. Users can directthe task assignment system via natural language commands, which are applied asconstraints to a mixed-integer linear program (MILP) using a large languagemodel (LLM). Additionally, our proposed system can alert users to potentialissues with their commands, and engage them in a corrective dialogue in orderto find a viable solution. We conclude with a description of our planneduser-evaluation in the simulated environment Overcooked and describe next stepstowards developing a flexible and transparent task allocation system.

Towards A Natural Language Interface for Flexible Multi-Agent Task Assignment