Search papers, labs, and topics across Lattice.
The paper introduces a novel framework for intelligent AI delegation, addressing limitations in existing methods that rely on static heuristics. This framework enables dynamic adaptation to environmental changes and robust handling of failures by incorporating elements like authority transfer, accountability, and trust establishment. The proposed framework aims to facilitate complex delegation networks involving both AI and human agents, contributing to the development of protocols for the agentic web.
Forget rigid heuristics: this adaptive AI delegation framework dynamically adjusts task allocation, authority transfer, and trust-building, promising more robust agentic systems.
AI agents are able to tackle increasingly complex tasks. To achieve more ambitious goals, AI agents need to be able to meaningfully decompose problems into manageable sub-components, and safely delegate their completion across to other AI agents and humans alike. Yet, existing task decomposition and delegation methods rely on simple heuristics, and are not able to dynamically adapt to environmental changes and robustly handle unexpected failures. Here we propose an adaptive framework for intelligent AI delegation - a sequence of decisions involving task allocation, that also incorporates transfer of authority, responsibility, accountability, clear specifications regarding roles and boundaries, clarity of intent, and mechanisms for establishing trust between the two (or more) parties. The proposed framework is applicable to both human and AI delegators and delegatees in complex delegation networks, aiming to inform the development of protocols in the emerging agentic web.
DeepMind