R-HTN: Rebellious Online HTN Planning for Safety and Game AI

2026-02-01

AI Summary

This work proposes a novel hierarchical task network (HTN) planning framework endowed with “intelligent disobedience” capabilities to address the risk of agents violating safety or personalization constraints while executing user-specified tasks. By embedding a set of behavioral norms \( D \) into the online HTN planning process, the authors design the R-HTN algorithm, enabling agents to either halt execution (Nonadaptive mode) or proactively replan to achieve their goals in a compliant manner (Adaptive mode) when norm conflicts arise. This study represents the first integration of intelligent disobedience mechanisms into HTN-based planning. Empirical evaluation across two task domains demonstrates that R-HTN agents consistently adhere to prescribed norms and successfully accomplish tasks whenever feasible, even when their resulting execution paths diverge from the user’s original expectations.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Multiagent Systems: Multiagent Planning
• Planning, Routing, and Scheduling: Replanning and Plan Repair

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

We introduce online Hierarchical Task Network (HTN) agents whose behaviors are governed by a set of built-in directives \D. Like other agents that are capable of rebellion (i.e., {\it intelligent disobedience}), our agents will, under some conditions, not perform a user-assigned task and instead act in ways that do not meet a user's expectations. Our work combines three concepts: HTN planning, online planning, and the directives \D, which must be considered when performing user-assigned tasks. We investigate two agent variants: (1) a Nonadaptive agent that stops execution if it finds itself in violation of \D~ and (2) an Adaptive agent that, in the same situation, instead modifies its HTN plan to search for alternative ways to achieve its given task. We present R-HTN (for: Rebellious-HTN), a general algorithm for online HTN planning under directives \D. We evaluate R-HTN in two task domains where the agent must not violate some directives for safety reasons or as dictated by their personality traits. We found that R-HTN agents never violate directives, and aim to achieve the user-given goals if feasible though not necessarily as the user expected.

Problem

• Hierarchical Task Network
• Online Planning
• Intelligent Disobedience
• Safety Constraints
• Directive Compliance

Innovation

• Rebellious HTN
• Online planning
• Intelligent disobedience
• Hierarchical Task Network
• Directive-based reasoning