Exploring Plan Space through Conversation: An Agentic Framework for LLM-Mediated Explanations in Planning
arXiv:2603.02070v3 Announce Type: replace Abstract: When automating plan generation for a real-world sequential decision problem, the goal is often not to replace the human planner, but to facilitate an iterative reasoning and elicitation process, where the human's role is to guide the AI planner according to their preferences and expertise. In this context, explanations that respond to users' questions are crucial to improve their understanding of potential solutions and increase their trust in the system. To enable natural interaction with such a system, we present a multi-agent Large Langua
The increasing sophistication of LLMs and the growing demand for transparent and human-guided AI systems are enabling new paradigms for Human-AI interaction in complex problem-solving domains.
This development enhances the practical usability and trustworthiness of AI in critical decision-making contexts, moving beyond mere automation to interactive expert augmentation.
The focus shifts from AI acting as an opaque black box to an interactive planning assistant that collaboratively explores solutions and explains its reasoning to human users.
- · AI developers
- · Human planners
- · Industries with complex planning needs
- · AI-driven consulting
- · AI systems lacking interpretability
- · Purely automated decision systems without human oversight
Increased adoption of AI tools in high-stakes planning scenarios due to improved understanding and trust.
Development of new regulatory frameworks emphasizing explainable AI and human-in-the-loop systems across various sectors.
The emergence of 'AI-mediated explainability' as a core design principle for future autonomous systems, standardizing clear communication between humans and machines.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.AI