Memory Centric Power Allocation for Multi-Agent Embodied Question Answering

2026-04-20

AI Summary

This work addresses the neglect of long-term perceptual memory quality in existing edge resource management approaches for multi-agent embodied question answering. To this end, it introduces memory quality (QoM) as a primary optimization objective and proposes a novel QoM evaluation mechanism based on Generative Adversarial Examination (GAE), which quantifies memory retrieval capability through forward simulation. Furthermore, a memory-centric power allocation (MCPA) strategy is designed to maximize QoM under communication resource constraints. Theoretical analysis reveals a proportional relationship between transmit power and GAE error probability. Experimental results demonstrate that the proposed method significantly outperforms existing baselines across diverse scenarios, achieving notable improvements in key performance metrics.

Technology Category

• Multiagent Systems: Mechanism Design
• Search and Optimization: Sampling/Simulation-based Search
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

This paper considers multi-agent embodied question answering (MA-EQA), which aims to query robot teams on what they have seen over a long horizon. In contrast to existing edge resource management methods that emphasize sensing, communication, or computation performance metrics, MA-EQA emphasizes the memory qualities. To cope with this paradigm shift, we propose a quality of memory (QoM) model based on generative adversarial exam (GAE), which leverages forward simulation to assess memory retrieval and uses the resulting exam scores to compute QoM values. Then we propose memory centric power allocation (MCPA), which maximizes the QoM function under communication resource constraints. Through asymptotic analysis, it is found that the transmit powers are proportional to the GAE error probability, thus prioritizing towards high-QoM robots. Extensive experiments demonstrate that MCPA achieves significant improvements over extensive benchmarks in terms of diverse metrics in various scenarios.

Problem

• multi-agent embodied question answering
• memory quality
• power allocation
• resource constraints
• memory-centric

Innovation

• Quality of Memory (QoM)
• Generative Adversarial Exam (GAE)
• Memory-Centric Power Allocation (MCPA)
• Multi-Agent Embodied Question Answering
• Forward Simulation