Toward an Unbiased Collective Memory for Efficient LLM-Based Agentic 6G Cross-Domain Management

2025-09-30

AI Summary

In 6G RAN-Edge networks, LLM-based agents suffer from cognitive biases—such as primacy, recency, confirmation, and availability biases—leading to inaccurate collective memory retrieval and imbalanced experience learning. Method: This paper proposes a bias-mitigated collective memory-enhanced LLM agent coordination framework, integrating RAN/Edge dual-agent iterative negotiation, digital twin–based closed-loop validation, and a long-context-aware memory repository. It innovatively incorporates semantic retrieval, failure-experience weighting, diversity constraints, and slow-decay temporal weighting to systematically suppress cognitive biases. Contribution/Results: Experiments demonstrate that, compared to memory-less and conventional memory baselines, the framework reduces negotiation rounds by 4.5× and 3.5×, respectively, eliminates SLA violations entirely, and significantly improves latency and energy consumption distributions.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Agreement, Argumentation & Negotiation
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

This paper introduces a novel framework for proactive cross-domain resource orchestration in 6G RAN-Edge networks, featuring large language model (LLM)-augmented agents. The system comprises specialized RAN (energy efficiency) and Edge (latency assurance) agents that engage in iterative negotiation, supported by advanced reasoning and planning capabilities. Agents dynamically interact with a digital twin (DT) to test their proposals and leverage a long-term collective memory where their joint successful and failed agreements along with the related network contexts are distilled into strategies to either follow or avoid and subsequently stored. Given that agents are subject to a plethora of cognitive distortions when retrieving those past experiences -- such as primacy, recency, confirmation and availability biases -- we propose in this work a novel unbiased memory design (A reusable mockup version of the unbiased memory source code is available for non-commercial use at https://github.com/HatimChergui/unbiased-collective-memory). featuring (i) semantic retrieval of past strategies via Jaccard similarity; (ii) learning from failures through amplified weighting of SLA violations and mandatory inclusion of failed negotiation cases to mitigate confirmation bias; (iii) diversity enforcement to minimize availability bias and (iv) recency and primacy weighting with slow decay to counteract temporal biases. Evaluation results showcase the impact of existing biases and how the unbiased memory allows to tackle them by learning from both successful and failed strategies, either present or old, resulting in $ imes 4.5$ and $ imes 3.5$ reductions of unresolved negotiations compared to non-memory and vanilla memory baselines, respectively, while totally mitigating SLA violations as well as improving latency and energy saving distributions.

Problem

• Mitigating cognitive biases in multi-agent collective memory systems
• Enhancing 6G cross-domain resource orchestration through unbiased strategies
• Improving negotiation outcomes by learning from past successes and failures

Innovation

• LLM-augmented agents enable proactive cross-domain resource orchestration
• Digital twin integration tests proposals through dynamic interaction
• Unbiased memory design mitigates cognitive biases via semantic retrieval