arXiv subjects

Farhad Rezazadeh

Publications and source records attributed to Farhad Rezazadeh.

At least 19 recordsLinked to original sources

arXiv2026

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

Agentic artificial intelligence is a candidate enabler of Level-4 autonomy in sixth-generation (6G) networks, but agents reasoning over a shared memory inherit its distortions. We study cross-domain radio access network (RAN)--edge orchestration in which a RAN agent minimizing energy and an edge agent minimizing latency negotiate, validate proposals against a digital twin (DT), and share a collective memory. Such a memory is a sampling device: what agents retrieve, not what they store, determines what they do. We define the Retrieval Bias Index, a divergence between the induced retrieval law and a representative reference, decomposed along temporal, confirmation and availability axes, and show that additive retrieval scoring is an exponential tilt of the undebiased law, yielding a closed form for the failure-amplification weight and a saturation floor set by the store's own composition; a further result bounds excess service level agreement (SLA) violation additively in retrieval bias and DT mismatch. On a tandem queue for which stochastic network calculus supplies a feasible region, an oracle and a Nash bargaining reference, the operator attains a $12.7\times$ bias reduction over a recency store and the smallest distance to the bargaining solution among six memory architectures.

cs.NI↗

arXiv2026

Mitigating Anchoring Bias in LLM-Based Agents for Energy-Efficient 6G Autonomous Networks

This paper presents an autonomous agentic resource negotiation framework designed to enable zero-touch network slicing in 6G architectures using Large Language Model (LLM) agents. While LLMs offer powerful reasoning capabilities, we demonstrate that such agents inherently suffer from anchoring bias, rigidly adhering to initial heuristic proposals and causing severe network over-provisioning. To systematically mitigate this cognitive bias, we propose a novel randomized anchoring strategy modeled via a Truncated 3-Parameter Weibull distribution. This mathematically bounded approach seamlessly integrates with burst-aware Digital Twins (DTs) employing Conditional Value at Risk (CVaR) to rigorously guarantee strict Service Level Agreement (SLA) tail-latencies. To validate our methodology, we introduce and prove the \emph{Bimodal Constraint-Avoidance Utility Theorem}, demonstrating that while feasible negotiations follow classical convex bounds, highly constrained scenarios undergo a phase transition governed by an inverse rational decay envelope. Empirical results generated using a locally hosted 1B-parameter model otel-llm-1b-it confirm these dual-regime bounds. Our cognitive de-biasing successfully dismantles rigid negotiation patterns, forcing agents into active exploration to safely ride SLA boundaries and boost system energy savings up to 25\%. Crucially, the lightweight 1B LLM achieves sub-second inference latencies (0.95s mean), ensuring our multi-agent framework is compatible with the operational timescales of the O-RAN non-Real-Time RAN Intelligent Controller (non-RT RIC)\footnote{Our source code is available for non-commercial use at https://github.com/HatimChergui.

cs.NI↗

arXiv2026

Rivaling Transformers: Multi-Scale Structured State-Space Mixtures for Agentic 6G O-RAN

In sixth-generation (6G) Open Radio Access Networks (O-RAN), proactive control is preferable. A key open challenge is delivering control-grade predictions within Near-Real-Time (Near-RT) latency and computational constraints under multi-timescale dynamics. We therefore cast RAN Intelligent Controller (RIC) analytics as an agentic perceive-predict xApp that turns noisy, multivariate RAN telemetry into short-horizon per-User Equipment (UE) key performance indicator (KPI) forecasts to drive anticipatory control. In this regard, Transformers are powerful for sequence learning and time-series forecasting, but they are memory-intensive, which limits Near-RT RIC use. Therefore, we need models that maintain accuracy while reducing latency and data movement. To this end, we propose a lightweight Multi-Scale Structured State-Space Mixtures (MS3M) forecaster that mixes HiPPO-LegS kernels to capture multi-timescale radio dynamics. We develop stable discrete state-space models (SSMs) via bilinear (Tustin) discretization and apply their causal impulse responses as per-feature depthwise convolutions. Squeeze-and-Excitation gating dynamically reweights KPI channels as conditions change, and a compact gated channel-mixing layer models cross-feature nonlinearities without Transformer-level cost. The model is KPI-agnostic -- Reference Signal Received Power (RSRP) serves as a canonical use case -- and is trained on sliding windows to predict the immediate next step. Empirical evaluations conducted using our bespoke O-RAN testbed KPI time-series dataset (59,441 windows across 13 KPIs). Crucially for O-RAN constraints, MS3M achieves a 0.057 s per-inference latency with 0.70M parameters, yielding 3-10x lower latency than the Transformer baselines evaluated on the same hardware, while maintaining competitive accuracy.

cs.NI↗

arXiv2026

Agentic World Modeling for 6G: Near-Real-Time Generative State-Space Reasoning

We argue that sixth-generation (6G) intelligence is not fluent token prediction but the capacity to imagine and choose -- to simulate future scenarios, weigh trade-offs, and act with calibrated uncertainty. We reframe open radio access network (O-RAN) near-real-time (Near-RT) control via counterfactual dynamics and a world modeling (WM) paradigm that learns an action-conditioned generative state space. This enables quantitative "what-if" forecasting beyond large language models (LLMs) as the primary modeling primitive. Actions such as physical resource blocks (PRBs) are treated as first-class control inputs in a causal world model, and both aleatoric and epistemic uncertainty are modeled for prediction and what-if analysis. An agentic, model predictive control (MPC)-based cross-entropy method (CEM) planner operates over short horizons, using prior-mean rollouts within data-driven PRB bounds to maximize a deterministic reward. The model couples multi-scale structured state-space mixtures (MS3M) with a compact stochastic latent to form WM-MS3M, summarizing key performance indicators (KPIs) histories and predicting next-step KPIs under hypothetical PRB sequences. On realistic O-RAN traces, WM-MS3M cuts mean absolute error (MAE) by 1.69% versus MS3M with 32% fewer parameters and similar latency, and achieves 35-80% lower root mean squared error (RMSE) than attention/hybrid baselines with 2.3-4.1x faster inference, enabling rare-event simulation and offline policy screening.

cs.NI↗

arXiv2026

LiQSS: Post-Transformer Linear Quantum-Inspired State-Space Tensor Networks for Real-Time 6G

Proactive and agentic control in Sixth-Generation (6G) Open Radio Access Networks (O-RAN) requires control-grade prediction under stringent Near-Real-Time (Near-RT) latency and computational constraints. While Transformer-based models are effective for sequence modeling, their quadratic complexity limits scalability in Near-RT RAN Intelligent Controller (RIC) analytics. This paper investigates a post-Transformer design paradigm for efficient radio telemetry forecasting. We propose a quantum-inspired many-body state-space tensor network that replaces self-attention with stable structured state-space dynamics kernels, enabling linear-time sequence modeling. Tensor-network factorizations in the form of Tensor Train (TT) / Matrix Product State (MPS) representations are employed to reduce parameterization and data movement in both input projections and prediction heads, while lightweight channel gating and mixing layers capture non-stationary cross-Key Performance Indicator (KPI) dependencies. The proposed model is instantiated as an agentic perceive-predict xApp and evaluated on a bespoke O-RAN KPI time-series dataset comprising 59,441 sliding windows across 13 KPIs, using Reference Signal Received Power (RSRP) forecasting as a representative use case. Our proposed Linear Quantum-Inspired State-Space (LiQSS) model is 10.8x-15.8x smaller and approximately 1.4x faster than prior structured state-space baselines. Relative to Transformer-based models, LiQSS achieves up to a 155x reduction in parameter count and up to 2.74x faster inference, without sacrificing forecasting accuracy.

cs.NI↗

arXiv2026

A Tutorial on Cognitive Biases in Agentic AI-Driven 6G Autonomous Networks

The path to higher network autonomy in 6G lies beyond the mere optimization of key performance indicators (KPIs), requiring systems that perceive and reason over the network environment as it is. This can be achieved through agentic AI, where large language model (LLM)-powered agents utilize multimodal telemetry, memory, and cross-domain negotiation to achieve multi-objective goals. However, deploying such agents introduces cognitive biases inherited from human design, which can severely distort reasoning and actuation. This paper provides a comprehensive tutorial on well-known cognitive biases, detailing their taxonomy, mathematical formulation, emergence in telecom systems, and tailored mitigation strategies. We validate these concepts through two distinct use-cases in 6G management. First, we tackle anchoring bias in inter-slice resource negotiation. To overcome the prohibitive execution delays of cloud-based LLMs, this use-case deploys a locally hosted 1B-parameter model on an RTX A4000 GPU, successfully achieving sub-second inference latencies compatible with near-real-time operations. By replacing fixed heuristic anchors with a Truncated Weibull randomized anchor strategy, the agents dismantle rigid biases, intelligently consume SLA slack, and dynamically double the system-wide energy savings (peaking at 25\%) without violating strict latency limits. Second, we mitigate temporal and confirmation biases in RAN-Edge cross-domain negotiation by designing an unbiased collective memory. By integrating semantic/temporal decay and an inflection bonus that actively highlights past negotiation failures, agents are prevented from over-relying on recent data or repeating past mistakes. Grounding decisions in this richer, debiased historical context yields highly robust agreements, achieving a $\times 5$ latency reduction and roughly 40\% higher energy savings compared to memoryless baselines.

cs.NI↗

arXiv2026

LLM-Based Agentic Negotiation for 6G: Addressing Uncertainty Neglect and Tail-Event Risk

A critical barrier to the trustworthiness of sixth-generation (6G) agentic autonomous networks is the uncertainty neglect bias; a cognitive tendency for large language model (LLM)-powered agents to make high-stakes decisions based on simple averages while ignoring the tail risk of extreme events. This paper proposes an unbiased, risk-aware framework for agentic negotiation, designed to ensure robust resource allocation in 6G network slicing. Specifically, agents leverage Digital Twins (DTs) to predict full latency distributions, which are then evaluated using a formal framework from extreme value theory, namely, Conditional Value-at-Risk (CVaR). This approach fundamentally shifts the agent's objective from reasoning over the mean to reasoning over the tail, thereby building a statistically-grounded buffer against worst-case outcomes. Furthermore, our framework ensures full uncertainty awareness by requiring agents to quantify epistemic uncertainty -- confidence in their own DTs predictions -- and propagate this meta-verification to make robust decisions, preventing them from acting on unreliable data. We validate this framework in a 6G inter-slice negotiation use-case between an eMBB and a URLLC agent across 200 trials. The results demonstrate the profound failure of the biased, mean-based baseline, which systematically violates the strict URLLC SLA 11 times. Our unbiased, CVaR-aware agent successfully mitigates this bias, eliminating SLA violations entirely and significantly reducing the 99.999th-percentile latencies by up to 51.7\%. We show this reliability comes at the rational and quantifiable cost of reduced energy savings, exposing the false economy of the biased approach. Crucially, executing our framework with an otel-llm-1b-it model on a single NVIDIA RTX A4000 GPU achieves sub-1.5-second inference times, validating the feasibility for non-real-time RIC use-cases.

cs.NI↗

arXiv2026

Learning Low-Dimensional Representation for O-RAN Testing via Transformer-ESN

Open Radio Access Network (O-RAN) architectures enhance flexibility for 6G and NextG networks. However, it also brings significant challenges in O-RAN testing with evaluating abundant, high-dimensional key performance indicators (KPIs). In this paper, we introduce a novel two-stage framework to learn temporally-aware low-dimensional representations of O-RAN testing KPIs. To be specific, stage one employs an information-theoretic H-score to train a hybrid self-attentive transformer and echo state network (ESN) reservoir, called Transformer-ESN, capturing temporal dynamics and producing task-aligned $8$-dimensional embeddings. Stage two evaluates these embeddings by training a lightweight multilayer perceptron (MLP) predictor exclusively on them for key target KPIs such as reference signal received quality (RSRQ) and spectral efficiency. Using real-world O-RAN testbed data (video streaming with interference), our approach demonstrates a significant advantage specifically when training samples are very limited. In this scenario, the low-dimensional representations learned from the Transformer-ESN yield mean square error (MSE) reductions of up to 41.9\% for RSRQ and 29.9\% for spectral efficiency compared to predictions from the original high-dimensional data. The framework exhibits high efficiency for O-RAN testing, significantly reducing testing complexities for O-RAN systems.

eess.SP↗

arXiv2025

Digital Co-Founders: Transforming Imagination into Viable Solo Business via Agentic AI

This paper investigates how individual entrepreneurs can turn creative ideas into successful solo businesses in an era increasingly shaped by Artificial Intelligence (AI) agents. It highlights the key steps that connect personal vision, structured experimentation, and lasting value creation, and shows how AI agents can act as digital co-founders throughout this journey. Building on research in entrepreneurship, creativity, and innovation, we present a framework with three key stages: (1) Imagination shaping, where vague goals become clear value propositions, supported by AI agents that help with market scanning, idea refinement, and rapid concept generation; (2) Reality testing, where these ideas are tested through low-cost experiments, structured feedback loops, and efficient execution, with AI agents automating tasks such as prototyping, content creation, customer interaction, and data analysis; and (3) Reality scaling, where successful ideas are transformed into repeatable processes, scalable market strategies, and long-term business models, increasingly operated and optimized by autonomous or semi-autonomous AI workflows. We focus on the specific context of solopreneurship, characterized by limited human resources, complete accountability for decision-making, and a strong association between the founder's identity and the business. The framework clearly identifies key enabling factors such as mental adaptability, effective planning, and successful human-AI collaboration within digital ecosystems. It also thoughtfully addresses ongoing challenges, like uncertainty and cognitive overload, which are heightened by our constant connectivity.

cs.NI↗

arXiv2025

An Experimental Reservoir-Augmented Foundation Model: 6G O-RAN Case Study

Next-generation open radio access networks (O-RAN) continuously stream tens of key performance indicators (KPIs) together with raw in-phase/quadrature (IQ) samples, yielding ultra-high-dimensional, non-stationary time series that overwhelm conventional transformer architectures. We introduce a reservoir-augmented masked autoencoding transformer (RA-MAT). This time series foundation model employs echo state network (ESN) computing with masked autoencoding to satisfy the stringent latency, energy efficiency, and scalability requirements of 6G O-RAN testing. A fixed, randomly initialized ESN rapidly projects each temporal patch into a rich dynamical embedding without backpropagation through time, converting the quadratic self-attention bottleneck into a lightweight linear operation. These embeddings drive a patch-wise masked autoencoder that reconstructs 30% randomly masked patches, compelling the encoder to capture both local dynamics and long-range structure from unlabeled data. After self-supervised pre-training, RA-MAT is fine-tuned with a shallow task head while keeping the reservoir and most transformer layers frozen, enabling low-footprint adaptation to diverse downstream tasks such as O-RAN KPI forecasting. In a comprehensive O-RAN KPI case study, RA-MAT achieved sub-0.06 mean squared error (MSE) on several continuous and discrete KPIs. This work positions RA-MAT as a practical pathway toward real-time, foundation-level analytics in future 6G networks.

cs.NI↗

arXiv2025

Toward Generative 6G Simulation: An Experimental Multi-Agent LLM and ns-3 Integration

The move toward open Sixth-Generation (6G) networks necessitates a novel approach to full-stack simulation environments for evaluating complex technology developments before prototyping and real-world implementation. This paper introduces an innovative approach\footnote{A lightweight, mock version of the code is available on GitHub at that combines a multi-agent framework with the Network Simulator 3 (ns-3) to automate and optimize the generation, debugging, execution, and analysis of complex 5G network scenarios. Our framework orchestrates a suite of specialized agents -- namely, the Simulation Generation Agent, Test Designer Agent, Test Executor Agent, and Result Interpretation Agent -- using advanced LangChain coordination. The Simulation Generation Agent employs a structured chain-of-thought (CoT) reasoning process, leveraging LLMs and retrieval-augmented generation (RAG) to translate natural language simulation specifications into precise ns-3 scripts. Concurrently, the Test Designer Agent generates comprehensive automated test suites by integrating knowledge retrieval techniques with dynamic test case synthesis. The Test Executor Agent dynamically deploys and runs simulations, managing dependencies and parsing detailed performance metrics. At the same time, the Result Interpretation Agent utilizes LLM-driven analysis to extract actionable insights from the simulation outputs. By integrating external resources such as library documentation and ns-3 testing frameworks, our experimental approach can enhance simulation accuracy and adaptability, reducing reliance on extensive programming expertise. A detailed case study using the ns-3 5G-LENA module validates the effectiveness of the proposed approach. The code generation process converges in an average of 1.8 iterations, has a syntax error rate of 17.0%, a mean response time of 7.3 seconds, and receives a human evaluation score of 7.5.

cs.NI↗

arXiv2025

Towards Cloud-Native Agentic Protocol Learning for Conflict-Free 6G: A Case Study on Inter-Slice Resource Allocation

In this paper, we propose a novel cloud-native architecture for collaborative agentic network slicing. Our approach addresses the challenge of managing shared infrastructure, particularly CPU resources, across multiple network slices with heterogeneous requirements. Each network slice is controlled by a dedicated agent operating within a Dockerized environment, ensuring isolation and scalability. The agents dynamically adjust CPU allocations based on real-time traffic demands, optimizing the performance of the overall system. A key innovation of this work is the development of emergent communication among the agents. Through their interactions, the agents autonomously establish a communication protocol that enables them to coordinate more effectively, optimizing resource allocations in response to dynamic traffic demands. Based on synthetic traffic modeled on real-world conditions, accounting for varying load patterns, tests demonstrated the effectiveness of the proposed architecture in handling diverse traffic types, including eMBB, URLLC, and mMTC, by adjusting resource allocations to meet the strict requirements of each slice. Additionally, the cloud-native design enables real-time monitoring and analysis through Prometheus and Grafana, ensuring the system's adaptability and efficiency in dynamic network environments. The agents managed to learn how to maximize the shared infrastructure with a conflict rate of less than 3%.

cs.NI↗

arXiv2024

GenOnet: Generative Open xG Network Simulation with Multi-Agent LLM and ns-3

The move toward Sixth-Generation (6G) networks relies on open interfaces and protocols for seamless interoperability across devices, vendors, and technologies. In this context, open 6G development involves multiple disciplines and requires advanced simulation approaches for testing. In this demo paper, we propose a generative simulation approach based on a multi-agent Large Language Model (LLM) and Network Simulator 3 (ns-3), called Generative Open xG Network Simulation (GenOnet), to effectively generate, debug, execute, and interpret simulated Open Fifth-Generation (5G) environments. The first version of GenOnet application represents a specialized adaptation of the OpenAI GPT models. It incorporates supplementary tools, agents, 5G standards, and seamless integration with ns-3 simulation capabilities, supporting both C++ variants and Python implementations. This release complies with the latest Open Radio Access Network (O-RAN) and 3GPP standards.

cs.NI↗

arXiv2024

Toward Explainable Reasoning in 6G: A Proof of Concept Study on Radio Resource Allocation

The move toward artificial intelligence (AI)-native sixth-generation (6G) networks has put more emphasis on the importance of explainability and trustworthiness in network management operations, especially for mission-critical use-cases. Such desired trust transcends traditional post-hoc explainable AI (XAI) methods to using contextual explanations for guiding the learning process in an in-hoc way. This paper proposes a novel graph reinforcement learning (GRL) framework named TANGO which relies on a symbolic subsystem. It consists of a Bayesian-graph neural network (GNN) Explainer, whose outputs, in terms of edge/node importance and uncertainty, are periodically translated to a logical GRL reward function. This adjustment is accomplished through defined symbolic reasoning rules within a Reasoner. Considering a real-world testbed proof-of-concept (PoC), a gNodeB (gNB) radio resource allocation problem is formulated, which aims to minimize under- and over-provisioning of physical resource blocks (PRBs) while penalizing decisions emanating from the uncertain and less important edge-nodes relations. Our findings reveal that the proposed in-hoc explainability solution significantly expedites convergence compared to standard GRL baseline and other benchmarks in the deep reinforcement learning (DRL) domain. The experiment evaluates performance in AI, complexity, energy consumption, robustness, network, scalability, and explainability metrics. Specifically, the results show that TANGO achieves a noteworthy accuracy of 96.39% in terms of optimal PRB allocation in inference phase, outperforming the baseline by 1.22x.

cs.NI↗

arXiv2024

Intelligible Protocol Learning for Resource Allocation in 6G O-RAN Slicing

An adaptive standardized protocol is essential for addressing inter-slice resource contention and conflict in network slicing. Traditional protocol standardization is a cumbersome task that yields hardcoded predefined protocols, resulting in increased costs and delayed rollout. Going beyond these limitations, this paper proposes a novel multi-agent deep reinforcement learning (MADRL) communication framework called standalone explainable protocol (STEP) for future sixth-generation (6G) open radio access network (O-RAN) slicing. As new conditions arise and affect network operation, resource orchestration agents adapt their communication messages to promote the emergence of a protocol on-the-fly, which enables the mitigation of conflict and resource contention between network slices. STEP weaves together the notion of information bottleneck (IB) theory with deep Q-network (DQN) learning concepts. By incorporating a stochastic bottleneck layer -- inspired by variational autoencoders (VAEs) -- STEP imposes an information-theoretic constraint for emergent inter-agent communication. This ensures that agents exchange concise and meaningful information, preventing resource waste and enhancing the overall system performance. The learned protocols enhance interpretability, laying a robust foundation for standardizing next-generation 6G networks. By considering an O-RAN compliant network slicing resource allocation problem, a conflict resolution protocol is developed. In particular, the results demonstrate that, on average, STEP reduces inter-slice conflicts by up to 6.06x compared to a predefined protocol method. Furthermore, in comparison with an MADRL baseline, STEP achieves 1.4x and 3.5x lower resource underutilization and latency, respectively.

cs.NI↗

arXiv2024

A Mathematical Introduction to Deep Reinforcement Learning for 5G/6G Applications

Algorithmic innovation can unleash the potential of the beyond 5G (B5G)/6G communication systems. Artificial intelligence (AI)-driven zero-touch network slicing is envisaged as a promising cutting-edge technology to harness the full potential of heterogeneous 6G networks and enable the automation of demand-aware management and orchestration (MANO). The network slicing continues towards numerous slices with micro or macro services in 6G networks, and thereby, designing a robust, stable, and distributed learning mechanism is considered a necessity. In this regard, robust brain-inspired and dopamine-like learning methods, such as Actor-Critic approaches, can play a vital role. The tutorial begins with an introduction to network slicing, reinforcement learning (RL), and recent state-of-the-art (SoA) algorithms. Then, the paper elaborates on the combination of value-based and policy-based methods in the form of Actor-Critic techniques tailored to the needs of future wireless networks.

cs.NI↗

arXiv2023

Decentralized Energy Marketplace via NFTs and AI-based Agents

The paper introduces an advanced Decentralized Energy Marketplace (DEM) integrating blockchain technology and artificial intelligence to manage energy exchanges among smart homes with energy storage systems. The proposed framework uses Non-Fungible Tokens (NFTs) to represent unique energy profiles in a transparent and secure trading environment. Leveraging Federated Deep Reinforcement Learning (FDRL), the system promotes collaborative and adaptive energy management strategies, maintaining user privacy. A notable innovation is the use of smart contracts, ensuring high efficiency and integrity in energy transactions. Extensive evaluations demonstrate the system's scalability and the effectiveness of the FDRL method in optimizing energy distribution. This research significantly contributes to developing sophisticated decentralized smart grid infrastructures. Our approach broadens potential blockchain and AI applications in sustainable energy systems and addresses incentive alignment and transparency challenges in traditional energy trading mechanisms. The implementation of this paper is publicly accessible at \url{https://github.com/RasoulNik/DEM}.

cs.NI↗

arXiv2023

X-GRL: An Empirical Assessment of Explainable GNN-DRL in B5G/6G Networks

The rapid development of artificial intelligence (AI) techniques has triggered a revolution in beyond fifth-generation (B5G) and upcoming sixth-generation (6G) mobile networks. Despite these advances, efficient resource allocation in dynamic and complex networks remains a major challenge. This paper presents an experimental implementation of deep reinforcement learning (DRL) enhanced with graph neural networks (GNNs) on a real 5G testbed. The method addresses the explainability of GNNs by evaluating the importance of each edge in determining the model's output. The custom sampling functions feed the data into the proposed GNN-driven Monte Carlo policy gradient (REINFORCE) agent to optimize the gNodeB (gNB) radio resources according to the specific traffic demands. The demo demonstrates real-time visualization of network parameters and superior performance compared to benchmarks.

cs.NI↗