Muhammad Ahmed Mohsin

Omkar Ghugarkar, Vishvesh Bhat, Muhammad Ahmed Mohsin et al.

Generalization across agentic tool-calling environments remains a central challenge for reliable agentic reasoning systems. Although large language models achieve strong results on individual benchmarks, their ability to compose reasoning strategies, preserve intermediate states, and coordinate tools across domains remains underexplored. We present MAVEN (Modular Agentic Verification and Execution Network), a lightweight symbolic reasoning scaffold for structured decomposition, adaptive tool orchestration, and intermediate verification. We evaluate MAVEN across established tool-calling benchmarks, including BFCL v3, TauBench, Tau2Bench, AceBench, and introduce MAVEN-Bench, a stress-test benchmark for multi-step mathematical and physical reasoning with explicit verification and adversarial task composition. MAVEN-Bench exposes a substantial gap between partial reasoning quality and end-to-end task success; in direct MAVEN-Bench runs, MAVEN improves its GPT-OSS-120b base model from 48% to 71% accuracy without additional training. It also remains competitive with frontier proprietary baselines while using an open-weight backbone with an estimated cost ratio of roughly 1/10, suggesting that lightweight verification-centered scaffolds can strengthen compositional reasoning and motivate more process-aware evaluation of agents in the wild.

Muhammad Ahmed Mohsin, Muhammad Umer, Ahsan Bilal et al.

Large language model reasoning is often treated as a monolithic capability, relying on binary preference supervision that fails to capture partial progress or fine-grained reasoning quality. We introduce Continuous Utility Direct Preference Optimization (CU-DPO), a framework that aligns models to a portfolio of prompt-based cognitive strategies by replacing binary labels with continuous scores that capture fine-grained reasoning quality. We prove that learning with K strategies yields a Theta(K log K) improvement in sample complexity over binary preferences, and that DPO converges to the entropy-regularized utility-maximizing policy. To exploit this signal, we propose a two-stage training pipeline: (i) strategy selection, which optimizes the model to choose the best strategy for a given problem via best-vs-all comparisons, and (ii) execution refinement, which trains the model to correctly execute the selected strategy using margin-stratified pairs. On mathematical reasoning benchmarks, CU-DPO improves strategy selection accuracy from 35-46 percent to 68-78 percent across seven base models, yielding consistent downstream reasoning gains of up to 6.6 points on in-distribution datasets with effective transfer to out-of-distribution tasks.

Muhammad Umer, Muhammad Ahmed Mohsin, Ahsan Bilal et al.

Post-training has split large language model (LLM) alignment into two largely disconnected tracks. Online reinforcement learning (RL) with verifiable rewards drives emergent reasoning on math and code but depends on a programmatic verifier that cannot reach open-ended tasks, while preference optimization handles open-ended generation yet forgoes the continuous exploration that powers online RL. Closing this gap requires a verifier for open-ended quality, but a scalar reward model is the wrong shape for the job. Quality is multi-dimensional, and any scalar score is an incomplete proxy that lets online RL collapse onto whichever axis the score is most sensitive to. We turn instead to the General Preference Model (GPM), which embeds responses into $k$ skew-symmetric subspaces and represents preference as a structured, intransitivity-aware comparison. Building on this, we propose General Preference Reinforcement Learning (GPRL), which carries the $k$-way structure through to the policy update. GPRL computes per-dimension group-relative advantages, normalizes each on its own scale so no axis can dominate, and aggregates them with context-dependent eigenvalues. The same structure powers a closed-loop drift monitor that detects single-axis exploitation and corrects it on the fly by reweighting dimensions and tightening the trust region. Starting from $\texttt{Llama-3-8B-Instruct}$, GPRL reaches a length-controlled win rate of $56.51\%$ on AlpacaEval~2.0 while also outperforming SimPO and SPPO on Arena-Hard, MT-Bench, and WildBench by resisting reward hacking across extended training runs.

Ahsan Bilal, Muhammad Ahmed Mohsin, Muhammad Umer et al.

Test-time scaling investigates whether a fixed diffusion language model (DLM) can generate better outputs when given more inference compute, without additional training. However, naive best-of-$K$ sampling is fundamentally limited because it repeatedly draws from the same base diffusion distribution, whose high-probability regions are often misaligned with high-quality outputs. We propose $S^3$ (Stratified Scaling Search), a classical verifier-guided search method that improves generation by reallocating compute during the denoising process rather than only at the final output stage. At each denoising step, $S^3$ expands multiple candidate trajectories, evaluates them with a lightweight reference-free verifier, and selectively resamples promising candidates while preserving diversity within the search frontier. This procedure effectively approximates a reward-tilted sampling distribution that favors higher-quality outputs while remaining anchored to the model prior. Experiments with LLaDA-8B-Instruct on MATH-500, GSM8K, ARC-Challenge, and TruthfulQA demonstrate that $S^3$ consistently improves performance across benchmarks, achieving the largest gains on mathematical reasoning tasks while leaving the underlying model and decoding schedule unchanged. These results show that classical search over denoising trajectories provides a practical mechanism for test-time scaling in DLMs.

Muhammad Ahmed Mohsin, Ahsan Bilal, Muhammad Umer et al.

Large language models exhibit sycophancy, the tendency to shift their stated positions toward perceived user preferences or authority cues regardless of evidence. Standard alignment methods fail to correct this because scalar reward models conflate two distinct failure modes into a single signal: pressure capitulation, where the model changes a correct answer under social pressure, and evidence blindness, where the model ignores the provided context entirely. We operationalise sycophancy through formal definitions of pressure independence and evidence responsiveness, serving as a working framework for disentangled training rather than a definitive characterisation of the phenomenon. We propose the first approach to sycophancy reduction via reward decomposition, introducing a multi-component Group Relative Policy Optimisation (GRPO) reward that decomposes the training signal into five terms: pressure resistance, context fidelity, position consistency, agreement suppression, and factual correctness. We train using a contrastive dataset pairing pressure-free baselines with pressured variants across three authority levels and two opposing evidence contexts. Across five base models, our two-phase pipeline consistently reduces sycophancy on all metric axes, with ablations confirming that each reward term governs an independent behavioural dimension. The learned resistance to pressure generalises beyond our training methodology and prompt structure, reducing answer-priming sycophancy by up to 17 points on SycophancyEval despite the absence of such pressure forms during training.

Kainat Riaz, Muhammad Ahmed Mohsin, Ahsan Bilal et al.

Automated scientific discovery using large language models relies on identifying genuinely novel solutions. Standard reinforcement learning penalizes high-variance mutations, which leads the policy to prioritize familiar patterns. As a result, the maximum reward plateaus even as the average reward increases. Overcoming this limitation requires a signal that distinguishes unexplored regions from intrinsically difficult problems. This necessitates measuring disagreement across independently adapted weight hypotheses rather than relying on a single network's confidence. UG-TTT addresses this challenge by maintaining a small ensemble of low-rank adapters over a frozen base model. The per-token disagreement, quantified as the mutual information between ensemble predictions and weight hypotheses, isolates epistemic uncertainty and identifies positions where insufficient coverage leads to adapter divergence rather than intrinsic problem difficulty. This measure is incorporated as an exploration bonus into the policy gradient, directing the policy toward positions where persistent adapter disagreement signals low training coverage, the same frontier where genuine discovery is possible. A nuclear norm regularizer ensures the adapters remain distinct from one another, thereby preserving the exploration signal throughout training. Across four scientific discovery benchmarks, UG-TTT increases the maximum reward on three tasks, maintains substantially higher solution diversity, and an ablation study confirms that the regularizer is essential for sustaining this behavior.

Asad Aali, Muhammad Ahmed Mohsin, Vasiliki Bikia et al.

As language models (LMs) are increasingly adopted across domains, high-quality benchmarking frameworks that accurately estimate performance are essential for guiding deployment decisions. While frameworks such as Holistic Evaluation of Language Models (HELM) enable broad evaluation across tasks, they often rely on fixed prompts that fail to generalize across LMs, yielding unrepresentative performance estimates. Unless we approximate each LM's ceiling (maximum achievable via changes to the prompt), we risk underestimating performance. Declarative prompting frameworks, such as DSPy, offer a scalable alternative to manual prompt engineering by crafting structured prompts that can be optimized per task. However, such frameworks have not been systematically evaluated across established benchmarks. We present a reproducible DSPy+HELM framework that introduces structured prompting methods which elicit reasoning, enabling more accurate LM benchmarking. Using four prompting methods, we evaluate four frontier LMs across seven benchmarks (general/medical domain) against existing HELM baseline scores. We find that without structured prompting: (i) HELM underestimates LM performance (by 4% average), (ii) performance estimates vary more across benchmarks ($+$2% standard deviation), (iii) performance gaps are misrepresented (leaderboard rankings flip on 3/7 benchmarks), and (iv) introducing chain-of-thought reduces LM sensitivity to prompt design (smaller $Δ$ across prompts). To our knowledge, this is the first benchmarking study to systematically integrate structured prompting into an established evaluation framework, demonstrating how scalable performance-ceiling approximation yields more robust, decision-useful benchmarks. We open-source (i) DSPy+HELM Integration (https://github.com/stanford-crfm/helm/pull/3893) and (ii) Prompt Optimization Pipeline (https://github.com/StanfordMIMI/dspy-helm).

Ahsan Bilal, Muhammad Ahmed Mohsin, Muhammad Umer et al.

This survey explores the development of meta-thinking capabilities in Large Language Models (LLMs) from a Multi-Agent Reinforcement Learning (MARL) perspective. Meta-thinking self-reflection, assessment, and control of thinking processes is an important next step in enhancing LLM reliability, flexibility, and performance, particularly for complex or high-stakes tasks. The survey begins by analyzing current LLM limitations, such as hallucinations and the lack of internal self-assessment mechanisms. It then talks about newer methods, including RL from human feedback (RLHF), self-distillation, and chain-of-thought prompting, and each of their limitations. The crux of the survey is to talk about how multi-agent architectures, namely supervisor-agent hierarchies, agent debates, and theory of mind frameworks, can emulate human-like introspective behavior and enhance LLM robustness. By exploring reward mechanisms, self-play, and continuous learning methods in MARL, this survey gives a comprehensive roadmap to building introspective, adaptive, and trustworthy LLMs. Evaluation metrics, datasets, and future research avenues, including neuroscience-inspired architectures and hybrid symbolic reasoning, are also discussed.

Muhammad Ahmed Mohsin, Muhammad Jazib, Zeeshan Alam et al.

In the evolving landscape of 6G networks, semantic communications are poised to revolutionize data transmission by prioritizing the transmission of semantic meaning over raw data accuracy. This paper presents a Vision Transformer (ViT)-based semantic communication framework that has been deliberately designed to achieve high semantic similarity during image transmission while simultaneously minimizing the demand for bandwidth. By equipping ViT as the encoder-decoder framework, the proposed architecture can proficiently encode images into a high semantic content at the transmitter and precisely reconstruct the images, considering real-world fading and noise consideration at the receiver. Building on the attention mechanisms inherent to ViTs, our model outperforms Convolution Neural Network (CNNs) and Generative Adversarial Networks (GANs) tailored for generating such images. The architecture based on the proposed ViT network achieves the Peak Signal-to-noise Ratio (PSNR) of 38 dB, which is higher than other Deep Learning (DL) approaches in maintaining semantic similarity across different communication environments. These findings establish our ViT-based approach as a significant breakthrough in semantic communications.

Sagnik Bhattacharya, Muhammad Ahmed Mohsin, Kamyar Rajabalifardi et al.

This paper proposes a novel joint channel-estimation and source-detection algorithm using successive interference cancellation (SIC)-aided generative score-based diffusion models. Prior work in this area focuses on massive MIMO scenarios, which are typically characterized by full-rank channels, and fail in low-rank channel scenarios. The proposed algorithm outperforms existing methods in joint source-channel estimation, especially in low-rank scenarios where the number of users exceeds the number of antennas at the access point (AP). The proposed score-based iterative diffusion process estimates the gradient of the prior distribution on partial channels, and recursively updates the estimated channel parts as well as the source. Extensive simulation results show that the proposed method outperforms the baseline methods in terms of normalized mean squared error (NMSE) and symbol error rate (SER) in both full-rank and low-rank channel scenarios, while having a more dominant effect in the latter, at various signal-to-noise ratios (SNR).

Oluwaseyi Giwa, Tobi Awodunmila, Muhammad Ahmed Mohsin et al.

The dynamic allocation of spectrum in 5G / 6G networks is critical to efficient resource utilization. However, applying traditional deep reinforcement learning (DRL) is often infeasible due to its immense sample complexity and the safety risks associated with unguided exploration, which can cause severe network interference. To address these challenges, we propose a meta-learning framework that enables agents to learn a robust initial policy and rapidly adapt to new wireless scenarios with minimal data. We implement three meta-learning architectures, model-agnostic meta-learning (MAML), recurrent neural network (RNN), and an attention-enhanced RNN, and evaluate them against a non-meta-learning DRL algorithm, proximal policy optimization (PPO) baseline, in a simulated dynamic integrated access/backhaul (IAB) environment. Our results show a clear performance gap. The attention-based meta-learning agent reaches a peak mean network throughput of 48 Mbps, while the PPO baseline decreased drastically to 10 Mbps. Furthermore, our method reduces SINR and latency violations by more than 50% compared to PPO. It also shows quick adaptation, with a fairness index 0.7, showing better resource allocation. This work proves that meta-learning is a very effective and safer option for intelligent control in complex wireless systems.

Sagnik Bhattacharya, Muhammad Ahmed Mohsin, Ahsan Bilal et al.

Emerging wireless AR/VR applications require real-time transmission of correlated high-fidelity speech from multiple resource-constrained devices over unreliable, bandwidth-limited channels. Existing autoencoder-based speech source coding methods fail to address the combination of the following - (1) dynamic bitrate adaptation without retraining the model, (2) leveraging correlations among multiple speech sources, and (3) balancing downstream task loss with realism of reconstructed speech. We propose a neural distributed principal component analysis (NDPCA)-aided distributed source coding algorithm for correlated speech sources transmitting to a central receiver. Our method includes a perception-aware downstream task loss function that balances perceptual realism with task-specific performance. Experiments show significant PSNR improvements under bandwidth constraints over naive autoencoder methods in task-agnostic (19%) and task-aware settings (52%). It also approaches the theoretical upper bound, where all correlated sources are sent to a single encoder, especially in low-bandwidth scenarios. Additionally, we present a rate-distortion-perception trade-off curve, enabling adaptive decisions based on application-specific realism needs.

Muhammad Ahmed Mohsin, Muhammad Umer, Ahsan Bilal et al.

Large Language Models (LLMs) have benefited enormously from scaling, yet these gains are bounded by five fundamental limitations: (1) hallucination, (2) context compression, (3) reasoning degradation, (4) retrieval fragility, and (5) multimodal misalignment. While existing surveys describe these phenomena empirically, they lack a rigorous theoretical synthesis connecting them to the foundational limits of computation, information, and learning. This work closes that gap by presenting a unified, proof-informed framework that formalizes the innate theoretical ceilings of LLM scaling. First, computability and uncomputability imply an irreducible residue of error: for any computably enumerable model family, diagonalization guarantees inputs on which some model must fail, and undecidable queries (e.g., halting-style tasks) induce infinite failure sets for all computable predictors. Second, information-theoretic and statistical constraints bound attainable accuracy even on decidable tasks, finite description length enforces compression error, and long-tail factual knowledge requires prohibitive sample complexity. Third, geometric and computational effects compress long contexts far below their nominal size due to positional under-training, encoding attenuation, and softmax crowding. We further show how likelihood-based training favors pattern completion over inference, how retrieval under token limits suffers from semantic drift and coupling noise, and how multimodal scaling inherits shallow cross-modal alignment. Across sections, we pair theorems and empirical evidence to outline where scaling helps, where it saturates, and where it cannot progress, providing both theoretical foundations and practical mitigation paths like bounded-oracle retrieval, positional curricula, and sparse or hierarchical attention.

Muhammad Ahmed Mohsin, Junaid Ahmad, Muhammad Hamza Nawaz et al.

Ambient intelligence (AmI) is a computing paradigm in which physical environments are embedded with sensing, computation, and communication so they can perceive people and context, decide appropriate actions, and respond autonomously. Realizing AmI at global scale requires sixth generation (6G) wireless networks with capabilities for real time perception, reasoning, and action aligned with human behavior and mobility patterns. We argue that Generative Artificial Intelligence (GenAI) is the creative core of such environments. Unlike traditional AI, GenAI learns data distributions and can generate realistic samples, making it well suited to close key AmI gaps, including generating synthetic sensor and channel data in under observed areas, translating user intent into compact, semantic messages, predicting future network conditions for proactive control, and updating digital twins without compromising privacy. This chapter reviews foundational GenAI models, GANs, VAEs, diffusion models, and generative transformers, and connects them to practical AmI use cases, including spectrum sharing, ultra reliable low latency communication, intelligent security, and context aware digital twins. We also examine how 6G enablers, such as edge and fog computing, IoT device swarms, intelligent reflecting surfaces (IRS), and non terrestrial networks, can host or accelerate distributed GenAI. Finally, we outline open challenges in energy efficient on device training, trustworthy synthetic data, federated generative learning, and AmI specific standardization. We show that GenAI is not a peripheral addition, but a foundational element for transforming 6G from a faster network into an ambient intelligent ecosystem.

Oluwaseyi Giwa, Muhammad Ahmed Mohsin, Folarin Jubril Adesola et al.

Reliable link adaptation is critical for efficient wireless communications in dynamic fading environments. However, reinforcement learning (RL) solutions often suffer from unstable convergence due to poorly conditioned policy gradients, hindering their practical application. We propose the quantum-preconditioned policy gradient (QPPG) algorithm, which leverages Fisher-information-based preconditioning to stabilise and accelerate policy updates. Evaluations in Rayleigh fading scenarios show that QPPG achieves faster convergence, a 28.6% increase in average throughput, and a 43.8% decrease in average transmit power compared to classical methods. This work introduces quantum-geometric conditioning to link adaptation, marking a significant advance in developing robust, quantum-inspired reinforcement learning for future 6G networks, thereby enhancing communication reliability and energy efficiency.

Muhammad Umer, Muhammad Ahmed Mohsin, Huma Ghafoor et al.

This thesis delves into the forefront of wireless communication by exploring the synergistic integration of three transformative technologies: STAR-RIS, CoMP, and NOMA. Driven by the ever-increasing demand for higher data rates, improved spectral efficiency, and expanded coverage in the evolving landscape of 6G development, this research investigates the potential of these technologies to revolutionize future wireless networks. The thesis analyzes the performance gains achievable through strategic deployment of STAR-RIS, focusing on mitigating inter-cell interference, enhancing signal strength, and extending coverage to cell-edge users. Resource sharing strategies for STAR-RIS elements are explored, optimizing both transmission and reflection functionalities. Analytical frameworks are developed to quantify the benefits of STAR-RIS assisted CoMP-NOMA networks under realistic channel conditions, deriving key performance metrics such as ergodic rates and outage probabilities. Additionally, the research delves into energy-efficient design approaches for CoMP-NOMA networks incorporating RIS, proposing novel RIS configurations and optimization algorithms to achieve a balance between performance and energy consumption. Furthermore, the application of Deep Reinforcement Learning (DRL) techniques for intelligent and adaptive optimization in aerial RIS-assisted CoMP-NOMA networks is explored, aiming to maximize network sum rate while meeting user quality of service requirements. Through a comprehensive investigation of these technologies and their synergistic potential, this thesis contributes valuable insights into the future of wireless communication, paving the way for the development of more efficient, reliable, and sustainable networks capable of meeting the demands of our increasingly connected world.