ReM-MoA: Reasoning Memory Sustains Mixture-of-Agents Scaling

Mixture-of-Agents (MoA) architectures improve inference-time scaling by organizing multiple LLM agents into layered reasoning pipelines. However, existing MoA variants fail to sustain gains as depth increases, exhibiting degradation, early plateauing, or saturation. We propose ReM-MoA, a memory-augmented MoA framework that sustains scaling through two mechanisms: (1) a Ranked Reasoning Memory that persistently stores and ranks reasoning traces from all layers using a comparative Reviewer Agent, and (2) a Curated Diversified Memory Routing scheme that exposes different agents to distinct combinations of successful and failed traces, preserving exploration diversity while propagating high-quality reasoning. We further introduce an optional multi-domain Reviewer distillation pipeline that improves ranking quality through frontier-model supervision. Across five reasoning benchmarks spanning math, formal logic, code, knowledge, and commonsense, ReM-MoA consistently outperforms prior MoA variants across both depth and width scaling, and its advantage widens with depth, establishing structured cross-layer reasoning memory as a key missing mechanism for scalable multi-agent inference.

Sparse Subspace-to-Expert Sharing for Task-Agnostic Continual Learning

Continual learning in Large Language Models (LLMs) is hindered by the plasticity-stability dilemma, where acquiring new capabilities often leads to catastrophic forgetting of previous knowledge. Existing methods typically treat parameters uniformly, failing to distinguish between specific task knowledge and shared capabilities. We introduce Mixture of Sparse Experts for Task Agnostic Continual Learning (SETA), a framework that resolves the plasticity-stability conflict through adaptive sparse subspace decomposition into task-specific expert modules. Unlike standard updates, where tasks compete for the same parameters, SETA separates knowledge into unique experts, designed to isolate task-specific patterns, and shared experts, responsible for capturing common features. This structure is maintained through adaptive elastic anchoring and a routing-aware regularization that jointly protect shared knowledge at both the weight and routing levels and enable a unified gating network to automatically retrieve the correct expert combination during inference. Extensive experiments across diverse domain-specific benchmarks demonstrate that SETA achieves competitive or superior overall performance relative to state-of-the-art continual learning baselines, with particularly strong retention of early-task knowledge and improved backward transfer on LLaMA-2 7B and Qwen3-4B.

LLM-Guided ANN Index Optimization for Human-Object Interaction Retrieval

Retrieval systems underpin modern AI applications -- spanning visual search, recommendation engines, and multi-modal question answering. Modern multi-stage retrieval systems require the joint optimization of highly coupled parameters, yet traditional hyperparameter optimization (HPO) methods -- including Tree-structured Parzen Estimators (TPE) and Gaussian Process Bayesian Optimization -- rely on an independence assumption that fundamentally prevents them from navigating these coupled configuration spaces. We address this limitation with a phase-aware large language model (LLM) agent that conditions each proposal on its full optimization history, navigating the coupled parameter space across phase-partitioned exploration, exploitation, and fine-tuning stages. Evaluated on the HICO-DET human-object interaction retrieval benchmark using Intel VDMS (Visual Data Management System), our agent outperforms Optuna TPE by +33.3% and VDTuner by +34.2% under SIEVE (Safeguarded Index Evaluation of Vector-search Efficiency, a quality-constrained throughput metric), delivering a 15.3x throughput gain over UniIR. Validation across three benchmarks confirms that the agent's advantage grows with the degree of parameter coupling: +33.3% on HICO-DET (high coupling), methods converge within 1% on GLDv2 (moderate coupling) and within 3.6% on SIFT1M (near-independent control). Cross-system validation on Milvus confirms the optimizer ranks first on all three datasets without modification, demonstrating transferability across vector database management system (VDBMS) platforms.

Fast MoE Inference via Predictive Prefetching and Expert Replication

The Mixture of Experts (MoE) architecture has become a fundamental building block in state-of-the-art large language models (LLMs), improving domain-specific expertise in LLMs and scaling model capacity without proportionally increasing their computational overhead. However, MoE inference often suffers from suboptimal GPU utilization, load imbalance, and elevated latency arising from multiple tokens waiting on the same experts for their computation which arises from sparsity of expert activation. To address these challenges, we propose a dynamic expert replication strategy that predicts which experts are likely to be overloaded and replicates them for upcoming batches of tokens. The replicated experts process batch tokens concurrently across layers, which leads to improved parallelism, shorter GPU idle time, and significantly faster inference. Experimental evaluations conducted on large-scale MoE models, including Switch-base-128 and Switch-base-256, demonstrate that our method achieves near-complete GPU utilization (approx 100%), leading to upto 3x improvement in inference speed while preserving approximately 90-95% of the performance of baseline architectures

CRAFT: Forgetting-Aware Intervention-Based Adaptation for Continual Learning

Large language models (LLMs) can acquire new capabilities through fine-tuning, but continual adaptation often leads to catastrophic forgetting. We propose CRAFT, a continual learning framework that avoids updating model weights by instead learning low-rank interventions on hidden representations. CRAFT proceeds in three stages: it first routes each task to a group of similar tasks based on output-distribution divergence; it then fine-tunes the model using a Kullback-Leibler (KL) divergence against the group's prior state, which directly controls forgetting and determines convergence; finally, it merges interventions for the updated task into the shared representation using the same KL signal. This design unifies routing, regularization, and merging through a single KL-based objective. CRAFT improves overall performance and reduces forgetting compared to strong LoRA-based approaches across multiple benchmarks and model scales, while remaining robust to task ordering. These results suggest that controlling adaptation in representation space, guided by output-space divergence, provides a scalable and principled approach to continual learning in LLMs.

NOMAD: Generating Embeddings for Massive Distributed Graphs

Successful machine learning on graphs or networks requires embeddings that not only represent nodes and edges as low-dimensional vectors but also preserve the graph structure. Established methods for generating embeddings require flexible exploration of the entire graph through repeated use of random walks that capture graph structure with samples of nodes and edges. These methods create scalability challenges for massive graphs with millions-to-billions of edges because single-node solutions have inadequate memory and processing capabilities. We present NOMAD, a distributed-memory graph embedding framework using the Message Passing Interface (MPI) for distributed graphs. NOMAD implements proximity-based models proposed in the widely popular LINE (Large-scale Information Network Embedding) algorithm. We propose several practical trade-offs to improve the scalability and communication overheads confronted by irregular and distributed graph embedding methods, catering to massive-scale graphs arising in web and science domains. NOMAD demonstrates median speedups of 10/100x on CPU-based NERSC Perlmutter cluster relative to the popular reference implementations of multi-threaded LINE and node2vec, 35-76x over distributed PBG, and competitive embedding quality relative to LINE, node2vec, and GraphVite, while yielding 12-370x end-to-end speedups on real-world graphs.

Communication-free Sampling and 4D Hybrid Parallelism for Scalable Mini-batch GNN Training

Graph neural networks (GNNs) are widely used for learning on graph datasets derived from various real-world scenarios. Learning from extremely large graphs requires distributed training, and mini-batching with sampling is a popular approach for parallelizing GNN training. Existing distributed mini-batch approaches have significant performance bottlenecks due to expensive sampling methods and limited scaling when using data parallelism. In this work, we present ScaleGNN, a 4D parallel framework for scalable mini-batch GNN training that combines communication-free distributed sampling, 3D parallel matrix multiplication (PMM), and data parallelism. ScaleGNN introduces a uniform vertex sampling algorithm, enabling each process (GPU device) to construct its local mini-batch, i.e., subgraph partitions without any inter-process communication. 3D PMM enables scaling mini-batch training to much larger GPU counts than vanilla data parallelism with significantly lower communication overheads. We also present additional optimizations to overlap sampling with training, reduce communication overhead by sending data in lower precision, kernel fusion, and communication-computation overlap. We evaluate ScaleGNN on five graph datasets and demonstrate strong scaling up to 2048 GPUs on Perlmutter, 2048 GCDs on Frontier, and 1024 GPUs on Tuolumne. On Perlmutter, ScaleGNN achieves 3.5x end-to-end training speedup over the SOTA baseline on ogbn-products.

OptiML: An End-to-End Framework for Program Synthesis and CUDA Kernel Optimization

Generating high-performance CUDA kernels remains challenging due to the need to navigate a combinatorial space of low-level transformations under noisy and expensive hardware feedback. Although large language models can synthesize functionally correct CUDA code, achieving competitive performance requires systematic exploration and verification of optimization choices. We present OptiML, an end-to-end framework that maps either natural-language intent or input CUDA code to performance-optimized CUDA kernels by formulating kernel optimization as search under verification. OptiML consists of two decoupled stages. When the input is natural language, a Mixture-of-Thoughts generator (OptiML-G) acts as a proposal policy over kernel implementation strategies, producing an initial executable program. A search-based optimizer (OptiML-X) then refines either synthesized or user-provided kernels using Monte Carlo Tree Search over LLM-driven edits, guided by a hardware-aware reward derived from profiler feedback. Each candidate transformation is compiled, verified, and profiled with Nsight Compute, and evaluated by a composite objective that combines runtime with hardware bottleneck proxies and guardrails against regressions. We evaluate OptiML in both synthesis-and-optimize and optimization-only settings on a diverse suite of CUDA kernels. Results show that OptiML consistently discovers verified performance improvements over strong LLM baselines and produces interpretable optimization trajectories grounded in profiler evidence.

Split-on-Share: Mixture of Sparse Experts for Task-Agnostic Continual Learning

Continual learning in Large Language Models (LLMs) is hindered by the plasticity-stability dilemma, where acquiring new capabilities often leads to catastrophic forgetting of previous knowledge. Existing methods typically treat parameters uniformly, failing to distinguish between specific task knowledge and shared capabilities. We introduce Mixture of Sparse Experts for Task-Agnostic Continual Learning, referred to as SETA, a framework that resolves the plasticity-stability conflict by decomposing the model into modular subspaces. Unlike standard updates, where tasks compete for the same parameters, SETA separates knowledge into unique experts, designed to isolate task-specific patterns, and shared experts, responsible for capturing common features. This structure is maintained through elastic weight anchoring, which protects critical shared knowledge and enables a unified gating network to automatically retrieve the correct expert combination for each task during inference. Extensive experiments across diverse domain-specific and general benchmarks demonstrate that SETA consistently outperforms state-of-the-art parameter-efficient fine-tuning-based continual learning methods.

AgenticPruner: MAC-Constrained Neural Network Compression via LLM-Driven Strategy Search

Neural network pruning remains essential for deploying deep learning models on resource-constrained devices, yet existing approaches primarily target parameter reduction without directly controlling computational cost. This yields unpredictable inference latency in deployment scenarios where strict Multiply-Accumulate (MAC) operation budgets must be met. We propose AgenticPruner, a framework utilizing large language models to achieve MAC-constrained optimization through iterative strategy learning. Our approach coordinates three specialized agents: a Profiling Agent that analyzes model architecture and MAC distributions, a Master Agent that orchestrates the workflow with divergence monitoring, and an Analysis Agent powered by Claude 3.5 Sonnet that learns optimal strategies from historical attempts. Through in-context learning, the Analysis Agent improves convergence success rate from 48% to 71% compared to grid search. Building upon isomorphic pruning's graph-based structural grouping, our method adds context-aware adaptation by analyzing patterns across pruning iterations, enabling automatic convergence to target MAC budgets within user-defined tolerance bands. We validate our framework on ImageNet-1K across ResNet, ConvNeXt, and DeiT architectures. On CNNs, our approach achieves MAC targeting while maintaining or improving accuracy: ResNet-50 reaches 1.77G MACs with 77.04% accuracy (+0.91% vs baseline); ResNet-101 achieves 4.22G MACs with 78.94% accuracy (+1.56% vs baseline). For ConvNeXt-Small, pruning to 8.17G MACs yields 1.41x GPU and 1.07x CPU speedup with 45% parameter reduction. On Vision Transformers, we demonstrate MAC-budget compliance within user-defined tolerance bands (typically +1% to +5% overshoot, -5% to -15% undershoot), establishing feasibility for deployment scenarios requiring strict computational guarantees.