APQF: Agentic Profiling-Guided Structured Pruning and Mixed-Precision Quantization with Adaptive Fine-Tuning

Modern deep neural networks achieve strong performance, but their scale makes them costly and slow, especially on resource-constrained edge devices. Pruning and quantization address this, but rely on manual, expert choices and on algorithms that are hard to apply across architectures. Uniform settings also ignore how differently individual layers respond to compression, which costs accuracy. We introduce APQF, an agentic profiling-guided framework that combines structured pruning, mixed-precision quantization-aware training, and accuracy recovery in one automated pipeline. A profiling agent measures how cost is distributed across the model and how sensitive each part is to pruning, and this evidence drives per-layer pruning ratios, per-layer bit-widths, and the recovery strategy, all proposed by LLM planners and validated before execution. To our knowledge, APQF is the first framework to combine LLM-guided, profiling-grounded decisions with a fully training-aware pruning and quantization pipeline for both CNNs and vision transformers. We evaluate APQF on ResNet, VGG7, ViT, DeiT, and Swin using ImageNet-1k and CIFAR-10. On ImageNet it cuts compute to 5.6-7.7 percent of the original bit-operations, a 13-18x reduction, while keeping accuracy close to the baseline, and under a 200K-image budget it stays roughly 17 points higher in Top-1 than existing joint pruning and quantization methods. On CIFAR-10 it compresses further than that method on four of five architectures. On VGG7 it reaches 93.15 percent using only 0.41 percent of baseline bit-operations, the only method at that compression level to improve on its full-precision baseline. Ablations show that uniform compression loses the most accuracy at matched compute, and that withholding profiling data from the planner hurts every model. Six LLM planners, including free open-weight ones, all reach 97.4-97.9 percent on Swin-Tiny.

Interpretable Adaptive Sampling for LLM Test-Time Scaling

Test-time scaling improves LLM reasoning by generating and aggregating multiple candidate answers, yet many pipelines use fixed per-query budgets that spend the same compute on easy and difficult prompts. These fixed budgets are also difficult to inspect because they do not explain why a given prompt receives a particular number of samples. We propose adaptive} test-time scaling with a lightweight fuzzy controller that maps interpretable signals, including estimated prompt complexity and model confidence, to a per-query sampling budget. The controller assigns fewer samples to easier or more confident prompts and more samples to harder or less certain prompts, making inference-time compute inspectable rather than fixed or opaque. We evaluate under a fair-alignment protocol with matched decoding settings and controlled answer selection, and compare against best-of-$N$, compute-aware scaling, and self-certainty-based baselines on question-answering and mathematical reasoning tasks. Across models and datasets, adaptive fuzzy control improves over several standard baselines and remains close to a selector-matched full-budget control while reducing the average number of samples. These findings suggest that interpretable adaptive sampling is a practical direction for more efficient test-time reasoning in large language models.

Multi-turn RL with Structural and Performance Aware Rewards for CUDA Kernel Generation

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a powerful technique to enhance the reasoning capacity of LLMs for optimized code generation. However, existing RLVR approaches primarily rely on outcome-based signals such as correctness and speedup, overlooking performance-critical structural properties of programs that are essential for generating optimized code. In this work, we propose CudaPerf, a reflective RL framework that incorporates both verifiable execution rewards and structural code-aware rewards derived from parallelization features (e.g., memory coalescing, occupancy, Arithmatic Intensity, and synchronization patterns). CudaPerf operates in two stages: (1) an offline pairwise ranking module that learns to distinguish strong and weak program candidates via contrastive comparisons, and (2) an online RL training phase that jointly optimizes for correctness, performance, and structural efficiency through a unified reward signal. To further enhance learning, CudaPerf utilizes iterative refinement using execution feedback enabling progressive improvement of generated candidates. We also introduce a dataset comprising 2.9k C to CUDA and 1k PyTorch to CUDA programs, each paired with diverse input configurations and multiple CUDA implementations encompassing diverse optimization strategies. CudaPerf is evaluated across multiple benchmarks comprising both C to CUDA and PyTorch to CUDA transformations. Empirical findings suggest that CudaPerf significantly outperforms strong baselines, including Qwen-3-32B (for C to CUDA) and CUDA Agent (for PyTorch to CUDA) by achieving up to 5X & 3.32X improvements in speedup, and 17% & 7% improvements in correctness, respectively.

VarRate: Training-Free Variable-Rate KV Cache Compression for Long-Context LLMs

The key-value (KV) cache is the main memory bottleneck in long-context large language model (LLM) inference. Two leading training-free families are both structurally limited: token-selection methods (SnapKV, Ada-KV) score importance from an observation window and evict low-scoring tokens, but eviction is irreversible -- so when the importance signal degrades under query-agnostic reuse, accuracy collapses by 11-15 points; uniform low-rank coding keeps every token but spends equal rank everywhere, wasting budget. We observe that both failures share one cure: rank should be allocated, not evicted. We present VarRate, a training-free KV codec that assigns each token a variable low-rank budget by its query salience, keeping every token at a nonzero rank. Comparable adaptive-rank codecs reach this allocation only through training; VarRate requires none. Because no token is dropped, it degrades by only 3.5-5.5 points where query-aware selection collapses. At a matched 20% budget on LongBench (16 tasks), VarRate stays within 0.8 points of the uncompressed model on both Llama-3.1-8B and Qwen2.5-7B. Averaged over the two, it is the strongest matched-memory compressor. It significantly beats its uniform-rank ablation on both models. Against KVzip, a method purpose-built for query-agnostic reuse, it is accuracy-equivalent in three of four settings and within a point overall, at about one-eighth the prefill overhead.

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.

POTracker: Optimizing Large Language Models for Standard-Compliant Power Outage Report Generation

Recent large language models (LLMs) are good at general text generation, but it is still hard to use them for domain-specific data generation because the output must follow strict formatting and structural rules. Unlike open-ended tasks such as question answering or translation, domain-specific generation must be both semantically correct and compliant with existing guidelines and standards. In this work, we study the nationwide interoperability problem of utility power outage reports in the United States. In practice, outage reports need to be machine-readable (e.g., JSON or XML) and must strictly follow requirements from energy-sector regulatory bodies. To address this problem, we propose POTracker, an optimized LLM for power outage report generation. We fine-tune Qwen2.5-7B-Instruct using our proposed objective. The key contribution is a new loss function, POTrackerLoss, that considers both textual similarity and structural (tag) similarity between the generated report and the ground-truth report. We evaluate POTracker on a dataset of 1,000 power outage reports and compare it with five well-known fine-tuning methods and one rule-based XML conversion method. Results show that POTracker outperforms other fine-tuning approaches, improving overall accuracy by up to 51% and reaching 86.47% structural accuracy for generated power outage reports. In addition, we conduct a human study to assess the quality of the ground-truth standard reports, where domain experts assign the generated labels an average score of 4.03 on a 0--5 scale.

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.