AIBullisharXiv – CS AI · Jun 97/10
🧠Researchers present Multi-Agent Reflexion (MAR), a technique that improves LLM reasoning by using multiple AI agents with distinct personas to debate and generate diverse reflections rather than having a single model reflect on itself. The approach achieves 47% accuracy on HotPotQA and 82.7% on HumanEval, outperforming traditional single-agent reflection methods that suffer from repetitive error patterns.
AIBullisharXiv – CS AI · May 297/10
🧠Researchers demonstrate that aggregating complete reasoning traces from multiple LLM agents recovers correct solutions more effectively than majority voting, even when agents unanimously agree. A new approach called Self-Consistent Mixture of Agents uses semantic-preserving perturbations to generate trace diversity while maintaining safety guarantees, outperforming heterogeneous model ensembles across mathematical and scientific reasoning tasks.
AIBullisharXiv – CS AI · May 127/10
🧠Researchers introduce SciAidanBench, a benchmark revealing that LLM capability improvements are uneven across tasks and domains—a phenomenon termed 'jaggedness.' By evaluating 19 models across 8 providers, they demonstrate that stronger models don't uniformly excel at scientific creativity, but this fragmentation can be leveraged through ensemble methods to achieve superior performance.
AIBullisharXiv – CS AI · Apr 157/10
🧠CascadeDebate introduces a novel multi-agent deliberation system for large language model cascades that dynamically allocates computational resources based on query difficulty. By inserting lightweight agent ensembles at escalation boundaries to resolve ambiguous cases internally, the system achieves up to 26.75% performance improvement while reducing unnecessary escalations to expensive models.
AIBullisharXiv – CS AI · Apr 77/10
🧠Researchers developed StableTTA, a training-free method that significantly improves AI model accuracy on ImageNet-1K, with 33 models achieving over 95% accuracy and several surpassing 96%. The method allows lightweight architectures to outperform Vision Transformers while using 95% fewer parameters and 89% less computational cost.
AINeutralarXiv – CS AI · Mar 177/10
🧠Research comparing 200 humans and 95 AI detectors found humans significantly outperform AI at detecting deepfakes, especially in low-quality mobile phone videos where AI accuracy drops to near chance levels. The study reveals human-AI hybrid systems are most effective, as humans and AI make complementary errors in deepfake detection.
AINeutralarXiv – CS AI · Mar 47/105
🧠Researchers introduce Federated Inference (FI), a new collaborative paradigm where independently trained AI models can work together at inference time without sharing data or model parameters. The study identifies key requirements including privacy preservation and performance gains, while highlighting system-level challenges that differ from traditional federated learning approaches.
AINeutralarXiv – CS AI · Jun 256/10
🧠ESTANet proposes a lightweight deep learning framework for real-time error detection in procedural videos by exploiting prediction inconsistencies among multiple action detectors with varying sensitivities. The system achieves state-of-the-art performance on multiple datasets while maintaining computational efficiency, demonstrating that leveraging inherent detector properties can solve complex vision tasks without architectural complexity.
AINeutralarXiv – CS AI · Jun 235/10
🧠Researchers developed and compared machine learning models to automatically classify cryopathy syndromes from laboratory data, addressing clinical challenges caused by overlapping diagnostic patterns and rare diagnoses. A soft-voting ensemble combining Random Forest and Gradient Boosted Trees achieved the best performance, with tree-based methods substantially outperforming neural networks for this medical classification task.
AINeutralarXiv – CS AI · Jun 236/10
🧠Researchers propose SAFER, a training-free framework that enhances the robustness of test-time adaptation (TTA) methods against adversarial attacks on contaminated data streams. The method uses stochastic augmentation and reliability-guided prediction pooling to maintain performance while mitigating domain shift without requiring source data access.
AINeutralarXiv – CS AI · Jun 236/10
🧠Researchers propose an adaptive Mixture-of-Experts framework combining EfficientNet-B0, DenseNet-121, and Swin-Tiny for plant leaf disease classification, achieving 91.68% recall on imbalanced potato leaf datasets. The soft routing mechanism dynamically assigns expert weights to capture multi-scale features, demonstrating superior performance over single-architecture models and strong cross-dataset generalization on durian and sesame leaf diseases.
AIBullisharXiv – CS AI · Jun 196/10
🧠Researchers developed an ensemble machine learning approach using Google's Gemini and Gemma large language models to automatically identify EQ-5D health quality-of-life studies in PubMed abstracts. The combined model achieved 0.74 F1-score and accuracy, demonstrating that ensemble methods outperform individual LLMs for biomedical document classification tasks.
🧠 Gemini
AINeutralarXiv – CS AI · Jun 196/10
🧠Researchers demonstrate that using multiple decompilers (Ghidra and RetDec) with large language models improves malware classification accuracy compared to single-decompiler approaches. By providing complementary pseudo-C views of the same binary, the multi-view strategy increases recall on malicious samples without requiring additional training, offering a practical enhancement for LLM-based malware triage.
AIBullisharXiv – CS AI · Jun 116/10
🧠Researchers developed MSUE, a multi-expert question-answering system that achieved 0.95 accuracy in the 2026 SoccerNet VQA Challenge by combining vision-language models, large language models, and specialized experts. The solution uses an LLM router to dynamically dispatch questions to text, image, and video processing experts, demonstrating advances in multi-modal AI for domain-specific tasks.
AINeutralarXiv – CS AI · Jun 105/10
🧠Researchers demonstrate a divide-and-conquer approach to the CTF-4-Science Lorenz benchmark, a challenging test of chaotic system prediction. Rather than using a single model architecture, they match specialized techniques to specific prediction tasks, achieving a score of 79.63 and demonstrating that targeted, scenario-specific modeling outperforms generalized approaches on mixed forecasting problems.
AINeutralarXiv – CS AI · Jun 106/10
🧠Researchers propose Causal Ensemble Agent (CEA), a framework that combines multiple causal discovery algorithms with LLM-guided expert reweighting to improve accuracy in identifying causal relationships from data. The approach addresses limitations of existing methods by dynamically weighting statistical insights and leveraging domain knowledge, demonstrating superior performance across synthetic and real-world datasets.
AINeutralarXiv – CS AI · Jun 96/10
🧠Researchers propose a hybrid machine learning architecture combining FT-Transformer neural networks with XGBoost gradient boosting to predict customer churn in banking and subscription services. The ensemble method achieves superior performance metrics (62.10% F1, 0.861 AUC-ROC) compared to baseline models while addressing critical challenges in class imbalance and probability calibration.
AINeutralarXiv – CS AI · Jun 95/10
🧠Researchers introduce IDS-Anta++, an enhanced machine learning framework that defends intrusion detection systems against adversarial attacks through ensemble learning and multi-layer defensive mechanisms. The system achieves over 99% detection accuracy on clean data while demonstrating improved robustness against sophisticated attacks like FGSM and ZOO on standard cybersecurity datasets.
AINeutralarXiv – CS AI · Jun 55/10
🧠Researchers propose FRAP (Fused Reference Alignment Prediction), a method that combines a foundation model with a domain-specific base model to improve performance estimation when AI models encounter distribution shifts. By aligning and fusing predictions from both models through calibration, FRAP provides more reliable performance indicators without ground-truth labels.
AINeutralarXiv – CS AI · Jun 56/10
🧠Researchers introduce a severity-aware curriculum learning framework for medical text generation that trains multiple large language models sequentially on cases of increasing complexity, then selects the best response during inference. The approach achieves 90.30% performance on the MAQA dataset, demonstrating that combining progressive training strategies with multi-model ensembles improves medical AI reliability across varying case severities.
AINeutralarXiv – CS AI · Jun 56/10
🧠GuardNet, an ensemble-based detection system using shallow neural networks, demonstrates competitive performance in identifying prompt injection and jailbreak attacks on large language models while operating at 50ms latency suitable for production deployment. Although larger LLMs outperform it on some benchmarks, GuardNet achieves strong results (0.747 AUROC) with significantly lower computational overhead, challenging the assumption that adversarial robustness requires massive model scale.
🧠 Llama
AINeutralarXiv – CS AI · Jun 56/10
🧠Researchers propose MASF, a Multi-Model Adaptive Selection Framework that combines multiple fine-tuned transformer models with automatic evaluation metrics to improve abstractive text summarization quality. The framework achieves a BERTScore of 88.63% on the CNN/DailyMail dataset, outperforming several large language models including GPT3-D2 and Falcon-7b.
AINeutralarXiv – CS AI · Jun 45/10
🧠Researchers developed a metric-aware hybrid forecasting system for the CTF4Science Lorenz challenge that strategically combines multiple specialized models rather than relying on a single approach. The system achieved competitive scores (83.85529) by assigning different predictors to different task metrics: denoisers for trajectory reconstruction, ODE fitting for short-term forecasting, and synthetic libraries for long-time distribution matching.
AINeutralarXiv – CS AI · Jun 45/10
🧠Researchers propose ELFM-DEGDO, an ensemble machine learning model combining differential evolution and gradient descent optimization to improve latent factor analysis on high-dimensional, incomplete data. The dual-optimization approach with adaptive weighting outperforms traditional single-method models, demonstrating practical advantages for handling complex real-world datasets.
AINeutralarXiv – CS AI · Jun 46/10
🧠Researchers propose a variance-gated framework for uncertainty quantification in neural networks that decomposes predictive uncertainty using signal-to-noise ratios rather than traditional additive methods. The approach scales predictions by confidence factors derived from ensembles and reveals potential diversity collapse in committee machines, advancing how machine learning models evaluate per-sample uncertainty for high-risk applications.
