AINeutralarXiv – CS AI · Jun 26/10
🧠Researchers introduce Banyan, a benchmark for studying continual reinforcement learning that reveals task diversity improves immediate transfer between tasks but fails to sustain learning across multiple distribution shifts. While agents trained on diverse tasks generalize well to new task distributions, they forget earlier tasks and struggle with longer-horizon objectives as training continues.
AINeutralarXiv – CS AI · Jun 26/10
🧠Researchers introduce AdvCL, a novel framework that repurposes adversarial perturbations to improve continual learning in large language models by addressing forgetting, limited transfer, and adversarial vulnerability. The approach combines three modules—Intra-Smooth, Proto-Clip, and Inter-Align—to provide geometric control signals that stabilize model adaptation across sequential tasks while maintaining robustness.
AINeutralarXiv – CS AI · Jun 26/10
🧠Researchers propose Palimpsa, a self-attention model that frames in-context learning as a continual learning problem using Bayesian metaplasticity to overcome memory interference in long sequences. The framework unifies existing gated linear attention models as special cases and demonstrates improved performance on associative recall and reasoning tasks, offering a theoretical foundation for enhancing memory capacity in transformer-based architectures.
AINeutralarXiv – CS AI · Jun 26/10
🧠Researchers introduce EvoBrain, a continual learning framework that enables EEG foundation models to adapt across multiple brain-computer interface tasks without catastrophic forgetting. The system uses neural-spectral normalization and distillation techniques to balance learning new tasks while retaining knowledge from previous ones, advancing toward unified brain decoding systems.
AINeutralarXiv – CS AI · Jun 26/10
🧠Researchers introduce AgentCL, an evaluation framework for assessing continual learning in language agents, along with MemProbe, a memory design method that helps agents accumulate and reuse knowledge across tasks while avoiding interference. The framework uses controlled task streams to rigorously measure how well agents learn and transfer knowledge over time, revealing that current memory designs struggle to balance learning plasticity with stable knowledge reuse.
AINeutralarXiv – CS AI · Jun 26/10
🧠Researchers propose ReCAP, a continual learning framework that enables portfolio management systems to adapt to non-stationary financial markets by detecting regime shifts and maintaining a library of adaptive trading policies. The approach combines regime detection with selective policy updates to improve returns while reducing computational overhead compared to traditional retraining methods.
AINeutralarXiv – CS AI · Jun 16/10
🧠Researchers introduce Dynamic Adapter Routing (DAR), a novel approach to continual multimodal retrieval that moves beyond traditional class-incremental learning methods. The study presents a new evaluation framework for vision-language models that better captures real-world retrieval dynamics, with DAR demonstrating superior performance and strong generalization capabilities.
AINeutralarXiv – CS AI · Jun 16/10
🧠Researchers identify that deep neural networks lose plasticity during continual learning due to Hessian spectral collapse, where curvature information vanishes and prevents gradient-based optimization. The study proposes regularization techniques combining high effective feature rank maintenance and L2 penalties to preserve learning capacity across sequential tasks.
AINeutralarXiv – CS AI · May 296/10
🧠Researchers introduce XXLTraffic and EvoXXLTraffic, new datasets spanning 27 years of California and Australian traffic sensor data that account for real-world network growth. Unlike existing benchmarks assuming fixed sensor networks, these datasets expose the challenge of forecasting across dynamically evolving road infrastructure with sensor growth rates exceeding 10,000%, and reveal that current state-of-the-art models fail to generalize under such conditions.
AINeutralarXiv – CS AI · May 296/10
🧠TIMEGATE is a new policy framework that optimizes machine learning system adaptation by intelligently managing computational budgets across training, labeling, and evaluation cycles. The research demonstrates 2.3x efficiency gains in labeling versus training and achieves 66% evaluation-compute savings without compromising model accuracy, with validated results across tabular data and large language models like LLaMA-3.1-8B.
AINeutralarXiv – CS AI · May 286/10
🧠Researchers introduce PEAM, a parametric memory framework for AI agents in Minecraft that consolidates learned skills directly into model parameters rather than relying on retrieval-based memory. The system uses a mixture-of-experts architecture with contrastive learning to internalize both successful and failed experiences, achieving better long-horizon task performance while avoiding catastrophic forgetting.
AINeutralarXiv – CS AI · May 286/10
🧠Researchers introduce Continual Model Routing (CMR), a framework addressing the challenge of efficiently selecting from thousands of pre-trained models in expanding AI hubs. They present CMRBench, a large-scale benchmark with over 2,000 candidate models, and CARvE, a contrastive embedding method that outperforms existing routing strategies as model repositories grow.
AINeutralarXiv – CS AI · May 286/10
🧠Researchers propose Architecture-driven Shift (ADS), a lightweight computational method to predict how pre-trained neural networks will perform in continual learning scenarios by measuring logit shift without expensive calculations. The approach theoretically decouples architecture characteristics from data dependency, achieving strong correlation with actual performance across 175+ diverse model architectures.
AINeutralarXiv – CS AI · May 286/10
🧠Researchers propose E²-LoRA, a novel continual learning method that addresses task interference by concentrating knowledge into low-rank representations rather than spreading it across multiple basis vectors. The approach theoretically proves that preserving parameters along principal drift directions minimizes reconstruction error while freeing model capacity for future tasks.
AINeutralarXiv – CS AI · May 286/10
🧠Researchers demonstrate that reinforcement learning can synthesize novel compositional reasoning skills, but only when models first master independent atomic skills through supervised fine-tuning. Using a controlled synthetic dataset, they show SFT alone produces memorization without generalization, while RL bridges the gap to genuine skill integration when prerequisites are met.
AINeutralarXiv – CS AI · May 286/10
🧠Researchers introduce SAME, a new approach for training Multimodal Large Language Models that can continuously learn new tasks without forgetting previous capabilities. The method addresses fundamental problems in continual learning by stabilizing how AI systems route tasks to specialized expert networks and preventing knowledge degradation over time.
AINeutralarXiv – CS AI · May 276/10
🧠Researchers propose HyperCRL, a continual learning method for model-based reinforcement learning that uses task-conditional hypernetworks to efficiently learn dynamics models across sequential tasks without retraining on historical data. The approach maintains fixed-capacity networks while achieving competitive performance with methods that store growing amounts of past experience, enabling faster training cycles critical for long-horizon robot learning applications.
AINeutralarXiv – CS AI · May 126/10
🧠Researchers identify capability erosion in self-evolving LLM agents, where systems adapting to new tasks progressively lose previously learned abilities across workflow, skill, model, and memory dimensions. The study proposes Capability-Preserving Evolution (CPE), a stabilization framework that maintains performance on existing tasks while enabling new adaptations, demonstrating improvements in retained capability stability across all evolution channels.
🧠 GPT-5
AINeutralarXiv – CS AI · May 126/10
🧠MAGE introduces a novel framework for self-evolving language model agents that uses co-evolutionary knowledge graphs to preserve learned knowledge across iterations without modifying the base model. The system externalizes learning into structured memory subgraphs, enabling frozen backbone models to improve through retrieved guidance while maintaining inference stability across nine diverse benchmarks.
AINeutralarXiv – CS AI · May 126/10
🧠Researchers introduced PrimeKG-CL, a benchmark dataset for continual graph learning built from nine biomedical databases with 129K+ nodes and 8.1M+ edges across two temporal snapshots (2021-2023). The work evaluates how different machine learning strategies handle evolving biomedical knowledge graphs, revealing that decoder choice and learning strategy interact significantly and that standard metrics fail to distinguish between retaining valid facts and forgetting outdated ones.
🏢 Hugging Face
AINeutralarXiv – CS AI · May 125/10
🧠Researchers demonstrate that preserving API request/response trajectories during continual learning significantly improves tool-use performance in language models. Fine-tuning Llama 3.1 8B on sequential API domains shows trajectory supervision achieves 56.9% accuracy versus 39.2% without intermediate context, though at a 25.1% token cost increase.
🧠 Llama
AINeutralarXiv – CS AI · May 126/10
🧠Researchers introduce UFO, a framework addressing robust continual graph learning by simultaneously tackling catastrophic forgetting and noisy data supervision in evolving graphs. The method uses flow-based generative modeling to mitigate forgetting and instance-level reliability scoring to handle corrupted labels, demonstrating superior performance across benchmark datasets.
AINeutralarXiv – CS AI · May 96/10
🧠Researchers introduce HEDP, a domain incremental learning framework that enables AI models to adapt to new data domains without retraining by combining energy-based regularization with distance-based weighting mechanisms. The approach demonstrates a 2.57% accuracy improvement on unseen domains while reducing catastrophic forgetting, addressing a critical challenge in continuous learning systems.
AINeutralarXiv – CS AI · May 96/10
🧠Researchers introduce ICU-Bench, a new benchmark for testing machine unlearning in multimodal AI models, addressing privacy concerns from large-scale training datasets. The benchmark reveals that current unlearning methods struggle with continuous privacy deletion requests, highlighting a critical gap between theoretical approaches and real-world deployment needs.
AINeutralarXiv – CS AI · May 96/10
🧠A new research paper identifies implicit reward overfitting in Reinforcement Learning with Verifiable Rewards (RLVR), revealing that model improvements concentrate in rank-1 components while potentially sacrificing broader knowledge retention. The findings suggest RLVR optimizes singular spectrum distributions rather than general reasoning, with implications for improving AI training paradigms and continual learning approaches.
