arXiv:2511.01093v1 Announce Type: new 
Abstract: Continual Learning (CL) methods have traditionally focused on mitigating catastrophic forgetting through gradient-based retraining, an approach ill-suited for deployed agents that must adapt in real time. We introduce our Adaptive Teaching and Learning System (ATLAS), a dual-agent architecture that decouples reasoning (Teacher) from execution (Student) and incorporates a persistent learning memory that stores distilled guidance from experience. This informs the orchestration layer, enabling the system to dynamically adjust its operational strategies, such as supervision level or initial plan selection, at inference time. In doing so, ATLAS achieves gradient-free continual learning, shifting the locus of adaptation from model parameters to system-level orchestration. We formulate this as a system-centric paradigm for continual learning, where the objective is adaptive efficiency: maximizing task success while minimizing computational cost through inference-time orchestration rather than parameter updates. Evaluated on Microsoft's ExCyTIn-Bench, an open-source benchmark simulating complex cyberthreat investigation, ATLAS achieves 54.1% success with GPT-5-mini as its Student, outperforming the larger GPT-5 (High) by 13% while reducing cost by 86%. Cross-incident validation demonstrates generalization: frozen pamphlets from Incident #5 improve accuracy from 28% to 41% with zero retraining, while shifting output composition from verbose exploration to structured reasoning. Together, these findings establish gradient-free continual learning as a viable path toward adaptive, deployable AI systems and provide causally annotated traces valuable for training explicit world models.

يتم تقديم نهج جديد للتعلم المستمر (CL) مع نظام التعليم والتعلم التكيفي (ATLAS)، الذي يفصل بين التفكير والتنفيذ في الوكلاء. تتيح هذه البنية المزدوجة الوكلاء التكيف في الوقت الحقيقي، مما يعالج قيود طرق التدريب التقليدية التي غالبًا ما تؤدي إلى النسيان الكارثي. من خلال دمج ذاكرة تعلم مستمرة، يعزز ATLAS قدرة الوكلاء على التعلم من التجارب، مما يمثل تقدمًا كبيرًا في مجال الذكاء الاصطناعي.

Se presenta un nuevo enfoque para el Aprendizaje Continu (CL) con el Sistema de Enseñanza y Aprendizaje Adaptativo (ATLAS), que separa el razonamiento de la ejecución en los agentes. Esta innovadora arquitectura de doble agente permite la adaptación en tiempo real, abordando las limitaciones de los métodos de entrenamiento tradicionales que a menudo conducen al olvido catastrófico. Al incorporar una memoria de aprendizaje persistente, ATLAS mejora la capacidad de los agentes para aprender de las experiencias, lo que representa un avance significativo en el campo de la inteligencia artificial.

Une nouvelle approche de l'apprentissage continu (CL) est introduite avec le système d'enseignement et d'apprentissage adaptatif (ATLAS), qui sépare le raisonnement de l'exécution chez les agents. Cette architecture à double agent permet une adaptation en temps réel, répondant aux limites des méthodes de formation traditionnelles qui entraînent souvent un oubli catastrophique. En intégrant une mémoire d'apprentissage persistante, ATLAS améliore la capacité des agents à apprendre de leurs expériences, ce qui constitue une avancée significative dans le domaine de l'intelligence artificielle.

A new approach to Continual Learning (CL) is being introduced with the Adaptive Teaching and Learning System (ATLAS), which separates reasoning from execution in agents. This innovative dual-agent architecture allows for real-time adaptation, addressing the limitations of traditional training methods that often lead to catastrophic forgetting. By incorporating a persistent learning memory, ATLAS enhances the ability of agents to learn from experiences, making it a significant advancement in the field of artificial intelligence.

Continual Learning, Not Training: Online Adaptation For Agents

arXiv:2411.00365v2 Announce Type: replace 
Abstract: In the paradigm of decentralized learning, a group of agents collaborate to learn a global model using a distributed dataset without a central server; nevertheless, it is severely challenged by the heterogeneity of the data distribution across the agents. For example, the data may be distributed non-independently and identically, and even be noised or poisoned. To address these data challenges, we propose ROSS, a novel robust decentralized stochastic learning algorithm based on Shapley values, in this paper. Specifically, in each round, each agent aggregates the cross-gradient information from its neighbors, i.e., the derivatives of its local model with respect to the datasets of its neighbors, to update its local model in a momentum like manner, while we innovate in weighting the derivatives according to their contributions measured by Shapley values. We perform solid theoretical analysis to reveal the linear convergence speedup of our ROSS algorithm. We also verify the efficacy of our algorithm through extensive experiments on public datasets. Our results demonstrate that, in face of the above variety of data challenges, our ROSS algorithm has significant advantages over existing state-of-the-art proposals in terms of both convergence and prediction accuracy.

تم اقتراح خوارزمية جديدة للتعلم اللامركزي تُدعى ROSS، والتي تستخدم قيم شابلي لتعزيز قوة التعلم العشوائي بين الوكلاء. تتناول هذه الطريقة التحديات التي تطرحها توزيعات البيانات غير المتجانسة، مما يسمح للوكلاء بتعلم نموذج عالمي بشكل تعاوني دون الحاجة إلى خادم مركزي. يقوم كل وكيل بتحديث نموذجه من خلال تجميع معلومات التدرج المتقاطع من الوكلاء المجاورين، مع وزنها وفقًا لمساهماتهم.

Se ha propuesto un nuevo algoritmo de aprendizaje descentralizado llamado ROSS, que utiliza valores de Shapley para mejorar la robustez del aprendizaje estocástico entre agentes. Este enfoque aborda los desafíos planteados por las distribuciones de datos heterogéneas, permitiendo que los agentes aprendan de manera colaborativa un modelo global sin un servidor central. Cada agente actualiza su modelo agregando información de gradiente cruzado de los agentes vecinos, ponderada por sus contribuciones.

Un nouvel algorithme d'apprentissage décentralisé nommé ROSS a été proposé, utilisant les valeurs de Shapley pour améliorer la robustesse de l'apprentissage stochastique parmi les agents. Cette approche répond aux défis posés par les distributions de données hétérogènes, permettant aux agents d'apprendre de manière collaborative un modèle global sans serveur central. Chaque agent met à jour son modèle en agrégeant des informations de gradient croisé provenant des agents voisins, pondérées par leurs contributions.

A new decentralized learning algorithm named ROSS has been proposed, which utilizes Shapley values to enhance the robustness of stochastic learning among agents. This approach addresses challenges posed by heterogeneous data distributions, allowing agents to collaboratively learn a global model without a central server. Each agent updates its model by aggregating cross-gradient information from neighboring agents, weighted by their contributions.

ROSS: RObust decentralized Stochastic learning based on Shapley values

One More Thing in AI – Your Shortcut to AI Mastery

Continual Learning, Not Training: Online Adaptation For Agents

Was this article worth reading? Share it

One More Thing in AI

LucidQuery AI

Chattermate

Cogent

AIvilization

Legion AI

Ready to build your own newsroom?