arXiv:2510.23682v1 Announce Type: new 
Abstract: Large language models show promise as autonomous decision-making agents, yet their deployment in high-stakes domains remains fraught with risk. Without architectural safeguards, LLM agents exhibit catastrophic brittleness: identical capabilities produce wildly different outcomes depending solely on prompt framing. We present Chimera, a neuro-symbolic-causal architecture that integrates three complementary components - an LLM strategist, a formally verified symbolic constraint engine, and a causal inference module for counterfactual reasoning. We benchmark Chimera against baseline architectures (LLM-only, LLM with symbolic constraints) across 52-week simulations in a realistic e-commerce environment featuring price elasticity, trust dynamics, and seasonal demand. Under organizational biases toward either volume or margin optimization, LLM-only agents fail catastrophically (total loss of \$99K in volume scenarios) or destroy brand trust (-48.6% in margin scenarios). Adding symbolic constraints prevents disasters but achieves only 43-87% of Chimera's profit. Chimera consistently delivers the highest returns (\$1.52M and \$1.96M respectively, some cases +\$2.2M) while improving brand trust (+1.8% and +10.8%, some cases +20.86%), demonstrating prompt-agnostic robustness. Our TLA+ formal verification proves zero constraint violations across all scenarios. These results establish that architectural design not prompt engineering determines the reliability of autonomous agents in production environments. We provide open-source implementations and interactive demonstrations for reproducibility.

يتم تقديم بنية جديدة تُدعى Chimera لتحسين موثوقية نماذج اللغة الكبيرة (LLMs) في أدوار اتخاذ القرار. يجمع هذا الإطار العصبي الرمزي السببي بين مكونات مختلفة لمعالجة التناقضات التي تنشأ من صياغة المطالبات، مما قد يؤدي إلى نتائج غير متوقعة. من خلال تحسين متانة وكلاء الذكاء الاصطناعي، فإن هذا التطور مهم لأنه يفتح الباب لتطبيقات أكثر أمانًا للذكاء الاصطناعي في المجالات الحرجة، مما يضمن أن هذه التقنيات يمكن الوثوق بها في البيئات ذات المخاطر العالية.

Se presenta una nueva arquitectura llamada Chimera para mejorar la fiabilidad de los grandes modelos de lenguaje (LLM) en roles de toma de decisiones. Este marco neuro-simbólico-causal combina varios componentes para abordar las inconsistencias que surgen del enmarcado de las indicaciones, lo que puede llevar a resultados impredecibles. Al mejorar la robustez de los agentes de IA, este desarrollo es significativo ya que abre la puerta a aplicaciones más seguras de la IA en áreas críticas, asegurando que estas tecnologías puedan ser confiables en entornos de alto riesgo.

Une nouvelle architecture appelée Chimera est présentée pour améliorer la fiabilité des grands modèles de langage (LLM) dans les rôles de prise de décision. Ce cadre neuro-symbolique-causal combine divers composants pour résoudre les incohérences qui résultent du cadrage des invites, ce qui peut entraîner des résultats imprévisibles. En améliorant la robustesse des agents IA, ce développement est important car il ouvre la voie à des applications plus sûres de l'IA dans des domaines critiques, garantissant que ces technologies peuvent être fiables dans des environnements à enjeux élevés.

A new architecture called Chimera is being introduced to enhance the reliability of large language models (LLMs) in decision-making roles. This neuro-symbolic-causal framework combines various components to address the inconsistencies that arise from prompt framing, which can lead to unpredictable outcomes. By improving the robustness of AI agents, this development is significant as it opens the door for safer applications of AI in critical areas, ensuring that these technologies can be trusted in high-stakes environments.

Beyond Prompt Engineering: Neuro-Symbolic-Causal Architecture for Robust Multi-Objective AI 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

Beyond Prompt Engineering: Neuro-Symbolic-Causal Architecture for Robust Multi-Objective AI Agents

Was this article worth reading? Share it

One More Thing in AI

LucidQuery AI

Chattermate

Magicley AI

Legion AI

ChatOne

Ready to build your own newsroom?