Architecture papers

Browse recent papers, open the full write-up, or filter the archive by topic.

96 papers found

ReviewPaperPublishedTopics

6.8Toward an Organizational Science of Multi-Agent LLM Systems: Decoupling Who, How, and Which AlgorithmThis work is relevant for AI researchers and engineers interested in optimizing multi-agent systems by allowing flexible and adaptive configurations that can improve performance and efficiency.Jul 29, 2026LLM Agent Architecture

6.8MODUS: Decoder-Only Any-to-Any Modeling of Diverse ModalitiesThis approach could simplify multimodal model architectures by eliminating the need for modality-specific components, potentially broadening the applicability of pre-trained models.Jul 29, 2026Multimodal Architecture

7.2Risk Governance for Generative AI Mental Health Support: A Multi-Turn Safety ArchitectureThis work is crucial for deploying LLMs in sensitive areas like mental health, ensuring safer and more effective interactions.Jul 28, 2026LLM Safety Architecture

7.2Scaling Native Multimodal Pre-Training From ScratchUnderstanding the scaling properties of multimodal models can lead to more efficient resource allocation and improved model performance, which is crucial for advancing AI capabilities in processing diverse data types.Jul 27, 2026Multimodal Vision Language Architecture

6.8Autoregressive EHR Foundation Models with Multimodal InputsThis research is relevant for AI engineers and researchers focused on improving clinical prediction models by effectively utilizing diverse data types from electronic health records.Jul 27, 2026Multimodal Architecture

7.2Multimodal Pretraining for Generalizable EEG Representation LearningThis work is significant for AI researchers and engineers interested in EEG analysis, as it offers a generalizable model that can adapt to various seizure detection scenarios without requiring extensive labeled data.Jul 24, 2026Multimodal Architecture Interpretability

7.2Operational Hallucination and Safety Drift in AI AgentsUnderstanding and mitigating reliability risks in AI agents is crucial for safe deployment in real-world applications, especially in high-stakes scenarios.Jul 22, 2026LLM Agent Safety

7.0Reward-Driven LLM Agent Workflows: Synthesizing POMDP Routing and Self-Correction for Autonomous Decision-MakingThis research could enhance the autonomy and efficiency of AI agents in complex environments, which is crucial for developing more capable and reliable AI systems.Jul 21, 2026LLM Agent Reasoning

7.2Agentic ERP: Multi-Agent Large Language Model Architecture for Autonomous Enterprise Resource PlanningThis work is relevant for AI researchers and engineers interested in applying LLMs to automate complex enterprise systems, potentially reducing human workload and improving operational efficiency.Jul 21, 2026LLM Agent Architecture

6.8How Do You Choose Your AI Component? An Interview Study of Secure AI Integration in PracticeAI engineers and researchers should care because overlooking security in AI component integration can lead to vulnerabilities, repeating past mistakes in software dependency management.Jul 21, 2026Security Survey Architecture

6.8LLMs and Agentic AI Systems for Smart Grids: A Tutorial on Architectures and ApplicationsThis work is relevant for AI researchers and engineers interested in applying LLMs to technical domains like smart grids, offering a structured approach to ensure reliable and accurate outputs.Jul 21, 2026LLM Agent Evaluation

6.8Evidence-Grounded Verified Agentic Reasoning: A Path Toward Eliminating LLM Hallucination in Empirical Inference via Tool-Attested Kernel ProofsThis work is relevant for AI researchers and engineers focused on improving the reliability and trustworthiness of LLM outputs, particularly in high-stakes applications.Jul 15, 2026LLM Reasoning Architecture

7.2A Foundation Model for Multimodal Event Sequences in Financial ApplicationsThis approach could streamline financial predictive modeling by leveraging diverse data sources, potentially leading to more accurate predictions and efficient model development.Jul 14, 2026Multimodal Architecture Data

7.2Neuro-Agentic Control: A Deep Learning-based LLM-Powered Agentic AI Framework for Controlling Security ControlsThis research is relevant for AI engineers and researchers focused on improving the security and reliability of industrial IoT systems using advanced AI techniques.Jul 13, 2026LLM Agent Security

7.2Mixture of Probes: Learning from Privileged Modalities in Multimodal LLMs Through ProbingThis research is relevant for AI engineers and researchers working with multimodal models, as it addresses the challenge of leveraging training-only modalities to improve model performance in real-world applications where all modalities may not be available at inference.Jul 13, 2026LLM Multimodal Vision Language

7.2The LLMbda Calculus: AI Agents, Conversations, and Information FlowThis work is relevant for AI engineers and researchers focused on enhancing the security and reliability of LLM agents, particularly in environments where data provenance and information flow are critical.Jul 13, 2026LLM Agent Security

7.0Collective Intelligence with Foundation ModelsThis research highlights the potential of diverse model coordination to improve AI decision-making, which is crucial for developing reliable and transparent AI systems in complex domains.Jul 11, 2026Agent Reasoning Architecture

6.8From Prompts to Contracts: Harness Engineering for Auditable Enterprise LLM AgentsThis work is relevant for AI engineers and researchers interested in developing reliable and auditable LLM applications for enterprise use, addressing key challenges in productization such as traceability and validation.Jul 11, 2026LLM Agent Architecture

7.2Tool-Making and Self-Evolving LLM Agents in Low-Latency SystemsThis approach can make LLM systems more efficient and reliable, which is crucial for real-time applications in industrial settings.Jul 11, 2026LLM Agent Infra

7.2Decoding the Multimodal Mind: Generalizable Brain-to-Text Translation via Multimodal Alignment and Adaptive RoutingThis research could advance brain-computer interfaces by enabling more accurate and flexible decoding of brain activity across multiple modalities, potentially impacting fields like neuroprosthetics and communication aids.Jul 8, 2026Multimodal Alignment Architecture

6.5Not All Refusals Are Equal: How Safety Alignment Fails Cybersecurity at ScaleUnderstanding how to adjust safety mechanisms in LLMs for specific domains like cybersecurity can enhance their utility and effectiveness in sensitive applications.Jul 8, 2026LLM Security Safety

7.5Beyond Correctness: Enhancing Architectural Reasoning in Code LLMs via Scalable Labeling with Agentic JudgmentThis research addresses a critical gap in software engineering by providing a scalable method for evaluating architectural quality, which is essential for maintaining code quality in real-world applications.Jul 8, 2026LLM Agent Reasoning

6.5Organizational Memory for Agentic Business Process ExecutionThis work is relevant for AI engineers and researchers interested in improving the scalability and consistency of LLM-based business process automation in enterprises.Jul 7, 2026LLM Agent Architecture

7.5Biological Motifs for Agentic ControlUnderstanding and applying biological control motifs could lead to more robust and secure AI systems, addressing critical challenges in the deployment of autonomous agents.Jul 7, 2026Agent Security Architecture

7.0MechMath Agent Team: LLM Driven Agents for Mathematical ResearchThis research could significantly enhance the efficiency and capability of mathematical research by providing a structured AI-driven approach to problem-solving.Jul 7, 2026LLM Agent Reasoning

7.5Human-Centric Reflective Architecture for Human-AI Collaborative Decision-MakingThis research addresses critical challenges in aligning AI recommendations with human expectations, which is essential for effective human-AI collaboration in various applications.Jul 7, 2026Agent Alignment Architecture

6.8Risk Architecture for AI-Native Engineering Teams: An Organizational Framework for Agentic System GovernanceAI engineers and researchers need effective risk management frameworks to handle the unique challenges of agentic AI systems, which differ significantly from traditional software systems.Jul 3, 2026Architecture Safety Security

6.8Hardware-Enforced Semantic Coordination for Safety-Critical Real-Time Autonomous SystemsThis work addresses the critical need for deterministic coordination and safety guarantees in real-time autonomous systems, which is essential for their reliable deployment in safety-critical environments.Jul 3, 2026Agent Safety Architecture

7.5Criticality-Based Guard Rail Validation for AI Agent Decisions in Autonomous Telecom NetworksAs telecommunications move towards full autonomy, ensuring the reliability and safety of AI decisions is crucial to prevent network failures and maintain compliance with regulations.Jul 3, 2026Agent Security Safety

7.0COOPA: A Modular LLM Agent Architecture for Operations Research ProblemsThis work is relevant for AI researchers and engineers interested in improving decision-making processes in Operations Research through enhanced interpretability and solver flexibility.Jun 29, 2026LLM Agent Architecture

7.2What the LLM Should Not Say: Boundary-Aware Context Grounding for A Seven-Channel EEG AgentThis work addresses the critical issue of misinterpretation in EEG analysis, which can lead to erroneous scientific conclusions, making it relevant for both researchers and practitioners in neuroscience and AI.Jun 29, 2026LLM Agent Evaluation

6.8Governed Shared Memory for Multi-Agent LLM SystemsImproving shared memory management in multi-agent systems is crucial for robust and secure knowledge propagation, which is vital for the development of scalable AI systems.Jun 25, 2026LLM Agent Infra

7.2Cosmos 3: Omnimodal World Models for Physical AIThis work could streamline the development of embodied AI systems by providing a versatile and unified model architecture that handles diverse data types, potentially accelerating advancements in robotics and multimodal AI applications.Jun 25, 2026Multimodal Vision Language Agent

7.2FISHER: A Foundation Model for Multi-Modal Industrial Signal Comprehensive RepresentationThis work is significant for AI engineers and researchers focusing on industrial signal processing, offering a scalable and robust solution to data heterogeneity and sampling rate variability, potentially improving diagnostic accuracy and versatility in industrial applications.Jun 25, 2026Multimodal Benchmark Architecture

7.2ReM-MoA: Reasoning Memory Sustains Mixture-of-Agents ScalingThis work is relevant for AI researchers focused on improving the scalability and efficiency of multi-agent systems, particularly in reasoning tasks.Jun 25, 2026LLM Agent Reasoning

6.8Critique of Agent ModelUnderstanding and defining agency in AI is crucial for developing systems that can operate autonomously and safely in real-world environments.Jun 25, 2026Agent Architecture Safety

6.5Reinforcement Learning Foundation Models Should Already Be A ThingThis work suggests a new direction for reinforcement learning by leveraging synthetic data and attention-based architectures, potentially simplifying the development of RL models.Jun 20, 2026Agent Architecture

6.8LLM-as-Code Agentic Programming for Agent HarnessThis approach could improve the stability and reliability of LLM-based systems, which is crucial for their deployment in real-world applications.Jun 16, 2026LLM Agent Architecture

6.8E-mem: Multi-agent based Episodic Context Reconstruction for LLM Agent MemoryImproving memory handling in LLMs can significantly enhance their reasoning capabilities, making them more effective for complex problem-solving tasks.Jun 16, 2026LLM Agent Reasoning

7.2Architectural Wisdom: A Framework for Governing Optimization in AI SystemsThis work is relevant as it addresses critical failures in AI systems that arise from poorly defined objectives, potentially guiding future designs for more robust and ethical AI.Jun 16, 2026Architecture Alignment Safety

6.8Emerging Flexible Designs for Geospatial Multimodal Foundation ModelsUnderstanding the trade-offs in model architectures for geospatial data can help researchers and practitioners build more effective and flexible models for Earth observation tasks.Jun 12, 2026Multimodal Benchmark Architecture

7.2The Containment Gap: How Deployed Agentic AI Frameworks Fail Public-Facing Safety RequirementsAs agentic AI systems are increasingly used in sensitive public domains, ensuring their safety and reliability is crucial to prevent harmful outcomes.Jun 12, 2026Agent Safety Security

6.8Intelligence as Managed Autonomy: Failure, Escalation, and Governance for Agentic AI SystemsUnderstanding and managing AI system failures is crucial for developing reliable and safe autonomous systems, especially in critical domains like healthcare and robotics.Jun 12, 2026Agent Safety Architecture

7.2Parthenon Law: A Self-Evolving Legal-Agent FrameworkThis framework could significantly improve the efficiency and reliability of legal-domain LLM agents, making them more practical for real-world legal tasks.Jun 12, 2026LLM Agent Architecture

6.8Resource-Aware LLM Reasoning for Mobile Edge General IntelligenceThis work is relevant for AI engineers and researchers interested in deploying sophisticated AI reasoning capabilities on edge devices, where computational resources are limited.Jun 11, 2026LLM Reasoning Infra

6.5Enhancing AI Interpretability and Safety through Localised ArchitecturesAs AI models grow in complexity, improving interpretability and safety is crucial for their adoption in sensitive applications.Jun 10, 2026Interpretability Architecture Safety

6.8Agentic Physical AI toward a Domain-Specific Foundation Model for Energy Systems: A Case Study on Nuclear Reactor ControlThis work is relevant for AI researchers and engineers interested in applying AI to safety-critical systems, offering insights into domain-specific model development and reliability in controlled simulations.Jun 8, 2026Agent Safety Architecture

7.2Ontology-Constrained Neural Reasoning in Enterprise Agentic Systems: A Neurosymbolic Architecture for Domain-Grounded AI AgentsThis work is relevant for AI engineers and researchers focused on improving the reliability and compliance of AI systems in enterprise settings, addressing key limitations of current LLMs.Jun 6, 2026LLM Agent Reasoning

6.8Provably Auditable and Safe LLM Agents from Human-Authored OntologiesThis work is relevant for AI engineers and researchers interested in developing reliable and auditable LLM agents for complex domains, particularly in fields like healthcare and security.Jun 5, 2026LLM Agent Security

7.2Revisiting Model Stitching In the Foundation Model EraUnderstanding how to effectively stitch different VFMs can lead to more efficient and powerful multimodal models, which is crucial for advancing AI capabilities in complex tasks.Jun 5, 2026Multimodal Architecture Vision Language