Architecture papers

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

38 papers found

ReviewPaperPublishedTopics

7.2Chronicle: A Multimodal Foundation Model for Joint Language and Time Series UnderstandingThis work is significant for AI researchers interested in developing models that can seamlessly integrate and process multimodal data, potentially leading to more robust and versatile AI systems.May 22, 2026Multimodal Architecture Evaluation

6.8Agentic Physical AI toward a Domain-Specific Foundation Model for Nuclear Reactor ControlThis work is relevant for AI engineers and researchers interested in developing reliable AI systems for safety-critical applications like nuclear reactor control.May 22, 2026Agent Safety Architecture

7.5JoyAI-Image: Awaking Spatial Intelligence in Unified Multimodal Understanding and GenerationThis research could significantly improve applications in vision-language-action systems, making it relevant for engineers and researchers working on multimodal AI.May 22, 2026Multimodal Vision Language Architecture

7.5Governance by Design: Architecting Agentic AI for Organizational Learning and Scalable AutonomyAs organizations increasingly deploy agentic AI systems, understanding governance mechanisms is crucial for ensuring accountability and safety while achieving scalable autonomy.May 22, 2026Agent Architecture Other

7.0ARM: Discovering Agentic Reasoning Modules for Generalizable Multi-Agent SystemsThis approach could streamline the design of multi-agent systems, reducing the need for manual engineering and improving performance across diverse tasks and models.May 21, 2026LLM Agent Reasoning

6.8A Methodology for Selecting and Composing Runtime Architecture Patterns for Production LLM AgentsUnderstanding and optimizing the integration of stochastic LLM outputs with deterministic systems is crucial for improving the reliability and efficiency of production AI systems.May 21, 2026LLM Agent Architecture

7.5Multi-Paradigm Agent Interaction in Practice:A Systematic Analysis of Generator-Evaluator, ReAct Loop,and Adversarial Evaluation in the buddyMe FrameworkThis research provides practical design guidelines for developing stable and reliable multi-paradigm agent systems, which is crucial as LLM agents become more integrated into real-world applications.May 19, 2026LLM Agent Evaluation

6.8Position: A Three-Layer Probabilistic Assume-Guarantee Architecture Is Structurally Required for Safe LLM Agent DeploymentEnsuring the safety of LLM agents is crucial for their reliable deployment in real-world applications, and this paper proposes a structured approach to address this challenge.May 19, 2026LLM Agent Safety

7.2Context, Reasoning, and Hierarchy: A Cost-Performance Study of Compound LLM Agent Design in an Adversarial POMDPUnderstanding cost-effective design choices for LLM agents in complex environments can guide practitioners in developing more efficient and effective AI systems.May 18, 2026LLM Agent Reasoning

7.5Seeing is Understanding: Unlocking Causal Attention into Modality-Mutual Attention for Multimodal LLMsThis work addresses a critical challenge in multimodal AI, potentially improving the accuracy and relevance of model outputs in applications that integrate text and images.May 18, 2026Multimodal Vision Language Alignment

7.2Brain-OF: An Omnifunctional Foundation Model for fMRI, EEG and MEGThis work is significant for AI researchers and engineers interested in neuroscience as it offers a unified model for integrating multiple neuroimaging modalities, potentially leading to more comprehensive brain activity analysis.May 18, 2026Multimodal Architecture Other

7.5Towards Foundation Models for Relational Databases with Language Models and Graph Neural NetworksThis work addresses a significant gap in deep learning for relational data, potentially improving predictive applications that rely on structured information.May 18, 2026Architecture Benchmark

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.May 16, 2026LLM Agent Reasoning

7.5Beyond Autonomy: A Dynamic Tiered AgentRunner Framework for Governable and Resilient Enterprise AI ExecutionThis work addresses critical gaps in current AI frameworks by enhancing safety and efficiency, making it relevant for enterprises looking to deploy AI responsibly.May 13, 2026Agent Safety Architecture

7.5Human-Inspired Memory Architecture for LLM AgentsThis research addresses critical limitations in LLM memory management, potentially improving their performance in long-term interactions, which is essential for real-world applications.May 13, 2026LLM Architecture Evaluation

7.2Physics-Grounded Multi-Agent Architecture for Traceable, Risk-Aware Human-AI Decision Support in ManufacturingThis work is relevant for AI researchers and engineers focused on manufacturing, as it proposes a structured approach to integrate AI with human decision-making, potentially improving precision and safety in high-stakes environments.May 7, 2026Agent Architecture Safety

6.8Say the Mission, Execute the Swarm: Agent-Enhanced LLM Reasoning in the Web-of-DronesThis research explores the potential of LLMs in real-time UAV swarm management, a growing area of interest in autonomous systems and robotics, highlighting both capabilities and current limitations.May 7, 2026LLM Agent Reasoning

7.5Stable Agentic Control: Tool-Mediated LLM Architecture for Autonomous Cyber DefenseThis research addresses critical needs in cybersecurity by providing a framework that ensures reliable decision-making in high-stakes environments, which is essential for modern security operations.May 7, 2026LLM Agent Security

7.2Ontology-Constrained Neural Reasoning in Enterprise Agentic Systems: A Neurosymbolic Architecture for Domain-Grounded AI AgentsThis work addresses key limitations of LLMs in enterprise settings, such as hallucination and compliance, potentially leading to more reliable and domain-specific AI applications.May 6, 2026LLM Agent Reasoning

6.8Position: Safety and Fairness in Agentic AI Depend on Interaction Topology, Not on Model Scale or AlignmentUnderstanding the role of interaction topology in AI systems can lead to better safety and fairness outcomes, which is crucial for deploying AI in high-stakes environments.May 6, 2026Agent Safety Alignment

7.5A Language for Describing Agentic LLM ContextsStandardizing context representation can enhance communication and understanding among researchers and engineers working with LLMs, potentially improving system design and collaboration.May 6, 2026LLM Agent Architecture

6.5AIs and Humans with AgencyUnderstanding agency in AI is crucial for developing systems that can effectively collaborate with humans in real-world scenarios.May 6, 2026Agent Alignment Architecture

7.2Earth System Foundation Model (ESFM): A unified framework for heterogeneous data integration and forecastingThis work is relevant for AI researchers and engineers focused on climate science, as it provides a versatile tool for integrating and forecasting diverse environmental data, potentially improving predictions of extreme weather events.May 6, 2026Multimodal Data Architecture

7.0ML-Agent: Reinforcing LLM Agents for Autonomous Machine Learning EngineeringThis work could make autonomous ML engineering more accessible by reducing computational costs and enabling smaller models to achieve competitive performance.May 5, 2026LLM Agent Architecture

7.2Disentangled Safety Adapters Enable Efficient Guardrails and Flexible Inference-Time AlignmentAI engineers and researchers should care because DSA provides a method to implement safety measures without significantly impacting performance, offering a balance between safety and task efficiency.May 5, 2026Safety Alignment Architecture

6.8Self-Evolving Software AgentsThis research could lead to more adaptive and autonomous software agents capable of evolving in response to changing environments, which is valuable for dynamic and complex systems.May 1, 2026LLM Agent Reasoning

6.8Deterministic Legal Agents: A Canonical Primitive API for Auditable Reasoning over Temporal Knowledge GraphsThis work is relevant for AI researchers and engineers working on legal AI systems, as it offers a method to enhance the reliability and auditability of reasoning processes over complex temporal data.Apr 30, 2026LLM Agent Reasoning

7.0Structural Enforcement of Goal Integrity in AI Agents via Separation-of-Powers ArchitectureEnsuring goal integrity in AI agents is crucial for preventing harmful actions and improving the safety and reliability of autonomous systems.Apr 29, 2026Agent Alignment Safety

6.8Towards Automated Ontology Generation from Unstructured Text: A Multi-Agent LLM ApproachAutomating ontology generation can significantly streamline knowledge engineering processes, making it crucial for AI researchers and engineers focused on improving data organization and retrieval systems.Apr 29, 2026LLM Agent Architecture

7.2Analytica: Soft Propositional Reasoning for Robust and Scalable LLM-Driven AnalysisImproving the reasoning capabilities of LLMs in complex analysis tasks can significantly enhance their applicability and reliability in real-world scenarios, such as financial forecasting and scientific discovery.Apr 29, 2026LLM Agent Reasoning

6.8Focus Session: Hardware and Software Techniques for Accelerating Multimodal Foundation ModelsThis work is relevant for AI engineers and researchers looking to improve the efficiency and performance of multimodal foundation models, which are increasingly used in diverse applications.Apr 27, 2026Multimodal Infra Architecture

7.2Sovereign Agentic Loops: Decoupling AI Reasoning from Execution in Real-World SystemsThis work is crucial for AI engineers and researchers focused on deploying AI systems safely, as it addresses the risk of unsafe executions by ensuring that AI intents are validated before affecting real-world systems.Apr 27, 2026LLM Agent Safety

7.5Reasoning Primitives in Hybrid and Non-Hybrid LLMsUnderstanding the underlying mechanisms of reasoning in LLMs can lead to improved model architectures and better performance on complex tasks.Apr 24, 2026LLM Reasoning Architecture

7.5Separable Pathways for Causal Reasoning: How Architectural Scaffolding Enables Hypothesis-Space Restructuring in LLM AgentsUnderstanding how to improve causal reasoning in AI agents is crucial for developing more robust problem-solving capabilities in real-world applications.Apr 23, 2026LLM Agent Reasoning

7.5Automatic Ontology Construction Using LLMs as an External Layer of Memory, Verification, and Planning for Hybrid Intelligent SystemsThis work addresses critical limitations in current LLM systems, offering a pathway to more reliable and explainable AI applications in various domains.Apr 23, 2026LLM Reasoning Architecture

7.2Shift-Up: A Framework for Software Engineering Guardrails in AI-native Software Development -- Initial FindingsAs generative AI transforms software engineering, establishing effective frameworks like Shift-Up is crucial for maintaining code quality and project sustainability.Apr 23, 2026Coding Architecture

7.23D Foundation Model for Generalizable Disease Detection in Head Computed TomographyThis research demonstrates the potential of self-supervised learning to improve medical imaging diagnostics, reducing the need for annotated data and potentially enhancing early disease detection in clinical settings.Apr 22, 2026Vision Language Data Architecture

7.5The cognitive companion: a lightweight parallel monitoring architecture for detecting and recovering from reasoning degradation in LLM agentsThis research addresses a critical issue in LLM performance, providing insights that could enhance the reliability of AI systems in complex tasks.Apr 17, 2026LLM Agent Reasoning