Osprey: A Scalable Framework for the Orchestration of Agentic Systems

• URL: http://arxiv.org/abs/2508.15066v2
• Date: Tue, 04 Nov 2025 18:32:59 GMT
• Title: Osprey: A Scalable Framework for the Orchestration of Agentic Systems
• Authors: Thorsten Hellert, João Montenegro, Antonin Sulc,
• Abstract summary: Osprey Framework is a production-ready architecture for scalable agentic systems that integrate conversational context with robust tool orchestration across safety-critical domains.<n>Our framework provides: (i) dynamic capability classification to select only relevant tools; (ii) plan-first orchestration with explicit dependencies and optional human approval; and (iii) context-aware task extraction that combines dialogue history with external memory and domain resources.
• Score: 0.4970364068620607
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Coordinating workflows across complex systems remains a central challenge in safety-critical environments such as scientific facilities. Language-model-driven agents offer a natural interface for these tasks, but existing approaches often lack scalability, reliability, and human oversight. We introduce the Osprey Framework, a domain-agnostic, production-ready architecture for scalable agentic systems that integrate conversational context with robust tool orchestration across safety-critical domains. Our framework provides: (i) dynamic capability classification to select only relevant tools; (ii) plan-first orchestration with explicit dependencies and optional human approval; (iii) context-aware task extraction that combines dialogue history with external memory and domain resources; and (iv) production-ready execution with checkpointing, artifact management, and modular deployment. We demonstrate its versatility through two case studies: a deployment at the Advanced Light Source particle accelerator and a tutorial-style wind farm monitoring example. These results establish Osprey as a reliable and transparent framework for agentic systems across diverse high-stakes domains.

Related papers

• The Auton Agentic AI Framework [5.410458076724158]
  The field of Artificial Intelligence is undergoing a transition from Generative AI to Agentic AI.<n>This transition exposes a fundamental architectural mismatch: Large Language Models (LLMs) produce unstructured outputs, whereas the backend infrastructure they must control requires deterministic, schema-conformant inputs.<n>The present paper describes the Auton Agentic AI Framework, a principled architecture for the creation, creation, and governance of autonomous agent.
  arXiv  Detail & Related papers  (2026-02-27T06:42:08Z)
• Just Ask: Curious Code Agents Reveal System Prompts in Frontier LLMs [65.6660735371212]
  We present textbftextscJustAsk, a framework that autonomously discovers effective extraction strategies through interaction alone.<n>It formulates extraction as an online exploration problem, using Upper Confidence Bound--based strategy selection and a hierarchical skill space spanning atomic probes and high-level orchestration.<n>Our results expose system prompts as a critical yet largely unprotected attack surface in modern agent systems.
  arXiv  Detail & Related papers  (2026-01-29T03:53:25Z)
• The Why Behind the Action: Unveiling Internal Drivers via Agentic Attribution [63.61358761489141]
  Large Language Model (LLM)-based agents are widely used in real-world applications such as customer service, web navigation, and software engineering.<n>We propose a novel framework for textbfgeneral agentic attribution, designed to identify the internal factors driving agent actions regardless of the task outcome.<n>We validate our framework across a diverse suite of agentic scenarios, including standard tool use and subtle reliability risks like memory-induced bias.
  arXiv  Detail & Related papers  (2026-01-21T15:22:21Z)
• Formalizing the Safety, Security, and Functional Properties of Agentic AI Systems [10.734711935895225]
  We introduce a modeling framework for agentic AI systems composed of two foundational models.<n>The first, the host agent model, formalizes the top-level entity that interacts with the user, decomposes tasks, and orchestrates their execution by leveraging external agents and tools.<n>The second, the task lifecycle model, details the states and transitions of individual sub-tasks from creation to completion, providing a fine-grained view of task management and error handling.
  arXiv  Detail & Related papers  (2025-10-15T22:02:30Z)
• JoyAgent-JDGenie: Technical Report on the GAIA [27.025464023889853]
  Large Language Models are increasingly deployed as autonomous agents for complex real-world tasks.<n>We propose a generalist agent architecture that integrates planning and execution agents with critic model voting, a hierarchical memory system spanning working, semantic, and procedural layers, and a refined tool suite for search, code execution, and multimodal parsing.
  arXiv  Detail & Related papers  (2025-10-01T04:41:58Z)
• Towards General Agentic Intelligence via Environment Scaling [78.66355092082253]
  Advanced agentic intelligence is a prerequisite for deploying Large Language Models in real-world applications.<n>We design a scalable framework that automatically constructs heterogeneous environments that are fully simulated.<n>Experiments on agentic benchmarks, tau-bench, tau2-Bench, and ACEBench, demonstrate that our trained model, AgentScaler, significantly enhances the function-calling capability of models.
  arXiv  Detail & Related papers  (2025-09-16T17:57:20Z)
• Rethinking Testing for LLM Applications: Characteristics, Challenges, and a Lightweight Interaction Protocol [83.83217247686402]
  Large Language Models (LLMs) have evolved from simple text generators into complex software systems that integrate retrieval augmentation, tool invocation, and multi-turn interactions.<n>Their inherent non-determinism, dynamism, and context dependence pose fundamental challenges for quality assurance.<n>This paper decomposes LLM applications into a three-layer architecture: textbftextitSystem Shell Layer, textbftextitPrompt Orchestration Layer, and textbftextitLLM Inference Core.
  arXiv  Detail & Related papers  (2025-08-28T13:00:28Z)
• AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications [95.42093979627703]
  AgentScope supports flexible and efficient tool-based agent-environment interactions.<n>We ground agent behaviors in the ReAct paradigm and offer advanced agent-level infrastructure.<n>AgentScope also includes robust engineering support for developer-friendly experiences.
  arXiv  Detail & Related papers  (2025-08-22T10:35:56Z)
• A Survey on Agent Workflow -- Status and Future [2.817843718857682]
  This survey provides a comprehensive review of agent workflow systems.<n>We classify existing systems along two key dimensions: functional capabilities and architectural features.<n>We highlight common patterns, potential technical challenges, and emerging trends.
  arXiv  Detail & Related papers  (2025-08-02T04:15:30Z)
• State and Memory is All You Need for Robust and Reliable AI Agents [29.259008600842517]
  Large language models (LLMs) have enabled powerful advances in natural language understanding and generation.<n>Yet their application to complex, real-world scientific remain limited by challenges in memory, planning, and tool integration.<n>Here, we introduce SciBORG, a modular agentic framework that allows LLM-based agents to autonomously plan, reason, and achieve robust and reliable domain-specific task execution.
  arXiv  Detail & Related papers  (2025-06-30T02:02:35Z)
• An Agentic Framework for Autonomous Metamaterial Modeling and Inverse Design [2.66269503676104]
  We develop and demonstrate a framework specifically for the inverse design of photonic metamaterials.<n>The framework's effectiveness is demonstrated in its ability to automate, reason, plan, and adapt.<n> Notably, the Agentic Framework possesses internal reflection and decision flexibility, permitting highly varied and potentially novel outputs.
  arXiv  Detail & Related papers  (2025-06-07T22:10:05Z)
• Control Plane as a Tool: A Scalable Design Pattern for Agentic AI Systems [2.997108944111501]
  This paper conducts a comprehensive review of the types of agents, their modes of interaction with the environment, and the infrastructural and architectural challenges that emerge.<n>We propose a reusable design abstraction: the "Control Plane as a Tool" pattern.<n>This pattern allows developers to expose a single tool interface to an agent while encapsulating modular tool routing logic behind it.
  arXiv  Detail & Related papers  (2025-05-11T02:58:50Z)
• Autonomous Deep Agent [0.7489814067742621]
  Deep Agent is an advanced autonomous AI system designed to manage complex multi-phase tasks.<n>The system's foundation is built on our Hierarchical Task DAG framework.<n>Deep Agent establishes a novel paradigm in self-governing AI systems.
  arXiv  Detail & Related papers  (2025-02-10T21:46:54Z)
• Internet of Agents: Weaving a Web of Heterogeneous Agents for Collaborative Intelligence [79.5316642687565]
  Existing multi-agent frameworks often struggle with integrating diverse capable third-party agents. We propose the Internet of Agents (IoA), a novel framework that addresses these limitations. IoA introduces an agent integration protocol, an instant-messaging-like architecture design, and dynamic mechanisms for agent teaming and conversation flow control.
  arXiv  Detail & Related papers  (2024-07-09T17:33:24Z)
• ROS-LLM: A ROS framework for embodied AI with task feedback and structured reasoning [74.58666091522198]
  We present a framework for intuitive robot programming by non-experts. We leverage natural language prompts and contextual information from the Robot Operating System (ROS) Our system integrates large language models (LLMs), enabling non-experts to articulate task requirements to the system through a chat interface.
  arXiv  Detail & Related papers  (2024-06-28T08:28:38Z)
• AgentScope: A Flexible yet Robust Multi-Agent Platform [66.64116117163755]
  AgentScope is a developer-centric multi-agent platform with message exchange as its core communication mechanism. The abundant syntactic tools, built-in agents and service functions, user-friendly interfaces for application demonstration and utility monitor, zero-code programming workstation, and automatic prompt tuning mechanism significantly lower the barriers to both development and deployment.
  arXiv  Detail & Related papers  (2024-02-21T04:11:28Z)
• Realistic simulation of users for IT systems in cyber ranges [63.20765930558542]
  We instrument each machine by means of an external agent to generate user activity. This agent combines both deterministic and deep learning based methods to adapt to different environment. We also propose conditional text generation models to facilitate the creation of conversations and documents.
  arXiv  Detail & Related papers  (2021-11-23T10:53:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.