Agentic Lybic: Multi-Agent Execution System with Tiered Reasoning and Orchestration
On the map: LLM agents and tool use → Software engineering coding agents
Abstract (arXiv)
Autonomous agents for desktop automation struggle with complex multi-step tasks due to poor coordination and inadequate quality control. We introduce Agentic Lybic, a novel multi-agent system where the entire architecture operates as a finite-state machine (FSM). This core innovation enables dynamic orchestration. Our system comprises four components: a Controller, a Manager, three Workers (Technician for code-based operations, Operator for GUI interactions, and Analyst for decision support), and an Evaluator. The critical mechanism is the FSM-based routing between these components, which provides flexibility and generalization by dynamically selecting the optimal execution strategy for each subtask. This principled orchestration, combined with robust quality gating, enables adaptive replanning and error recovery. Evaluated officially on the OSWorld benchmark, Agentic Lybic achieves a state-of-the-art 57.07% success rate in 50 steps, substantially outperforming existing methods. Results demonstrate that principled multi-agent orchestration with continuous quality control provides superior reliability for generalized desktop automation in complex computing environments.
Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. Builds on 28 of its 38 references that are in the map. First posted on arXiv 14 Sep 2025.
Builds on
28 of 38 references.
References · 28
- 2024OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environmentscited by 1,195
- 2023CogAgent: A Visual Language Model for GUI Agentscited by 704
- 2025UI-TARS: Pioneering Automated GUI Interaction with Native Agentscited by 610
- 2024SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agentscited by 567
- 2024Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agentscited by 382
- 2024OS-ATLAS: A Foundation Action Model for Generalist GUI Agentscited by 378
- 2024Aguvis: Unified Pure Vision Agents for Autonomous GUI Interactioncited by 278
- 2025GUI-R1 : A Generalist R1-Style Vision-Language Action Model For GUI Agentscited by 244
- 2025UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learningcited by 215
- 2024OmniParser for Pure Vision Based GUI Agentcited by 198
- 2025Mobile-Agent-v3: Fundamental Agents for GUI Automationcited by 190
- 2024Agent S: An Open Agentic Framework that Uses Computers Like a Humancited by 187
16 more
- 2024Large Language Model-Brained GUI Agents: A Surveycited by 162
- 2025Agent S2: A Compositional Generalist-Specialist Framework for Computer Use Agentscited by 159
- 2024Aria-UI: Visual Grounding for GUI Instructionscited by 140
- 2025InfiGUI-R1: Advancing Multimodal GUI Agents from Reactive Actors to Deliberative Reasonerscited by 140
- 2025Scaling Computer-Use Grounding via User Interface Decomposition and Synthesiscited by 139
- 2024AutoWebGLM: A Large Language Model-based Web Navigating Agentcited by 130
- 2025Alita: Generalist Agent Enabling Scalable Agentic Reasoning with Minimal Predefinition and Maximal Self-Evolutioncited by 116
- 2025GTA1: GUI Test-time Scaling Agentcited by 106
- 2025InfiGUIAgent: A Multimodal Generalist GUI Agent with Native Reasoning and Reflectioncited by 67
- 2025ComputerRL: Scaling End-to-End Online Reinforcement Learning for Computer Use Agentscited by 50
- 2025CoAct-1: Computer-using Multi-Agent System with Coding Actionscited by 35
- 2025OmniParser V2: Structured-Points-of-Thought for Unified Visual Text Parsing and Its Generality to Multimodal Large Language Modelscited by 23
- 2025UItron: Foundational GUI Agent with Advanced Perception and Planningcited by 22
- 2025ScaleTrack: Scaling and back-tracking Automated GUI Agentscited by 16
- 2025From Autonomous Agents to Integrated Systems, A New Paradigm: Orchestrated Distributed Intelligencecited by 12
- 2025Evolving in Tasks: Empowering the Multi-modality Large Language Model as the Computer Use Agentcited by 11
Built on by
Citing papers per year: 2025: 1; 2026: 7.
8 papers.
- 2026OS-Symphony: A Holistic Framework for Robust and Generalist Computer-Using Agentcited by 21
- 2026Parallelizing Tool Execution and LLM Generation for Low-Latency Agent Servingcited by 20
- 2025Scaling Agents for Computer Usecited by 14
- 2026Video-Based Reward Modeling for Computer-Use Agentscited by 3
- 2026OS-Marathon: Benchmarking Computer-Use Agents on Vast-Horizon, Repetitive Taskscited by 2
- 2026MacAgentBench: Benchmarking AI Agents on Real-World macOS Desktopcited by 2
- 2026LocalLSTC: A Long Short-Term Control Architecture for Locally Deployed GUI Agentscited by 0
- 2026AnyAct: Universal Action for Self-Evolving Agentscited by 0
- 2026AnyAct: Universal Action for Self-Evolving Agents29 Sep 2026
- 2026LocalLSTC: A Long Short-Term Control Architecture for Locally Deployed GUI Agents26 Aug 2026
- 2026MacAgentBench: Benchmarking AI Agents on Real-World macOS Desktop21 Jun 2026
- 2026Parallelizing Tool Execution and LLM Generation for Low-Latency Agent Serving19 Mar 2026
- 2026Video-Based Reward Modeling for Computer-Use Agents10 Mar 2026
- 2026OS-Marathon: Benchmarking Computer-Use Agents on Vast-Horizon, Repetitive Tasks28 Jan 2026
- 2026OS-Symphony: A Holistic Framework for Robust and Generalist Computer-Using Agent12 Jan 2026
- 2025Scaling Agents for Computer Use2 Oct 2025
Similar, not cited
Close in wording, no citation either way
- 2026POLARIS: Typed Planning and Governed Execution for Agentic AI in Back-Office Automation
- 2026Agent Operating Systems (AOS): Integrating Agentic Control Planes into, and Beyond, Traditional Operating Systems
- 2026EASy: Towards Efficient LLM-Based Agentic System
- 2026Eluna: An Agentic LLM System for Automating Warehouse Operations with Reasoning and Task Execution
- 2026Beyond State Machines: Executing Network Procedures with Agentic Tool-Calling Sequences
- 2026GraphBit: A Graph-based Agentic Framework for Non-Linear Agent Orchestration
- 2026LLM-as-Code: Agentic Programming for Agent Harness
- 2025COLA: A Scalable Multi-Agent Framework For Windows UI Task Automation