K^2-Agent: Co-Evolving Know-What and Know-How for Hierarchical Mobile Device Control

• URL: http://arxiv.org/abs/2603.00676v1
• Date: Sat, 28 Feb 2026 14:33:14 GMT
• Title: K^2-Agent: Co-Evolving Know-What and Know-How for Hierarchical Mobile Device Control
• Abstract summary: K2-Agent is a hierarchical framework that models human-like cognition by knowing and co-evolving declarative (what) and procedural (how) knowledge for planning and execution.<n>On the challenging AndroidWorld benchmark, K2-Agent achieves a 76.1% success rate using only raw and open-source backbones.
• Score: 73.50217471850658
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Existing mobile device control agents often perform poorly when solving complex tasks requiring long-horizon planning and precise operations, typically due to a lack of relevant task experience or unfamiliarity with skill execution. We propose K2-Agent, a hierarchical framework that models human-like cognition by separating and co-evolving declarative (knowing what) and procedural (knowing how) knowledge for planning and execution. K2-Agent's high level reasoner is bootstrapped from a single demonstration per task and runs a Summarize-Reflect-Locate-Revise (SRLR) loop to distill and iteratively refine task-level declarative knowledge through self-evolution. The low-level executor is trained with our curriculum-guided Group Relative Policy Optimization (C-GRPO), which (i) constructs a balanced sample pool using decoupled reward signals and (ii) employs dynamic demonstration injection to guide the model in autonomously generating successful trajectories for training. On the challenging AndroidWorld benchmark, K2-Agent achieves a 76.1% success rate using only raw screenshots and open-source backbones. Furthermore, K2-Agent shows powerful dual generalization: its high-level declarative knowledge transfers across diverse base models, while its low-level procedural skills achieve competitive performance on unseen tasks in ScreenSpot-v2 and Android-in-the-Wild (AitW).

Related papers

• openJiuwen: Beyond Static Harnesses for Long-Horizon Coding Agents [25.815001544093217]
  We present openJiuwen, an open-source harness for developer composability and adaptive task execution.<n> openJiuwen provides a shared execution substrate and Rail-based capability composition across single agents, delegated subagents, and Swarm Flow.<n>We systematically evaluate openJiuwen on SWE-bench Verified and Terminal-Bench 2.1, where it achieves 82.6% and 87.19%, respectively.
  arXiv  Detail & Related papers  (2026-08-28T06:31:38Z)
• OpenMobile: Building Open Mobile Agents with Task and Trajectory Synthesis [98.43366988856592]
  We present OpenMobile, an open-source framework that synthesizes high-quality task instructions and agent trajectories.<n>Agents trained on our data achieve competitive results across three dynamic mobile agent benchmarks.
  arXiv  Detail & Related papers  (2026-04-16T14:53:08Z)
• Experience as a Compass: Multi-agent RAG with Evolving Orchestration and Agent Prompts [22.323342919724492]
  HERA is a hierarchical framework that jointly evolves multi-agent orchestration and role-specific agent prompts.<n> HERA achieves an average improvement of 38.69% over recent baselines.<n>Topological analyses reveal emergent self-organization, where sparse exploration yields compact, high-utility multi-agent networks.
  arXiv  Detail & Related papers  (2026-04-01T13:45:52Z)
• Towards Human-Like Manipulation through RL-Augmented Teleoperation and Mixture-of-Dexterous-Experts VLA [62.16042475700567]
  We introduce IMCopilot, a shared-autonomy assistant to simplify teleoperation data collection.<n>We present MoDE-VLA, an architecture that seamlessly integrates heterogeneous force and tactile modalities into a pretrained VLA backbone.<n>We validate our approach on four tasks of escalating complexity, demonstrating doubled success rate improvement over the baseline in dexterous contact-rich tasks.
  arXiv  Detail & Related papers  (2026-03-09T09:02:30Z)
• Lemon Agent Technical Report [12.663220335253529]
  Lemon Agent is a multi-agent orchestrator-worker system built on a newly proposed AgentCortex framework.<n>Our system integrates a hierarchical self-adaptive scheduling mechanism that operates at both the overall orchestrator layer and workers layer.<n>By virtue of this two-tier architecture, the system achieves synergistic balance between global task coordination and local task execution.
  arXiv  Detail & Related papers  (2026-02-06T10:09:49Z)
• Offline Discovery of Interpretable Skills from Multi-Task Trajectories [8.119611773942562]
  We introduce LOKI, a three-stage end-to-end learning framework for offline skill discovery and hierarchical imitation.<n>LOKI achieves high success rates on the challenging D4RL Kitchen benchmark and outperforms standard HIL baselines.
  arXiv  Detail & Related papers  (2026-02-01T05:03:58Z)
• Mobile-Agent-RAG: Driving Smart Multi-Agent Coordination with Contextual Knowledge Empowerment for Long-Horizon Mobile Automation [57.12284831164602]
  Mobile agents show immense potential, yet current state-of-the-art (SoTA) agents exhibit inadequate success rates on real-world, long-horizon, cross-application tasks.<n>We propose Mobile-Agent-RAG, a novel hierarchical multi-agent framework that innovatively integrates dual-level retrieval augmentation.
  arXiv  Detail & Related papers  (2025-11-15T15:22:42Z)
• Hi-Agent: Hierarchical Vision-Language Agents for Mobile Device Control [72.43808515668947]
  We introduce Hi-Agent, a trainable hierarchical vision-language agent for mobile control.<n>Hi-Agent features a high-level reasoning model and a low-level action model that are jointly optimized.<n>Hi-Agent achieves a new State-Of-The-Art (SOTA) 87.9% task success rate on the Android-in-the-Wild (AitW) benchmark.
  arXiv  Detail & Related papers  (2025-10-16T07:38:21Z)
• Towards Self-Evolving Benchmarks: Synthesizing Agent Trajectories via Test-Time Exploration under Validate-by-Reproduce Paradigm [60.36837655498119]
  We propose a Trajectory-based validated-by-Reproducing Agent-benchmark Complexity Evolution framework.<n>This framework takes an original task from an existing benchmark and encourages agents to evolve it into a new task with higher difficulty.<n>Experiments on the GAIA benchmark demonstrate that the TRACE framework consistently enhances task complexity while improving the reliability of correctness.
  arXiv  Detail & Related papers  (2025-10-01T01:52:52Z)
• MobileSteward: Integrating Multiple App-Oriented Agents with Self-Evolution to Automate Cross-App Instructions [45.7564684180131]
  Mobile phone agents can assist people in automating daily tasks on their phones.<n>Existing procedure-oriented agents struggle with cross-app instructions.<n>We propose a self-evolving multi-agent framework named MobileSteward.
  arXiv  Detail & Related papers  (2025-02-24T03:12:45Z)
• Mobile-Agent-E: Self-Evolving Mobile Assistant for Complex Tasks [85.48034185086169]
  Mobile-Agent-E is a hierarchical multi-agent framework capable of self-evolution through past experience.<n>Mobile-Agent-E achieves a 22% absolute improvement over previous state-of-the-art approaches.
  arXiv  Detail & Related papers  (2025-01-20T20:35:46Z)
• Watch Every Step! LLM Agent Learning via Iterative Step-Level Process Refinement [50.481380478458945]
  Iterative step-level Process Refinement (IPR) framework provides detailed step-by-step guidance to enhance agent training. Our experiments on three complex agent tasks demonstrate that our framework outperforms a variety of strong baselines.
  arXiv  Detail & Related papers  (2024-06-17T03:29:13Z)

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.