OSExpert: Computer-Use Agents Learning Professional Skills via Exploration

• URL: http://arxiv.org/abs/2603.07978v1
• Date: Mon, 09 Mar 2026 05:27:56 GMT
• Title: OSExpert: Computer-Use Agents Learning Professional Skills via Exploration
• Abstract summary: General-purpose computer-use agents are far less helpful than human experts.<n>We introduce a depth-first search algorithm to explore and verify an environment's unit functions.<n>The agent then exploits compositionality between unit skills to self-construct a curriculum for composite tasks.
• Score: 55.660669638732024
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: General-purpose computer-use agents have shown impressive performance across diverse digital environments. However, our new benchmark, OSExpert-Eval, indicates they remain far less helpful than human experts. Although inference-time scaling enables adaptation, these agents complete complex tasks inefficiently with degraded performance, transfer poorly to unseen UIs, and struggle with fine-grained action sequences. To solve the problem, we introduce a GUI-based depth-first search (GUI-DFS) exploration algorithm to comprehensively explore and verify an environment's unit functions. The agent then exploits compositionality between unit skills to self-construct a curriculum for composite tasks. To support fine-grained actions, we curate a database of action primitives for agents to discover during exploration; these are saved as a skill set once the exploration is complete. We use the learned skills to improve the agent's performance and efficiency by (1) enriching agents with ready-to-use procedural knowledge, allowing them to plan only once for long trajectories and generate accurate actions, and (2) enabling them to end inference-time scaling earlier by realizing their boundary of capabilities. Extensive experiments show that our environment-learned agent takes a meaningful step toward expert-level computer use, achieving a around 20 percent performance gain on OSExpert-Eval and closing the efficiency gap to humans by around 80 percent

Related papers

• Running the Gauntlet: Re-evaluating the Capabilities of Agents Beyond Familiar Environments [67.2234316079859]
  GauntletBench is a web-based benchmark for evaluating agent generalisation in challenging scenarios.<n>It focuses on three underexplored capabilities (temporal perception, graphical understanding, and 3D reasoning) across five less-covered professional applications.<n>Our empirical results reveal that frontier agentic systems remain far from achieving human-level performance.
  arXiv  Detail & Related papers  (2026-06-12T12:32:24Z)
• Look Before You Leap: Autonomous Exploration for LLM Agents [46.001025916022066]
  Large language model based agents often fail in unfamiliar environments due to premature exploitation.<n>We identify autonomous exploration as a critical yet underexplored capability for building adaptive agents.
  arXiv  Detail & Related papers  (2026-05-15T16:24:16Z)
• Boosting Deep Reinforcement Learning with Semantic Knowledge for Robotic Manipulators [2.6913398550088483]
  Deep Reinforcement Learning (DRL) is a powerful framework for solving complex sequential decision-making problems.<n>We propose a novel integration of DRL with semantic knowledge in the form of Knowledge Graph Embeddings (KGEs)<n>Our architecture combines KGEs with visual observations, enabling the agent to exploit environmental knowledge during training.
  arXiv  Detail & Related papers  (2026-01-23T16:14:28Z)
• Experience-Driven Exploration for Efficient API-Free AI Agents [34.38668336861503]
  KG-Agent is an experience-driven learning framework that structures an agent's raw pixel-level interactions into a persistent State-Action Knowledge Graph.<n> KG-Agent overcomes inefficient exploration by linking functionally similar but visually distinct GUI states.<n>We demonstrate significant improvements in exploration efficiency and strategic depth over the state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-10-17T02:53:06Z)
• WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learning [73.91893534088798]
  WebSailor is a complete post-training methodology designed to instill this crucial capability.<n>Our approach involves generating novel, high-uncertainty tasks through structured sampling and information obfuscation.<n>WebSailor significantly outperforms all open-source agents in complex information-seeking tasks.
  arXiv  Detail & Related papers  (2025-09-16T17:57:03Z)
• WebSailor: Navigating Super-human Reasoning for Web Agent [72.5231321118689]
  WebSailor is a complete post-training methodology designed to instill this crucial capability.<n>Our approach involves generating novel, high-uncertainty tasks through structured sampling and information obfuscation.<n>WebSailor significantly outperforms all opensource agents in complex information-seeking tasks.
  arXiv  Detail & Related papers  (2025-07-03T12:59:07Z)
• UI-Evol: Automatic Knowledge Evolving for Computer Use Agents [23.21178608410048]
  We propose UI-Evol, a plug-and-play module for autonomous GUI knowledge evolution.<n> UI-Evol consists of two stages: a Retrace Stage that extracts faithful objective action sequences from actual agent-environment interactions, and a Critique Stage that refines existing knowledge.<n>Our results demonstrate that UI-Evol not only significantly boosts task performance but also addresses a previously overlooked issue of high behavioral standard deviation in computer use agents.
  arXiv  Detail & Related papers  (2025-05-28T04:32:05Z)
• Learning to Use Tools via Cooperative and Interactive Agents [58.77710337157665]
  Tool learning empowers large language models (LLMs) as agents to use external tools and extend their utility. We propose ConAgents, a Cooperative and interactive Agents framework, which coordinates three specialized agents for tool selection, tool execution, and action calibration separately. Our experiments on three datasets show that the LLMs, when equipped with ConAgents, outperform baselines with substantial improvement.
  arXiv  Detail & Related papers  (2024-03-05T15:08:16Z)
• Human-Timescale Adaptation in an Open-Ended Task Space [56.55530165036327]
  We show that training an RL agent at scale leads to a general in-context learning algorithm that can adapt to open-ended novel embodied 3D problems as quickly as humans. Our results lay the foundation for increasingly general and adaptive RL agents that perform well across ever-larger open-ended domains.
  arXiv  Detail & Related papers  (2023-01-18T15:39:21Z)
• Planning to Explore via Self-Supervised World Models [120.31359262226758]
  Plan2Explore is a self-supervised reinforcement learning agent. We present a new approach to self-supervised exploration and fast adaptation to new tasks. Without any training supervision or task-specific interaction, Plan2Explore outperforms prior self-supervised exploration methods.
  arXiv  Detail & Related papers  (2020-05-12T17:59:45Z)

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.