Scalable Behaviour Cloning on Browser Using via Skill Distillation

• URL: http://arxiv.org/abs/2606.32014v1
• Date: Tue, 30 Jun 2026 17:46:23 GMT
• Title: Scalable Behaviour Cloning on Browser Using via Skill Distillation
• Abstract summary: We argue that the bottleneck for browser agents is decision-making under incomplete information.<n>We convert user interaction trajectories into compact natural-language skills that agents can read, retrieve, reuse, and compose directly.
• Score: 4.437750866609224
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Internet users collectively perform an enormous range of skilled work through web browsers, from software development and document editing to search, forms, and enterprise workflows, making human browsing a highly scalable but under-exploited source of reusable browser skills. We argue that the bottleneck for browser agents is decision-making under incomplete information rather than low-level operation, and that the priors agents lack are already implicit in human interaction traces. We therefore study scalable behavior cloning for browser agents via skill distillation, converting user interaction trajectories into compact natural-language skills that agents can read, retrieve, reuse, and compose directly. We further organize the distilled skills into a skill graph so that growth proceeds through consolidation rather than unbounded accumulation. This suggests that the scalability of browser agents may come less from manually designed tasks and more from the collective skills already expressed by internet users. Our project is available at: https://lab.einsia.ai/browserbc/.

Related papers

• COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation [58.84646485020439]
  We present an automated trace-to-skill distillation system for generating person-grounded AI skills.<n> COLLEAGUE.SKILL produces a versioned skill package with two tracks: a capability track for practices, mental models, and decisions, and a bounded behavior track for communication style, interaction rules, and correction history.
  arXiv  Detail & Related papers  (2026-05-29T12:59:08Z)
• cotomi Act: Learning to Automate Work by Watching You [7.063461281524173]
  Cotomi Act is a browser-based computer-using agent that combines reliable multi-step task execution with persistent organizational knowledge learned from user behavior.<n>For execution, an agent scaffold with adaptive lazy observation achieves 80.4% on the 179-task WebArena human-evaluation subset.<n>In our live demonstration, attendees interact with the system in a real browser, issuing tasks and observing end-to-end autonomous execution and shared knowledge management.
  arXiv  Detail & Related papers  (2026-05-04T23:50:20Z)
• WebXSkill: Skill Learning for Autonomous Web Agents [104.76374637691212]
  WebXSkill is a framework that bridges the gap between code-based skills and natural language guidance.<n>On WebArena and WebVoyager, WebXSkill improves task success rate by up to 9.8 and 12.9 points over the baseline.
  arXiv  Detail & Related papers  (2026-04-14T21:48:15Z)
• OSExpert: Computer-Use Agents Learning Professional Skills via Exploration [55.660669638732024]
  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.
  arXiv  Detail & Related papers  (2026-03-09T05:27:56Z)
• BrowserAgent: Building Web Agents with Human-Inspired Web Browsing Actions [48.194688161526756]
  BrowserAgent operates directly on raw web pages via Playwright through a set of predefined browser actions.<n>We introduce an explicit memory mechanism to store key conclusions across steps, further enhancing the model's reasoning capabilities.
  arXiv  Detail & Related papers  (2025-10-12T15:43:37Z)
• WALT: Web Agents that Learn Tools [66.73502484310121]
  WALT is a framework that reverse-engineers latent website functionality into reusable invocable tools.<n>Rather than hypothesizing ad-hoc skills, WALT exposes robust implementations of automations already designed into websites.<n>On VisualWebArena and WebArena, WALT achieves higher success with fewer steps and less LLM-dependent reasoning.
  arXiv  Detail & Related papers  (2025-10-01T23:41:47Z)
• 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)
• Rethinking Agent Design: From Top-Down Workflows to Bottom-Up Skill Evolution [34.66260172204154]
  We introduce a bottom-up agent paradigm that mirrors the human learning process.<n>Agents acquire competence through a trial-and-reasoning mechanism-exploring, reflecting on outcomes, and abstracting skills over time.<n>We evaluate this paradigm in Slay the Spire and Civilization V, where agents perceive through raw visual inputs and act via mouse outputs, the same as human players.
  arXiv  Detail & Related papers  (2025-05-23T09:38:55Z)
• Never-Ending Behavior-Cloning Agent for Robotic Manipulation [38.756955029068294]
  NBAgent is a language-conditioned Never-ending Behavior-cloning Agent. It learns observation knowledge of novel 3D scene semantics and robot manipulation skills from skill-shared and skill-specific attributes.
  arXiv  Detail & Related papers  (2024-03-01T07:51:29Z)

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.