Skim: Speculative Execution for Fast and Efficient Web Agents

• URL: http://arxiv.org/abs/2605.16565v2
• Date: Tue, 19 May 2026 13:45:27 GMT
• Title: Skim: Speculative Execution for Fast and Efficient Web Agents
• Abstract summary: Skim is a speculative execution framework for web agents.<n>It exploits the predictable structure of purpose-built websites.<n>Skim reduces median per-task cost by 1.9x and latency by 33.4% with no accuracy loss.
• Score: 8.47432001892345
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Skim is a speculative execution framework for web agents that exploits the predictable structure of purpose-built websites. Today's web-agent expense is not intrinsic to the tasks but a property of how agents are composed: frontier-model inference, browser rendering, and ReAct-style planning are applied to every step of every task regardless of complexity. Skim's key observation is that websites enforce stable URL patterns, answer formats, and task-to-trajectory mappings across queries of the same type, so most queries can bypass these heavyweight components entirely. An offline profiler captures these patterns once per site. At runtime, Skim matches each query to a template, synthesizes the destination URL, and extracts the answer with a small model. A lightweight verifier gates each fast-path output against the query and schema; rare misspeculations cascade to the full agent, warm-started by the fast path's final URL to preserve upstream trajectory progress. Across standard web-agent benchmarks paired with three backboneagents (WebVoyager, AgentOccam, BrowserUse), Skim reduces median per-task cost by 1.9x and latency by 33.4% with no accuracy loss.

Related papers

• BrowserForge: Scaling Web Episode via Parallel Browser Sandboxes [54.96895469970198]
  BrowserForge generates web interaction data at scale by driving many browser sandboxes in parallel over the open web.<n> BrowserForge couples three components: an open-web sourcing stage that exposes the agent to hundreds of thousands of real, openly reachable websites.<n>A rule-plus-model cleaning pipeline removes failed runs and rewrites the surviving reasoning into a single unified chain-of-thought style.
  arXiv  Detail & Related papers  (2026-08-25T17:35:42Z)
• Tencent WorkBuddy Bench: A Multi-Domain Coding-Agent Benchmark with Contamination-Resistant Task Construction [57.138342889101345]
  Tencent WorkBuddy Bench is a multi-domain evaluation suite for coding agents.<n>This report documents its construction methodology, scoring protocol, and a cross-model leaderboard.
  arXiv  Detail & Related papers  (2026-07-23T04:34:06Z)
• WebSwarm: Recursive Multi-Agent Orchestration for Deep-and-Wide Web Search [104.75798763084424]
  Large language model (LLM)-based web search agents are transforming information seeking into complex, deep-and-wide search and research-oriented tasks.<n>We propose WebSwarm, a progressive progressive delegation framework that jointly constructs task decomposition and expansion.<n>We show that WebSwarm consistently outperforms single-agent and multi-agent baselines on deep, wide, and interleaved deep-and-wide tasks.
  arXiv  Detail & Related papers  (2026-07-09T16:28:49Z)
• WebChallenger: A Reliable and Efficient Generalist Web Agent [3.8083338863305882]
  WebChallenger is a web agent framework that addresses each gap through architecture design rather than model scale.<n>Our system achieves 56.3% on WebArena, 48.7% on VisualWebArena, 51.0% on Online-Mind2Web, and 70.9% on WorkArena.
  arXiv  Detail & Related papers  (2026-06-09T04:53:19Z)
• GTA: Generating Long-Horizon Tasks for Web Agents at Scale [82.43869456830664]
  We introduce a scalable framework, GTA, that integrates crawling, retrieval-based seeding, in-context generation, and automated quality control.<n>We instantiate the pipeline on over 50 websites covering e-commerce, government, forums, and news, with multilingual and multi-hop coverage.<n>Our contributions are three-fold: (i) formalizing multi-hop web-agent task generation, (ii) proposing an efficient and validated pipeline for automatic data creation, and (iii) releasing a dynamic benchmark with reproducible evaluation.
  arXiv  Detail & Related papers  (2026-05-28T01:05:50Z)
• Web Agents Should Adopt the Plan-Then-Execute Paradigm [9.920367562132336]
  We argue that web agents should default to plan-then-execute instead of ReAct.<n>Plan-then-execute changes this boundary: untrusted data may influence values or branches inside a predefined execution graph.<n>We identify the main barrier to adopting plan-then-execute on the web.
  arXiv  Detail & Related papers  (2026-05-14T02:48:57Z)
• WebAgentGuard: A Reasoning-Driven Guard Model for Detecting Prompt Injection Attacks in Web Agents [117.65855863464863]
  Web agents are highly vulnerable to prompt injection attacks.<n>Existing defenses, including system prompt defenses and direct fine-tuning of agents, have shown limited effectiveness.<n>We introduce WebAgentGuard, a reasoning-driven, multimodal guard model for prompt injection detection.
  arXiv  Detail & Related papers  (2026-04-14T04:50:35Z)
• Internal APIs Are All You Need: Shadow APIs, Shared Discovery, and the Case Against Browser-First Agent Architectures [0.0]
  Unbrowse is a shared route graph that transforms browser-based route discovery into a collectively maintained index.<n>The system passively learns routes from real browsing traffic and serves cached routes via direct API calls.<n>A three-path execution model -- local cache, shared graph, or browser fallback -- ensures the system is voluntary and self-correcting.
  arXiv  Detail & Related papers  (2026-04-01T09:51:46Z)
• TimeWarp: Evaluating Web Agents by Revisiting the Past [7.017865728670461]
  We introduce TimeWarp, a benchmark that emulates the evolving web using containerized environments that vary in UI, design, and layout.<n>Our experiments reveal web agents' vulnerability to changes and the limitations of behavior cloning (BC) on single-version trajectories.<n>We propose TimeTraj, a simple yet effective algorithm that uses plan distillation to collect trajectories across multiple versions.
  arXiv  Detail & Related papers  (2026-03-05T08:43:06Z)
• TabAgent: A Framework for Replacing Agentic Generative Components with Tabular-Textual Classifiers [5.792704492773729]
  TabAgent is a framework for replacing generative decision components in closed-set selection tasks with a compact textual-tabular classifier trained on execution traces.<n>On the long-horizon AppWorld benchmark, TabAgent maintains task-level success while eliminating shortlist-time LLM calls, reducing latency by approximately 95% and inference cost by 85-91%.
  arXiv  Detail & Related papers  (2026-02-18T13:01:17Z)
• BrowserArena: Evaluating LLM Agents on Real-World Web Navigation Tasks [51.803138848305814]
  We introduce BrowserArena, a live open-web agent evaluation platform that collects user-submitted tasks.<n>We identify three consistent failure modes: captcha resolution, pop-up banner removal, and direct navigation to URLs.<n>Our findings surface both the diversity and brittleness of current web agents.
  arXiv  Detail & Related papers  (2025-10-02T15:22:21Z)
• 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)
• WebLists: Extracting Structured Information From Complex Interactive Websites Using Executable LLM Agents [1.6673034682613495]
  We present WebLists, a benchmark of 200 data-extraction tasks across four common business and enterprise use-cases.<n>We show that both LLMs with search capabilities and SOTA web agents struggle with these tasks, with a recall of 3% and 31%, respectively.<n>We propose BardeenAgent, a novel framework that enables web agents to convert their execution into repeatable programs, and replay them at scale across pages with similar structure.<n>On the WebLists benchmark, BardeenAgent achieves 66% recall overall, more than doubling the performance of SOTA web agents, and reducing cost per output row by 3x.
  arXiv  Detail & Related papers  (2025-04-17T06:16:40Z)
• AgentOccam: A Simple Yet Strong Baseline for LLM-Based Web Agents [52.13695464678006]
  This study enhances an LLM-based web agent by simply refining its observation and action space.<n>AgentOccam surpasses the previous state-of-the-art and concurrent work by 9.8 (+29.4%) and 5.9 (+15.8%) absolute points respectively.
  arXiv  Detail & Related papers  (2024-10-17T17:50:38Z)

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.