# Skim: Speculative Execution for Fast and Efficient Web Agents

arXiv: https://arxiv.org/abs/2605.16565 · HTML: https://mlsanity.com/paper/2605.16565/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 30 of its 35 references that are in the map.
- First posted on arXiv 15 May 2026.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 30 of 30)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents](https://mlsanity.com/paper/2207.01206/) (2022)
- [Mind2Web: Towards a Generalist Agent for the Web](https://mlsanity.com/paper/2306.06070/) (2023)
- [GAIA: a benchmark for General AI Assistants](https://mlsanity.com/paper/2311.12983/) (2023)
- [Accelerating Large Language Model Decoding with Speculative Sampling](https://mlsanity.com/paper/2302.01318/) (2023)
- [GPT-4V(ision) is a Generalist Web Agent, if Grounded](https://mlsanity.com/paper/2401.01614/) (2024)
- [WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models](https://mlsanity.com/paper/2401.13919/) (2024)
- [Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents](https://mlsanity.com/paper/2410.05243/) (2024)
- [A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis](https://mlsanity.com/paper/2307.12856/) (2023)
- [ShowUI: One Vision-Language-Action Model for GUI Visual Agent](https://mlsanity.com/paper/2411.17465/) (2024)
- [WebLINX: Real-World Website Navigation with Multi-Turn Dialogue](https://mlsanity.com/paper/2402.05930/) (2024)
- [SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents](https://mlsanity.com/paper/2406.12952/) (2024)
- [AgentOccam: A Simple Yet Strong Baseline for LLM-Based Web Agents](https://mlsanity.com/paper/2410.13825/) (2024)
- [From Pixels to UI Actions: Learning to Follow Instructions via Graphical User Interfaces](https://mlsanity.com/paper/2306.00245/) (2023)
- [You Name It, I Run It: An LLM Agent to Execute Tests of Arbitrary Projects](https://mlsanity.com/paper/2412.10133/) (2024)
- [DOM-Q-NET: Grounded RL on Structured Language](https://mlsanity.com/paper/1902.07257/) (2019)
- [WebXSkill: Skill Learning for Autonomous Web Agents](https://mlsanity.com/paper/2604.13318/) (2026)
- [Speculative Actions: A Lossless Framework for Faster Agentic Systems](https://mlsanity.com/paper/2510.04371/) (2025)
- [MolmoWeb: Open Visual Web Agent and Open Data for the Open Web](https://mlsanity.com/paper/2604.08516/) (2026)
- [ContextBudget: Budget-Aware Context Management for Long-Horizon Search Agents](https://mlsanity.com/paper/2604.01664/) (2026)
- [ContractSkill: Repairable Contract-Based Skills for Multimodal Web Agents](https://mlsanity.com/paper/2603.20340/) (2026)
- [Dynamic Speculative Agent Planning](https://mlsanity.com/paper/2509.01920/) (2025)
- [Prune4Web: DOM Tree Pruning Programming for Web Agent](https://mlsanity.com/paper/2511.21398/) (2025)
- [Read More, Think More: Revisiting Observation Reduction for Web Agents](https://mlsanity.com/paper/2604.01535/) (2026)
- [What Limits Agentic Systems Efficiency?](https://mlsanity.com/paper/2510.16276/) (2025)
- [Region4Web: Rethinking Observation Space Granularity for Web Agents](https://mlsanity.com/paper/2605.07134/) (2026)
- [Caesar: Deep Agentic Web Exploration for Creative Answer Synthesis](https://mlsanity.com/paper/2604.20855/) (2026)

## Built on by (most cited first, 1 of 1)

- [DynBranch: Speculative Subgraph Reuse for Dynamic Agentic LLM Serving](https://mlsanity.com/paper/2609.31047/) (2026)

## Abstract (arXiv)

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.