WebClipper: Efficient Evolution of Web Agents with Graph-based Trajectory Pruning
- URL: http://arxiv.org/abs/2602.12852v1
- Date: Fri, 13 Feb 2026 11:56:20 GMT
- Title: WebClipper: Efficient Evolution of Web Agents with Graph-based Trajectory Pruning
- Authors: Junjie Wang, Zequn Xie, Dan Yang, Jie Feng, Yue Shen, Duolin Sun, Meixiu Long, Yihan Jiao, Zhehao Tan, Jian Wang, Peng Wei, Jinjie Gu,
- Abstract summary: Web agents rely on long tool-call trajectories with cyclic reasoning loops and exploration of unproductive branches.<n>We propose WebClipper, a framework that compresses web agent trajectories via graph-based pruning.<n>We introduce a new metric called F-AE Score to measure the model's overall performance in balancing accuracy and efficiency.
- Score: 25.920409811750105
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Deep Research systems based on web agents have shown strong potential in solving complex information-seeking tasks, yet their search efficiency remains underexplored. We observe that many state-of-the-art open-source web agents rely on long tool-call trajectories with cyclic reasoning loops and exploration of unproductive branches. To address this, we propose WebClipper, a framework that compresses web agent trajectories via graph-based pruning. Concretely, we model the agent's search process as a state graph and cast trajectory optimization as a minimum-necessary Directed Acyclic Graph (DAG) mining problem, yielding pruned trajectories that preserve essential reasoning while eliminating redundant steps. Continued training on these refined trajectories enables the agent to evolve toward more efficient search patterns and reduces tool-call rounds by about 20% while improving accuracy. Furthermore, we introduce a new metric called F-AE Score to measure the model's overall performance in balancing accuracy and efficiency. Experiments demonstrate that WebClipper compresses tool-call rounds under excellent performance, providing practical insight into balancing effectiveness and efficiency in web agent design.
Related papers
- WebLeaper: Empowering Efficiency and Efficacy in WebAgent via Enabling Info-Rich Seeking [60.35109192765302]
Information seeking is a core capability that enables autonomous reasoning and decision-making.<n>We propose WebLeaper, a framework for constructing high-coverage IS tasks and generating efficient solution trajectories.<n>Our method consistently achieves improvements in both effectiveness and efficiency over strong baselines.
arXiv Detail & Related papers (2025-10-28T17:51:42Z) - WebGraphEval: Multi-Turn Trajectory Evaluation for Web Agents using Graph Representation [13.14840279219976]
We present WebGraphEval, a framework that abstracts trajectories from multiple agents into a unified, weighted action graph.<n>We show that WebGraphEval captures cross-model regularities, highlights redundancy and inefficiency, and identifies critical decision points overlooked by outcome-based metrics.
arXiv Detail & Related papers (2025-10-22T03:29:25Z) - Branch-and-Browse: Efficient and Controllable Web Exploration with Tree-Structured Reasoning and Action Memory [69.49061918994882]
Branch-and-Browse is a fine-grained web agent framework that unifies structured reasoning-acting, contextual memory, and efficient execution.<n>On the WebArena benchmark, Branch-and-Browse achieves a task success rate of 35.8% and reduces execution time by up to 40.4% relative to state-of-the-art methods.
arXiv Detail & Related papers (2025-10-18T00:45:37Z) - Synthesizing Agentic Data for Web Agents with Progressive Difficulty Enhancement Mechanisms [81.90219895125178]
Web-based 'deep research' agents aim to solve complex question - answering tasks through long-horizon interactions with online tools.<n>These tasks remain challenging, as the underlying language models are often not optimized for long-horizon reasoning.<n>We introduce a two-pronged data synthesis pipeline that generates question - answer pairs by progressively increasing complexity.
arXiv Detail & Related papers (2025-10-15T06:34:46Z) - TGPO: Tree-Guided Preference Optimization for Robust Web Agent Reinforcement Learning [4.456860697635325]
Training Web Agents with reinforcement learning faces critical challenges including credit assignment misallocation, prohibitively high annotation costs, and reward sparsity.<n>Our framework incorporates a Process Reward Model that automatically generates fine-grained rewards through subgoal progress, redundancy detection, and action verification.<n>Experiments on Online-Mind2Web and our self-constructed C-WebShop datasets demonstrate that TGPO significantly outperforms existing methods.
arXiv Detail & Related papers (2025-09-17T16:58:44Z) - 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) - WebCoT: Enhancing Web Agent Reasoning by Reconstructing Chain-of-Thought in Reflection, Branching, and Rollback [78.55946306325914]
We identify key reasoning skills essential for effective web agents.<n>We reconstruct the agent's reasoning algorithms into chain-of-thought rationales.<n>Our approach yields significant improvements across multiple benchmarks.
arXiv Detail & Related papers (2025-05-26T14:03:37Z) - WebRollback: Enhancing Web Agents with Explicit Rollback Mechanisms [52.942566473658054]
We enhance web agents with an explicit rollback mechanism, enabling the agent to revert back to a previous state in its navigation trajectory.<n>This mechanism gives the model the flexibility to directly control the search process, leading to an effective and efficient web navigation method.
arXiv Detail & Related papers (2025-04-16T05:41:20Z) - Tree-based Focused Web Crawling with Reinforcement Learning [3.4877567508788134]
A focused crawler aims at discovering as many web pages and web sites relevant to a target topic as possible, while avoiding irrelevant ones.<n>We propose TRES, a novel framework for focused crawling that aims at maximizing both the number of relevant web pages and the number of relevant web sites.
arXiv Detail & Related papers (2021-12-12T00:19:47Z)
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.