Weasel: Out-of-Domain Generalization for Web Agents via Importance-Diversity Data Selection

• URL: http://arxiv.org/abs/2605.20291v2
• Date: Tue, 26 May 2026 02:53:26 GMT
• Title: Weasel: Out-of-Domain Generalization for Web Agents via Importance-Diversity Data Selection
• Abstract summary: Weasel is a trajectory selection method for offline training of web agents.<n>We improve out-of-domain performance while reducing training cost, producing roughly 9.7-12.5$times$ training speedups over standard fine-tuning.
• Score: 62.12561798137681
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) have enabled web agents that follow natural language goals through multi-step browser interactions. However, agents fine-tuned on specific trajectories and domain often struggle to generalize out of domain, and offline training can be compute-inefficient due to noisy, redundant trajectories and long accessibility-tree (AXTree) states. To address both issues, we propose Weasel, a trajectory selection method for offline training of web agents. Weasel selects a fixed-budget subset of trajectory steps by optimizing an objective that balances unary importance with pairwise diversity over states, websites, and interaction patterns, solving efficiently with a greedy algorithm. We further improve efficiency with target-centered AXTree pruning that keeps only content around the ground-truth action target, and we mitigate style mismatch for reasoning-native models by replacing expert traces with model-generated, style-consistent rationales. Across AgentTrek and NNetNav training datasets, evaluations in WebArena, WorkArena, and MiniWob, and experiments with Qwen2.5-7B, Gemma3-4B, and Qwen3-8B, Weasel improves out-of-domain performance while reducing training cost, producing roughly 9.7-12.5$\times$ training speedups over standard fine-tuning. We make the code available at https://github.com/fatemehpesaran310/weasel.

Related papers

• 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)
• AgentOpt v0.1 Technical Report: Client-Side Optimization for LLM-Based Agent [18.58248061903799]
  We introduce AgentOpt, the first framework-agnostic Python package for client-side AI optimization.<n>We first study model selection, a high-impact optimization lever in multi-step agent pipelines.<n>To efficiently explore the exponentially growing combination space, AgentOpt implements ten search algorithms.
  arXiv  Detail & Related papers  (2026-04-07T17:13:47Z)
• Offline Decision Transformers for Neural Combinatorial Optimization: Surpassing Heuristics on the Traveling Salesman Problem [0.0]
  Neural Combinatorial Optimization has shown promise, but its reliance on online reinforcement learning hampers deployment and underutilizes decades of algorithmic knowledge.<n>We address these limitations by applying the offline RL framework, Decision Transformer, to learn superior strategies directly from datasets.<n>We show that our method consistently produces higher-quality tours than the four classical tours, demonstrating the potential of offline RL to unlock and exceed the performance embedded in existing domain knowledge.
  arXiv  Detail & Related papers  (2026-03-26T09:47:22Z)
• OpAgent: Operator Agent for Web Navigation [23.928869500029432]
  We develop an online interaction environment and fine-tune the Vision-Language Model (VLM) using a specialized RL pipeline.<n>We introduce a Hybrid Reward Mechanism that combines a ground-truth-agnostic WebJudge for holistic outcome assessment and a Rule-based Decision Tree (RDT) for progress reward.<n> Notably, our RL-enhanced model achieves a 38.1% success rate (pass@5) on WebArena, outperforming all existing monolithic baselines.
  arXiv  Detail & Related papers  (2026-02-14T02:33:55Z)
• Prune4Web: DOM Tree Pruning Programming for Web Agent [20.59581294172181]
  Prune4Web is a novel paradigm that shifts DOM processing from resource-intensive LLM reading to efficient programmatic pruning.<n>We propose a specialized data annotation pipeline and a two-turn dialogue training strategy that jointly optimize the Planner, Programmatic Filter, and Grounder.
  arXiv  Detail & Related papers  (2025-11-26T13:49:39Z)
• Adversarial Style Augmentation for Domain Generalization [41.72506801753435]
  We introduce a novel Adrial Style Augmentation (ASA) method, which explores broader style spaces by generating more effective statistics perturbation. To facilitate the application of ASA, we design a simple yet effective module, namely AdvStyle, which instantiates the ASA method in a plug-and-play manner. Our method significantly outperforms its competitors on the PACS dataset under the single source generalization setting.
  arXiv  Detail & Related papers  (2023-01-30T03:52:16Z)
• Learning To Dive In Branch And Bound [95.13209326119153]
  We propose L2Dive to learn specific diving structurals with graph neural networks. We train generative models to predict variable assignments and leverage the duality of linear programs to make diving decisions.
  arXiv  Detail & Related papers  (2023-01-24T12:01:45Z)
• Mastering the Unsupervised Reinforcement Learning Benchmark from Pixels [112.63440666617494]
  Reinforcement learning algorithms can succeed but require large amounts of interactions between the agent and the environment. We propose a new method to solve it, using unsupervised model-based RL, for pre-training the agent. We show robust performance on the Real-Word RL benchmark, hinting at resiliency to environment perturbations during adaptation.
  arXiv  Detail & Related papers  (2022-09-24T14:22:29Z)
• Stagewise Unsupervised Domain Adaptation with Adversarial Self-Training for Road Segmentation of Remote Sensing Images [93.50240389540252]
  Road segmentation from remote sensing images is a challenging task with wide ranges of application potentials. We propose a novel stagewise domain adaptation model called RoadDA to address the domain shift (DS) issue in this field. Experiment results on two benchmarks demonstrate that RoadDA can efficiently reduce the domain gap and outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-08-28T09:29:14Z)
• Contrastive Learning and Self-Training for Unsupervised Domain Adaptation in Semantic Segmentation [71.77083272602525]
  UDA attempts to provide efficient knowledge transfer from a labeled source domain to an unlabeled target domain. We propose a contrastive learning approach that adapts category-wise centroids across domains. We extend our method with self-training, where we use a memory-efficient temporal ensemble to generate consistent and reliable pseudo-labels.
  arXiv  Detail & Related papers  (2021-05-05T11:55:53Z)
• Unsupervised and self-adaptative techniques for cross-domain person re-identification [82.54691433502335]
  Person Re-Identification (ReID) across non-overlapping cameras is a challenging task. Unsupervised Domain Adaptation (UDA) is a promising alternative, as it performs feature-learning adaptation from a model trained on a source to a target domain without identity-label annotation. In this paper, we propose a novel UDA-based ReID method that takes advantage of triplets of samples created by a new offline strategy.
  arXiv  Detail & Related papers  (2021-03-21T23:58:39Z)

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.