SynWeaver: Website-Prior Task and Trajectory Co-Synthesis for Web Agents

• URL: http://arxiv.org/abs/2608.12429v1
• Date: Wed, 12 Aug 2026 12:03:20 GMT
• Title: SynWeaver: Website-Prior Task and Trajectory Co-Synthesis for Web Agents
• Abstract summary: Web agents often struggle to generalize to unseen websites because they lack website-specific supervision.<n>We present bfSynWeaver, a website-prior task-trajectory co-text framework designed to address these challenges.
• Score: 2.920674375891394
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Web agents often struggle to generalize to unseen websites because they lack website-specific supervision. Recent exploration-based data synthesis methods reduce manual annotation, but they still face two key limitations: they often fail to cover the full functionality of a website, and without sufficient website prior knowledge, they tend to propose hallucinated tasks, which in turn limits the diversity and efficiency of downstream trajectory synthesis. We present \textbf{SynWeaver}, a website-prior task-trajectory co-synthesis framework designed to address these challenges. SynWeaver first performs structured website exploration and constructs a website map that covers a broad set of functionally distinct page states and executable interactions on the target website. It then derives page-level and transition-level supervision from this map to train a UI-aware model with website-specific priors, enabling more grounded task proposals. Finally, SynWeaver performs collaborative task-trajectory synthesis, jointly updating the task and execution trajectory when they become inconsistent, and then verifies and repairs the collected results to produce executable, semantically aligned supervision. Experiments on WebArena and WebVoyager demonstrate that SynWeaver consistently outperforms strong synthesis baselines and yields more effective supervision for both in-domain and out-of-domain generalization.

Related papers

• Training Needs Trustworthy Worlds: Verified Synthetic Web Environments for Agent Learning [48.88985618650394]
  Our framework represents each generated website as a structured scaffold of pages, navigation links, database records, state-change markers, and task constraints.<n>During interaction, ordinary UI transitions are executed deterministically, while persistent backend updates are invoked only through validated state-change markers.<n>Across 500 synthetic environments spanning six domains, our method reduces task-blocking defects and improves feasible-task rate from 48.6% to 94.8%.
  arXiv  Detail & Related papers  (2026-08-22T10:18:45Z)
• CAP: A Scalable Benchmark for Evaluating Cross-Site Browser Agents with Complex Actions and Perception [22.620664364045286]
  Large language models are increasingly deployed as autonomous agents that interact with the web through browsers.<n>We introduce CAP, a scalable benchmark for evaluating browser agents on cross-site, human-like web tasks.<n>We construct 420 tasks across 108 real-world websites and 24 domains under careful quality control.
  arXiv  Detail & Related papers  (2026-08-09T01:08:19Z)
• 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)
• 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)
• Avenir-Web: Human-Experience-Imitating Multimodal Web Agents with Mixture of Grounding Experts [59.68272935616536]
  Avenir-Web is a web agent that achieves a new open-source state of the art on the Online-Mind2Web benchmark in real-world deployment.<n>We evaluate Avenir-Web on Online-Mind2Web, a rigorous benchmark of live and user-centered web tasks.
  arXiv  Detail & Related papers  (2026-02-02T18:50:07Z)
• WebArbiter: A Principle-Guided Reasoning Process Reward Model for Web Agents [31.554790282560443]
  We introduce WebArbiter, a principle-inducing WebPRM that formulates reward modeling as text generation.<n>WebArbiter produces structured justifications that conclude with a preference verdict and identify the action most conducive to task completion.
  arXiv  Detail & Related papers  (2026-01-29T15:39:50Z)
• Adapting Web Agents with Synthetic Supervision [80.89365133130558]
  Web agents struggle to adapt to new websites due to the scarcity of environment specific tasks and demonstrations.<n>Recent works have explored synthetic data generation to address this challenge.<n>We propose SynthAgent, a fully synthetic supervision framework.
  arXiv  Detail & Related papers  (2025-11-08T18:45:33Z)
• WebDART: Dynamic Decomposition and Re-planning for Complex Web Tasks [30.48395228595732]
  Large language model (LLM) agents are becoming competent at straightforward web tasks, but struggle with objectives that require long horizon navigation, large scale information extraction, and reasoning under constraints.<n>We present WebDART, a general framework that enables a single LLM to handle such complex chores.<n>WebDART lifts success rates by up to 13.7 percentage points over previous SOTA agents, while matching their performance on the easier WebArena suite.
  arXiv  Detail & Related papers  (2025-10-08T02:34:59Z)
• WebSynthesis: World-Model-Guided MCTS for Efficient WebUI-Trajectory Synthesis [34.998277998052444]
  We propose WebSynthesis, a novel framework for trajectory synthesis and training.<n>We show that an agent trained using WebSynthesis on a small-scale synthetic dataset achieves performance comparable to or even surpassing that of models trained on large-scale real-world data.
  arXiv  Detail & Related papers  (2025-07-06T12:31:10Z)
• Instruction-Tuning Data Synthesis from Scratch via Web Reconstruction [83.0216122783429]
  Web Reconstruction (WebR) is a fully automated framework for synthesizing high-quality instruction-tuning (IT) data directly from raw web documents.<n>We show that datasets generated by WebR outperform state-of-the-art baselines by up to 16.65% across four instruction-following benchmarks.
  arXiv  Detail & Related papers  (2025-04-22T04:07:13Z)

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.