{"ID":2897888,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.04370","arxiv_id":"2507.04370","title":"WebSynthesis: World-Model-Guided MCTS for Efficient WebUI-Trajectory Synthesis","abstract":"Recent advancements in large language models (LLMs) have significantly improved the capabilities of web agents. However, effectively navigating complex and dynamic web environments still requires more advanced trajectory-level planning and execution. Prior studies have addressed self-improving agents by collecting extensive GUI trajectories from real-environment interactions. Despite their effectiveness, these approaches encounter two critical challenges: (1) Uncontrollable environment states, where real or sandboxed web environments often yield unstable and non-deterministic feedback, complicating the reproduction and debugging of agent behaviors; and (2) High API costs, as generating even a single interaction trajectory can involve hundreds of queries, leading to considerable API usage and computational expenses. To address these limitations and enable scalable self-improvement for agents, we propose WebSynthesis, a novel framework for trajectory synthesis and training. WebSynthesis leverages a learned world model to simulate virtual web environments, allowing a policy agent to perform efficient and reversible tree-based planning. This approach supports the large-scale generation of diverse and high-quality trajectories, which are subsequently utilized to refine the agent's policy. Experimental results demonstrate 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.","short_abstract":"Recent advancements in large language models (LLMs) have significantly improved the capabilities of web agents. However, effectively navigating complex and dynamic web environments still requires more advanced trajectory-level planning and execution. Prior studies have addressed self-improving agents by collecting exte...","url_abs":"https://arxiv.org/abs/2507.04370","url_pdf":"https://arxiv.org/pdf/2507.04370v1","authors":"[\"Yifei Gao\",\"Junhong Ye\",\"Jiaqi Wang\",\"Jitao Sang\"]","published":"2025-07-06T12:31:10Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}