Search papers, labs, and topics across Lattice.
This paper introduces DeepSearch-World, a deterministic environment designed for training web agents through self-distillation, addressing the limitations of fixed teacher-distilled trajectories and sparse-reward reinforcement learning. By leveraging 420K multi-hop QA tasks and enabling key cognitive behaviors like progress verification and failure recovery, the framework allows agents to iteratively improve their performance. The results show that the DeepSearch-World-9B agent achieves competitive scores on various benchmarks, demonstrating the potential of verifiable environments for scalable self-evolution in long-horizon tasks.
Self-distillation in a verifiable environment enables web agents to achieve competitive performance without reliance on external teacher models.
Training tool-use agents to improve from their own experience remains challenging, as supervised fine-tuning relies on fixed teacher-distilled trajectories, while sparse-reward reinforcement learning provides weak supervision for long-horizon interactions. We present DeepSearch-Evolve, a self-distillation framework for web agents built on DeepSearch-World, a deterministic and verifiable environment with reproducible search and page-reading tools. DeepSearch-World contains 420K multi-hop QA tasks constructed from entity-level random walks and supports key agentic cognitive behaviors useful for self-evolving, including progress verification, grounded reflection, and failure recovery. DeepSearch-Evolve iteratively performs trajectory generation, filtering, data mixing, and fine-tuning to train stronger agents. Without distillation from more capable models, DeepSearch-World-9B achieves competitive performance compared with open-source agents, reaching 31.2% on BrowseComp, 61.5% on GAIA, and 93.4% on HotpotQA, showing that verifiable environments enable scalable self-evolution for long-horizon web agents. We will release the environment, 420K training pool, validation set, model, and code to facilitate future research on self-improving deep search agents.
