DeepSearch-World: Self-Distillation for Deep Search Agents in a Verifiable Environment

• URL: http://arxiv.org/abs/2607.07820v2
• Date: Mon, 13 Jul 2026 12:09:44 GMT
• Title: DeepSearch-World: Self-Distillation for Deep Search Agents in a Verifiable Environment
• Abstract summary: We present DeepSearch-Evolve, a self-distillation framework for web agents built on DeepSearch-World.<n>DeepSearch-Evolve iteratively performs trajectory generation, filtering, data mixing, and fine-tuning to train stronger agents.<n>We will release the environment, 420K training pool, validation set, model, and code to facilitate future research on self-improving deep search agents.
• Score: 40.48626828756898
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: 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.

Related papers

• Tongyi DeepResearch Technical Report [111.78446943571782]
  To incentivize autonomous deep research agency, Tongyi DeepResearch is developed through an end-to-end training framework.<n>Tongyi DeepResearch achieves 30.5 billion total parameters, with only 3.3 billion activated per token.<n>We open-source the model, framework, and complete solutions to empower the community.
  arXiv  Detail & Related papers  (2025-10-28T17:53:02Z)
• WebSeer: Training Deeper Search Agents through Reinforcement Learning with Self-Reflection [51.10348385624784]
  We present WebSeer, a more intelligent search agent trained via reinforcement learning enhanced with a self-reflection mechanism.<n>Our approach substantially extends tool-use chains and improves answer accuracy.
  arXiv  Detail & Related papers  (2025-10-21T16:52:00Z)
• Beyond Turn Limits: Training Deep Search Agents with Dynamic Context Window [88.85901839023803]
  DeepMiner is a novel framework that elicits such abilities by introducing high-difficulty training tasks and dynamic context window.<n>We develop DeepMiner-32B, which achieves substantial performance improvements across multiple search agent benchmarks.
  arXiv  Detail & Related papers  (2025-10-09T14:31:39Z)
• InfoAgent: Advancing Autonomous Information-Seeking Agents [143.15973604285304]
  We introduce InfoAgent, a deep research agent powered by an innovative data synthesis pipeline and orchestrated web search tools.<n>With our methods, InfoAgent achieves 15.3% accuracy on BrowseComp, 29.2% on BrowseComp-ZH, and 40.4% on Xbench-DS.
  arXiv  Detail & Related papers  (2025-09-29T17:59:57Z)
• Fathom-DeepResearch: Unlocking Long Horizon Information Retrieval and Synthesis for SLMs [7.3517692707289415]
  We introduce Fathom-DeepResearch, an agentic system composed of two specialized models.<n>The first is Fathom-Search-4B, a DeepSearch model optimized for evidence-based investigation through live web search and targeted webpage querying.<n>The second is Fathom- Synthesizer-4B, trained from Qwen3-4B, which converts multi-turn DeepSearch traces into structured, citation-dense DeepResearch Reports.
  arXiv  Detail & Related papers  (2025-09-28T22:58:11Z)
• DeepDive: Advancing Deep Search Agents with Knowledge Graphs and Multi-Turn RL [60.47878242100153]
  We present DeepDive to advance deep search agents.<n>We propose a strategy to automatically synthesize complex, difficult, and hard-to-find questions from open knowledge graphs.<n>We apply end-to-end multi-turn reinforcement learning to enhance LLMs' long-horizon reasoning with deep search.
  arXiv  Detail & Related papers  (2025-09-12T17:52:35Z)
• Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RL [22.8456317506762]
  ASearcher is an open-source project for large-scale RL training of search agents.<n>ASearcher-Web-QwQ achieves Avg@4 scores of 51.1 on xBench and 58.7 on GAIA, surpassing existing open-source 32B agents.
  arXiv  Detail & Related papers  (2025-08-11T13:36:57Z)
• DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments [20.498100965239818]
  We introduce DeepResearcher, the first comprehensive framework for end-to-end training of LLM-based deep research agents.<n>Unlike RAG-based approaches that assume all necessary information exists within a fixed corpus, our method trains agents to navigate the noisy, unstructured, and dynamic nature of the open web.<n>Extensive experiments on open-domain research tasks demonstrate that DeepResearcher achieves substantial improvements of up to 28.9 points over prompt engineering-based baselines.
  arXiv  Detail & Related papers  (2025-04-04T04:41:28Z)

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.