cs.AIMar 16, 2026

OpenSeeker: Democratizing Frontier Search Agents by Fully Open-Sourcing Training Data

Authors: Yuwen Du, Rui Ye, Shuo Tang, Xinyu Zhu, Yijun Lu, Yuzhu Cai, Siheng Chen

Organizations: Shanghai Jiao Tong University

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Deep search capabilities have become an indispensable competency for frontier Large Language Model (LLM) agents, yet the development of high-performance search agents remains dominated by industrial giants due to a lack of transparent, high-quality training data. This persistent data scarcity has fundamentally hindered the progress of the broader research community in developing and innovating within this domain. To bridge this gap, we introduce OpenSeeker, the first fully open-source search agent (i.e., model and data) that achieves frontier-level performance through two core technical innovations: (1) Fact-grounded scalable controllable QA synthesis, which reverse-engineers the web graph via topological expansion and entity obfuscation to generate complex, multi-hop reasoning tasks with controllable coverage and complexity. (2) Denoised trajectory synthesis, which employs a retrospective summarization mechanism to denoise the trajectory, therefore promoting the teacher LLMs to generate high-quality actions. Experimental results demonstrate that OpenSeeker, trained (a single training run) on only 11.7k synthesized samples, achieves state-of-the-art performance across multiple benchmarks including BrowseComp, BrowseComp-ZH, xbench-DeepSearch, and WideSearch. Notably, trained with simple SFT, OpenSeeker significantly outperforms the second-best fully open-source agent DeepDive (e.g., 29.5% v.s. 15.3% on BrowseComp), and even surpasses industrial competitors such as Tongyi DeepResearch (trained via extensive continual pre-training, SFT, and RL) on BrowseComp-ZH (48.4% v.s. 46.7%). We fully open-source the complete training dataset and the model weights to democratize frontier search agent research and foster a more transparent, collaborative ecosystem.

Figures & tables

Figure 1: OpenSeeker stands out as the only fully open-source agent that achieves competitive performance on four search benchmarks, remarkably accomplishing this via simple SFT in a single training trial..
Figure 2: Overview of Fact-grounded scalable controllable QA synthesis. The pipeline begins with Graph Expansion , where a seed node is expanded into a subgraph of connected pages. Entity Extraction then distills key information themes into a structured Entity Subgraph. A generator synthesizes complex initial questions conditioned on this structure ( Question Generation ), ensuring multi-hop reasoning requirements. To enhance difficulty, we apply Entity Obfuscation to vagueify specific terms, finally producing a challenging question that necessitates deep graph traversal to solve.
Figure 3: Overview of Denoised Trajectory Synthesis. We employ a retrospective summarization mechanism where, after each tool call, the raw tool response from the previous turn is condensed into a ‘Summarized Response’ that replaces the original raw tool response in the history window. This cleaner context enables the teacher to generate high-quality reasoning and actions. Note the asymmetry: while synthesis relies on summarized context, the training and inference phases operate on raw tool response to force the model to learn intrinsic denoising capabilities.
Model Name# Samples# OS SamplesTrainingAcademicBrowseCompBC-ZHxbenchWideSearch
Closed-Source Proprietary Models
Claude-4-Sonnet?0?×\times14.722.5-62.0
Claude-4.5-Sonnet?0?×\times24.142.4--
Claude-4-Opus?0?×\times18.837.4--
OpenAI-o3?0?×\times49.168.7-60.0
OpenAI Deep Research?0?×\times51.542.9--
Table 1: Comparisons among our OpenSeeker and other search agents. ‘# Samples’ denotes the number of total training data samples; ‘# OS Samples’ denotes the number of open-source data samples; ‘Training’ denotes training techniques (CPT: continual pre-training, SFT: supervised fine-tuning, RL: reinforcement learning); ‘Academic’ denotes whether conducted by pure academic team ( ✓\checkmark : Yes, ×\times : No); ‘BC-ZH’ denotes BrowseComp-ZH; ‘WideSearch’ denotes item F1 result on the English subset. With simple SFT, OpenSeeker-v1-30B-SFT even surpasses Tongyi DeepResearch on BrowseComp-ZH which is trained via CPT, SFT, and RL. Among all SFT-based agents, OpenSeeker performs significantly best.
Data# Samples# OS SamplesAcademicBrowseCompBC-ZHxbenchWideSearch-EN
DeepDive-32B4.1 k4.1 k×\times9.523.048.5-
MiroThinker-32B-v0.1147 k147 k×\times10.613.8--
WebSailor-V2-30B?0×\times24.428.361.7-
WebLeaper-30B15 k0×\times27.7-66.044.1
OpenSeeker-v1-30B-SFT11.7 k11.7k✓29.548.474.059.4
Table 2: Performance comparison of different models trained via SFT. Our OpenSeeker consistently and significantly performs the best across four benchmarks with only 11.7k training samples.
Data# Samples# OS SamplesDeveloperBrowseCompxbenchWideSearch-EN
WebSailor-V2-10k10k0Tongyi24.5062.6738.91
WebSailor-V2-5k + WebLeaper-Basic-5k10k0Tongyi20.6758.3332.26
WebSailor-V2-5k + WebLeaper-Union-5k10k0Tongyi27.5062.3341.70
WebSailor-V2-5k + WebLeaper-Reverse-Union-10k15k0Tongyi27.6766.0044.07
OpenSeeker-v1-Data-11.7k11.7 k11.7kAcademic29.5074.0059.40
Table 3: Performance comparison under comparable data volumes. OpenSeeker achieves significant advantages across three benchmarks, demonstrating the high quality of our data.
Figure 4: Comparison of difficulty between OpenSeeker-v1-Data-ZH and BrowseComp-ZH using the same model for inference. OpenSeeker-v1-Data-ZH exhibits significantly higher average token counts and tool call counts than BrowseComp-ZH.
Figure 5: Comparison of difficulty between OpenSeeker-v1-Data-EN and BrowseComp-EN using the same model for inference. OpenSeeker-v1-Data-EN exhibits difficulty comparable to that of BrowseComp-EN.
Appendix figures & tables2 assets

Supplementary material from the paper’s appendix.

Appendix

Data# Samples# OS SamplesAcademicBrowseCompBC-ZHxbench
Openresearcher96k96k×\times26.3-65
REDSearcher?10k×\times34.726.8-
OpenSeeker-v1-Data-11.7k11.7 k11.7k✓29.548.474.0
Appendix
Table 4: Performance comparison of concurrent works trained via SFT.
Figure 6: Comparison of tool call counts using the same model for inference: OpenSeeker’s data vs. REDSearcher’s data. OpenSeeker’s data demonstrates a significantly higher average number of tool calls.
More in this topic

Deep Research Agents

Deep research agents plan long-horizon searches, synthesize cited evidence, and produce reports for complex open-ended questions.

See all 114 papers

Explore similar work

CardsList
May 5, 2026

OpenSeeker-v2: Pushing the Limits of Search Agents with Informative and High-Difficulty Trajectories

Deep search capabilities have become an indispensable competency for frontier Large Language Model (LLM) agents, yet their development remains dominated by industrial giants. The typical industry recipe involves a highly resource-intensive pipeline spanning pre-training, continual pre-training (CPT), supervised fine-tuning (SFT), and reinforcement learning (RL). In this report, we show that when fueled with informative and high-difficulty trajectories, a simple SFT approach could be surprisingly powerful for training frontier search agents. By introducing three simple data synthesis modifications: scaling knowledge graph size for richer exploration, expanding the tool set size for broader functionality, and strict low-step filtering, we establish a stronger baseline. Trained on merely 10.6k data points, our OpenSeeker-v2 achieves state-of-the-art performance across 4 benchmarks (30B-sized agents with ReAct paradigm): 46.0% on BrowseComp, 58.1% on BrowseComp-ZH, 34.6% on Humanity's Last Exam, and 78.0% on xbench, surpassing even Tongyi DeepResearch trained with heavy CPT+SFT+RL pipeline, which achieves 43.4%, 46.7%, 32.9%, and 75.0%, respectively. Notably, OpenSeeker-v2 represents the first state-of-the-art search agent within its model scale and paradigm to be developed by a purely academic team using only SFT. We are excited to open-source the OpenSeeker-v2 model weights and share our simple yet effective findings to make frontier search agent research more accessible to the community.

Yuwen Du, Rui Ye, Shuo Tang +4

1Shanghai Jiao Tong University

Supervised Fine-TuningTool-Augmented Language Model AgentsLLM Agent Trajectory SynthesisLLM AgentsLLM Agent Training
AskPDF
May 6, 2026

OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents

Deep search has become a crucial capability for frontier multimodal agents, enabling models to solve complex questions through active search, evidence verification, and multi-step reasoning. Despite rapid progress, top-tier multimodal search agents remain difficult to reproduce, largely due to the absence of open high-quality training data, transparent trajectory synthesis pipelines, or detailed training recipes. To this end, we introduce OpenSearch-VL, a fully open-source recipe for training frontier multimodal deep search agents with agentic reinforcement learning. First, we curated a dedicated pipeline to construct high-quality training data through Wikipedia path sampling, fuzzy entity rewriting, and source-anchor visual grounding, which jointly reduce shortcuts and one-step retrieval collapse. Based on this pipeline, we curate two training datasets, SearchVL-SFT-36k for SFT and SearchVL-RL-8k for RL. Besides, we design a diverse tool environment that unifies text search, image search, OCR, cropping, sharpening, super-resolution, and perspective correction, enabling agents to combine active perception with external knowledge acquisition. Finally, we propose a multi-turn fatal-aware GRPO training algorithm that handles cascading tool failures by masking post-failure tokens while preserving useful pre-failure reasoning through one-sided advantage clamping. Built on this recipe, OpenSearch-VL delivers substantial performance gains, with over 10-point average improvements across seven benchmarks, and achieves results comparable to proprietary commercial models on several tasks. We will release all data, code, and models to support open research on multimodal deep search agents.

Shuang Chen, Kaituo Feng, Hangting Chen +7

Tencent Hunyuan · University of California, Los Angeles · The Chinese University of Hong Kong +1

Multimodal IRMultimodal Search AgentsMultimodal AgentsRL for LLM AgentsMultimodal Tool Use
AskPDF
May 22, 2026

QUEST: Training Frontier Deep Research Agents with Fully Synthetic Tasks

Deep research agents extend the role of search engines from retrieving keyword-matched pages to synthesizing knowledge, fundamentally changing how humans interact with information. However, frontier systems remain proprietary, while existing open agents often generalize poorly across different task types, leaving unclear how to train a broadly capable deep research agent. We release QUEST, a family of open models (ranging from 2B to 35B) that serve as general-purpose deep research agents designed to handle a wide range of long-horizon search tasks, with strong capabilities in fact seeking, citation grounding, and report synthesis. To build QUEST, we propose an effective training recipe combining mid-training, supervised fine-tuning, and reinforcement learning. Central to this recipe is a curated data synthesis pipeline based on unified rubric trees, which applies to different task types and enables synthesizing training data with verifiable rewards without human annotation. In addition, QUEST incorporates a built-in context management mechanism that enables effective long-horizon reasoning and knowledge synthesis. Using only 8K synthesized tasks, QUEST approaches or even surpasses frontier closed-source agents across eight deep research benchmarks spanning diverse task types, and achieves the best overall performance among recent open-weight agents. We released everything: models, data, and training scripts.

Jian Xie, Tianhe Lin, Zilu Wang +16

The Ohio State University · Amazon AGI SF Lab

Deep Research AgentsLLM Agent TrainingSynthetic Data Generation for Language ModelsLong-Horizon LLM Agents
AskPDF