OpenSeeker is an open-source search agent system that democratizes access to frontier search capabilities by fully open-sourcing its training data. We fine-tuned Qwen3-30B-A3B-Thinking-2507 with 11.7K training examples and achieved state-of-the-art performance on frontier search benchmarks:
54
10 commits
2 linked in READMEs
updated Mar 17, 2026
README
OpenSeeker: Democratizing Frontier Search Agents by Fully Open-Sourcing Training Data
OpenSeeker is an open-source search agent system that democratizes access to frontier search capabilities by fully open-sourcing its training data. We fine-tuned Qwen3-30B-A3B-Thinking-2507 with 11.7K training examples and achieved state-of-the-art performance on frontier search benchmarks:
Highlights
- Superior performance on search agent benchmarks: 48.4 on BrowseComp-ZH, 29.5 on BrowseComp, 74.0 on xbench-DeepSearch, and 59.4 on WideSearch.
- Competitive with industrial models: Surpasses Tongyi DeepResearch on BrowseComp-ZH (48.4% vs. 46.7%), despite Tongyi DeepResearch being trained with extensive continual pre-training, supervised fine-tuning, and reinforcement learning.
- Fully open-sourced training data: The first work by a purely academic team to achieve state-of-the-art performance while simultaneously open-sourcing the full training data.
Performance
Contributors
9 commits
1 commits
Similar repos
OpenSeeker is an open-source search agent system that democratizes access to frontier search capabilities by fully open-sourcing its training data. We fine-tuned Qwen3-30B-A3B-Thinking-2507 with 11.7K training examples and achieved state-of-the-art performance on frontier search benchmarks:
54
10 commits
2 linked in READMEs
updated Mar 17, 2026
README
OpenSeeker: Democratizing Frontier Search Agents by Fully Open-Sourcing Training Data
OpenSeeker is an open-source search agent system that democratizes access to frontier search capabilities by fully open-sourcing its training data. We fine-tuned Qwen3-30B-A3B-Thinking-2507 with 11.7K training examples and achieved state-of-the-art performance on frontier search benchmarks:
Highlights
- Superior performance on search agent benchmarks: 48.4 on BrowseComp-ZH, 29.5 on BrowseComp, 74.0 on xbench-DeepSearch, and 59.4 on WideSearch.
- Competitive with industrial models: Surpasses Tongyi DeepResearch on BrowseComp-ZH (48.4% vs. 46.7%), despite Tongyi DeepResearch being trained with extensive continual pre-training, supervised fine-tuning, and reinforcement learning.
- Fully open-sourced training data: The first work by a purely academic team to achieve state-of-the-art performance while simultaneously open-sourcing the full training data.
Performance
Similar repos
Linked in READMEs
Contributors
9 commits
1 commits