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

• URL: http://arxiv.org/abs/2605.04036v1
• Date: Tue, 05 May 2026 17:55:25 GMT
• Title: OpenSeeker-v2: Pushing the Limits of Search Agents with Informative and High-Difficulty Trajectories
• Abstract summary: We show that a simple supervised fine-tuning approach could be surprisingly powerful for training frontier search agents.<n>Our OpenSeeker-v2 achieves state-of-the-art performance across 4 benchmarks (30B-sized agents with ReAct paradigm): 46.4% on BrowseComp, 58.1% on BrowseComp-ZH, 34.6% on Humanity's Last Exam, and 78.0% on xbench.<n>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.
• Score: 43.841018840819494
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• OpenThoughts-Agent: Data Recipes for Agentic Models [99.10629645072653]
  OT-Agent project is a fully open data curation pipeline for training agentic models.<n>We conduct more than 100 controlled ablation experiments to investigate each stage of the pipeline.<n>We assemble a training set of 100K examples from our pipeline and fine-tune Qwen3-32B on this dataset.
  arXiv  Detail & Related papers  (2026-06-23T17:34:29Z)
• OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents [50.79529228477821]
  We introduce OpenSearch-VL, a fully open-source recipe for training frontier multimodal deep search agents with agentic reinforcement learning.<n>First, we curated a dedicated pipeline to construct high-quality training data through Wikipedia path sampling, fuzzy entity rewriting, and source-anchor visual grounding.<n>Besides, we design a diverse tool environment that unifies text search, image search, OCR, cropping, sharpening, super-resolution, and perspective correction.
  arXiv  Detail & Related papers  (2026-05-06T17:50:38Z)
• DR-Venus: Towards Frontier Edge-Scale Deep Research Agents with Only 10K Open Data [38.62562667728391]
  Edge-scale deep research agents based on small language models are attractive for real-world deployment due to their advantages in cost, latency, and privacy.<n>We present DR-Venus, a frontier 4B deep research agent for edge-scale deployment, built entirely on open data.
  arXiv  Detail & Related papers  (2026-04-21T17:59:02Z)
• OpenSeeker: Democratizing Frontier Search Agents by Fully Open-Sourcing Training Data [43.955144962666196]
  We introduce OpenSeeker, the first fully open-source search agent (i.e., model and data) that achieves frontier-level performance.<n>We show that OpenSeeker achieves state-of-the-art performance across multiple benchmarks including BrowseComp, BrowseComp-ZH, xbench-DeepSearch, and WideSearch.<n>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.
  arXiv  Detail & Related papers  (2026-03-16T17:52:04Z)
• AgentCPM-Explore: Realizing Long-Horizon Deep Exploration for Edge-Scale Agents [75.67445299298949]
  AgentCPM-Explore is a compact 4B agent model with high knowledge density and strong exploration capability.<n>We introduce a holistic training framework featuring parameter-space model fusion, reward signal denoising, and contextual information refinement.<n>AgentCPM-Explore achieves state-of-the-art (SOTA) performance among 4B-class models, matches or surpasses 8B-class SOTA models on four benchmarks, and even outperforms larger-scale models such as Claude-4.5-Sonnet or DeepSeek-v3.2 in five benchmarks.
  arXiv  Detail & Related papers  (2026-02-06T08:24:59Z)
• OffSeeker: Online Reinforcement Learning Is Not All You Need for Deep Research Agents [68.79728889531806]
  State-of-the-art performance typically relies on online reinforcement learning (RL)<n>We introduce a fully open-source suite designed for effective offline training.<n>Our core contributions include DeepForge, a ready-to-use task synthesis framework that generates large-scale research queries without heavy preprocessing.
  arXiv  Detail & Related papers  (2026-01-26T13:13:59Z)
• LLMOrbit: A Circular Taxonomy of Large Language Models -From Scaling Walls to Agentic AI Systems [3.183924309596046]
  This survey examines over 50 models across 15 organizations through eight interconnected orbital dimensions.<n>We identify three critical crises: (1) data scarcity (9-27T tokens depleted by 2026-2028), (2) exponential cost growth ($3M to $300M+ in 5 years), and (3) unsustainable energy consumption (22x increase)<n>Three paradigm shifts emerge: (1) post-training gains (RLHF, GRPO, pure RL contribute substantially, DeepSeek-R1 achieving 79.8% MATH), (2) efficiency revolution (MoE routing 18x efficiency, Multi-head Latent Attention 8x KV cache compression enables GPT-4-level performance at $
  arXiv  Detail & Related papers  (2026-01-20T15:06:19Z)
• 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)
• Skywork Open Reasoner 1 Technical Report [51.403686909760914]
  We present Skywork-OR1, an effective and scalable reinforcement learning (RL) implementation for long Chain-of-Thought (CoT) models.<n>Building on the DeepSeek-R1-Distill model series, our RL approach achieves notable performance gains.<n>Our Skywork-OR1-32B model surpasses both DeepSeek-R1 and Qwen3-32B on the AIME24 and AIME25 benchmarks.
  arXiv  Detail & Related papers  (2025-05-28T12:56:04Z)
• Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn't [0.0]
  Our study investigates the potential of reinforcement learning to improve reasoning in small language models (LLMs)<n>Training on 4 NVIDIA A40 GPUs (48 GB VRAM each) within 24 hours resulted in rapid reasoning gains.<n>These findings highlight the efficacy of RL-based fine-tuning for small LLMs, offering a cost-effective alternative to large-scale approaches.
  arXiv  Detail & Related papers  (2025-03-20T15:13:23Z)

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.