# DR-Venus: Towards Frontier Edge-Scale Deep Research Agents with Only 10K Open Data arXiv: https://arxiv.org/abs/2604.19859 ยท HTML: https://mlsanity.com/paper/2604.19859/ ## Key facts - Cited by 5 papers in the map (data through 14 Oct 2026). - Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. - Builds on 29 of its 29 references that are in the map. - First posted on arXiv 21 Apr 2026. ## Placed in - LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/) ## Builds on (most cited first, 29 of 29) - [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024) - [GAIA: a benchmark for General AI Assistants](https://mlsanity.com/paper/2311.12983/) (2023) - [DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models](https://mlsanity.com/paper/2512.02556/) (2025) - [BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents](https://mlsanity.com/paper/2504.12516/) (2025) - [Kimi K2.5: Visual Agentic Intelligence](https://mlsanity.com/paper/2602.02276/) (2026) - [GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models](https://mlsanity.com/paper/2508.06471/) (2025) - [Tool Learning with Foundation Models](https://mlsanity.com/paper/2304.08354/) (2023) - [WebSailor: Navigating Super-human Reasoning for Web Agent](https://mlsanity.com/paper/2507.02592/) (2025) - [Tool Learning with Large Language Models: A Survey](https://mlsanity.com/paper/2405.17935/) (2024) - [BrowseComp-ZH: Benchmarking Web Browsing Ability of Large Language Models in Chinese](https://mlsanity.com/paper/2504.19314/) (2025) - [xbench: Tracking Agents Productivity Scaling with Profession-Aligned Real-World Evaluations](https://mlsanity.com/paper/2506.13651/) (2025) - [WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents](https://mlsanity.com/paper/2509.06501/) (2025) - [MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling](https://mlsanity.com/paper/2511.11793/) (2025) - [Tongyi DeepResearch Technical Report](https://mlsanity.com/paper/2510.24701/) (2025) - [WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learning](https://mlsanity.com/paper/2509.13305/) (2025) - [DeepDive: Advancing Deep Search Agents with Knowledge Graphs and Multi-Turn RL](https://mlsanity.com/paper/2509.10446/) (2025) - [DeepSearchQA: Bridging the Comprehensiveness Gap for Deep Research Agents](https://mlsanity.com/paper/2601.20975/) (2026) - [REDSearcher: A Scalable and Cost-Efficient Framework for Long-Horizon Search Agents](https://mlsanity.com/paper/2602.14234/) (2026) - [Information Gain-based Policy Optimization: A Simple and Effective Approach for Multi-Turn Search Agents](https://mlsanity.com/paper/2510.14967/) (2025) - [OpenSeeker: Democratizing Frontier Search Agents by Fully Open-Sourcing Training Data](https://mlsanity.com/paper/2603.15594/) (2026) - [OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis](https://mlsanity.com/paper/2603.20278/) (2026) - [Deep Research: A Systematic Survey](https://mlsanity.com/paper/2512.02038/) (2025) - [Beyond Turn Limits: Training Deep Search Agents with Dynamic Context Window](https://mlsanity.com/paper/2510.08276/) (2025) - [Marco DeepResearch: Unlocking Efficient Deep Research Agents via Verification-Centric Design](https://mlsanity.com/paper/2603.28376/) (2026) - [OffSeeker: Online Reinforcement Learning Is Not All You Need for Deep Research Agents](https://mlsanity.com/paper/2601.18467/) (2026) - [AgentCPM-Explore: Realizing Long-Horizon Deep Exploration for Edge-Scale Agents](https://mlsanity.com/paper/2602.06485/) (2026) - [RE-TRAC: REcursive TRAjectory Compression for Deep Search Agents](https://mlsanity.com/paper/2602.02486/) (2026) - [Nanbeige4.1-3B: A Small General Model that Reasons, Aligns, and Acts](https://mlsanity.com/paper/2602.13367/) (2026) - [Search More, Think Less: Rethinking Long-Horizon Agentic Search for Efficiency and Generalization](https://mlsanity.com/paper/2602.22675/) (2026) ## Built on by (most cited first, 5 of 5) - [PBSD: Privileged Bayesian Self-Distillation for Long-Horizon Credit Assignment](https://mlsanity.com/paper/2606.09348/) (2026) - [ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment](https://mlsanity.com/paper/2608.05102/) (2026) - [DuMate-DeepResearch: An Auditable Multi-Agent System with Recursive Search and Rubric-Grounded Reasoning](https://mlsanity.com/paper/2606.07299/) (2026) - [When Cloud Agents Meet Device Agents: Lessons from Hybrid Multi-Agent Systems](https://mlsanity.com/paper/2605.30102/) (2026) - [Boosting Deepresearch and LongContext Ability with Self-Generated Deepresearch Rollouts Traces](https://mlsanity.com/paper/2609.20844/) (2026) ## Abstract (arXiv) 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. In this work, we study how to train a strong small deep research agent under limited open-data by improving both data quality and data utilization. We present DR-Venus, a frontier 4B deep research agent for edge-scale deployment, built entirely on open data. Our training recipe consists of two stages. In the first stage, we use agentic supervised fine-tuning (SFT) to establish basic agentic capability, combining strict data cleaning with resampling of long-horizon trajectories to improve data quality and utilization. In the second stage, we apply agentic reinforcement learning (RL) to further improve execution reliability on long-horizon deep research tasks. To make RL effective for small agents in this setting, we build on IGPO and design turn-level rewards based on information gain and format-aware regularization, thereby enhancing supervision density and turn-level credit assignment. Built entirely on roughly 10K open-data, DR-Venus-4B significantly outperforms prior agentic models under 9B parameters on multiple deep research benchmarks, while also narrowing the gap to much larger 30B-class systems. Our further analysis shows that 4B agents already possess surprisingly strong performance potential, highlighting both the deployment promise of small models and the value of test-time scaling in this setting. We release our models, code, and key recipes to support reproducible research on edge-scale deep research agents.