DR-Venus: Towards Frontier Edge-Scale Deep Research Agents with Only 10K Open Data

About this episode

The episode discusses the development of DR-Venus, a deep research agent designed for edge-scale deployment using only 10K open data.

🤗 Upvotes: 38 | cs.LG, cs.AI, cs.CL, cs.IR Authors: Venus Team, Sunhao Dai, Yong Deng, Jinzhen Lin, Yusheng Song, Guoqing Wang, Xiaofeng Wu, Yuqi Zhou, Shuo Yang, Zhenzhe Ying, Zhanwei Zhang, Changhua Meng, Weiqiang Wang Title: DR-Venus: Towards Frontier Edge-Scale Deep Research Agents with Only 10K Open Data Arxiv: http://arxiv.org/abs/2604.19859v1 Abstract: 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…

People in this episode

Hosts: Jingwen Liang, Gengyu Wang

Topics covered

• deep research agents
• edge-scale deployment
• open data
• machine learning
• reinforcement learning

Keywords

• DR-Venus
• edge-scale
• deep learning
• open data
• reinforcement learning
• small language models

Mentioned in this episode

Organizations: Venus Team

More episodes of Daily Paper Cast

• EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments · June 13, 2026 · 24 min
• MiniMax Sparse Attention · June 13, 2026 · 26 min
• SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning · June 13, 2026 · 23 min
• InterleaveThinker: Reinforcing Agentic Interleaved Generation · June 13, 2026 · 21 min
• FORT-Searcher: Synthesizing Shortcut-Resistant Search Tasks for Training Deep Search Agents · June 13, 2026 · 23 min
• Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding? · June 13, 2026 · 20 min