# Step-DeepResearch Technical Report

arXiv: https://arxiv.org/abs/2512.20491 · HTML: https://mlsanity.com/paper/2512.20491/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 34 references that are in the map.
- First posted on arXiv 23 Dec 2025.

## Builds on (most cited first, 13 of 13)

- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (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)
- [GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models](https://mlsanity.com/paper/2508.06471/) (2025)
- [Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains](https://mlsanity.com/paper/2507.17746/) (2025)
- [KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation](https://mlsanity.com/paper/1911.06136/) (2019)
- [DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments](https://mlsanity.com/paper/2504.03160/) (2025)
- [WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning](https://mlsanity.com/paper/2411.02337/) (2024)
- [DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents](https://mlsanity.com/paper/2506.11763/) (2025)
- [ResearchRubrics: A Benchmark of Prompts and Rubrics For Evaluating Deep Research Agents](https://mlsanity.com/paper/2511.07685/) (2025)
- [ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks](https://mlsanity.com/paper/2508.15804/) (2025)
- [Agent Data Protocol: Unifying Datasets for Diverse, Effective Fine-tuning of LLM Agents](https://mlsanity.com/paper/2510.24702/) (2025)

## Built on by (most cited first, 12 of 12)

- [MiroThinker-1.7 & H1: Towards Heavy-Duty Research Agents via Verification](https://mlsanity.com/paper/2603.15726/) (2026)
- [Inference-Time Scaling of Verification: Self-Evolving Deep Research Agents via Test-Time Rubric-Guided Verification](https://mlsanity.com/paper/2601.15808/) (2026)
- [Agentic Aggregation for Parallel Scaling of Long-Horizon Agentic Tasks](https://mlsanity.com/paper/2604.11753/) (2026)
- [Time to REFLECT: Can We Trust LLM Judges for Evidence-based Research Agents?](https://mlsanity.com/paper/2605.19196/) (2026)
- [S1-DeepResearch: Beyond Search, Toward Real-World Long-Horizon Research Agents](https://mlsanity.com/paper/2606.15367/) (2026)
- [Yunque DeepResearch Technical Report](https://mlsanity.com/paper/2601.19578/) (2026)
- [ScholarGym: Benchmarking Large Language Model Capabilities in the Information-Gathering Stage of Deep Research](https://mlsanity.com/paper/2601.21654/) (2026)
- [SearchArt: Training Long-Horizon Search Agent with Scalable Synthetic and Verified Task](https://mlsanity.com/paper/2607.24850/) (2026)
- [AgentCPM-Report: Interleaving Drafting and Deepening for Open-Ended Deep Research](https://mlsanity.com/paper/2602.06540/) (2026)
- [IntPro: A Proxy Agent for Context-Aware Intent Understanding via Retrieval-conditioned Inference](https://mlsanity.com/paper/2603.03325/) (2026)
- [Towards Autonomous Business Intelligence via Data-to-Insight Discovery Agent](https://mlsanity.com/paper/2605.07202/) (2026)
- [Mint-Agent: Introducing Finance-Native Agentic Foundation Models](https://mlsanity.com/paper/2608.16386/) (2026)

## Abstract (arXiv)

As LLMs shift toward autonomous agents, Deep Research has emerged as a pivotal metric. However, existing academic benchmarks like BrowseComp often fail to meet real-world demands for open-ended research, which requires robust skills in intent recognition, long-horizon decision-making, and cross-source verification. To address this, we introduce Step-DeepResearch, a cost-effective, end-to-end agent. We propose a Data Synthesis Strategy Based on Atomic Capabilities to reinforce planning and report writing, combined with a progressive training path from agentic mid-training to SFT and RL. Enhanced by a Checklist-style Judger, this approach significantly improves robustness. Furthermore, to bridge the evaluation gap in the Chinese domain, we establish ADR-Bench for realistic deep research scenarios. Experimental results show that Step-DeepResearch (32B) scores 61.4% on Scale AI Research Rubrics. On ADR-Bench, it significantly outperforms comparable models and rivals SOTA closed-source models like OpenAI and Gemini DeepResearch. These findings prove that refined training enables medium-sized models to achieve expert-level capabilities at industry-leading cost-efficiency.