AgentCPM-Report: Interleaving Drafting and Deepening for Open-Ended Deep Research
- URL: http://arxiv.org/abs/2602.06540v1
- Date: Fri, 06 Feb 2026 09:45:04 GMT
- Title: AgentCPM-Report: Interleaving Drafting and Deepening for Open-Ended Deep Research
- Authors: Yishan Li, Wentong Chen, Yukun Yan, Mingwei Li, Sen Mei, Xiaorong Wang, Kunpeng Liu, Xin Cong, Shuo Wang, Zhong Zhang, Yaxi Lu, Zhenghao Liu, Yankai Lin, Zhiyuan Liu, Maosong Sun,
- Abstract summary: AgentCPM-Report is a lightweight yet high-performing local solution composed of a framework that mirrors the human writing process.<n>Our framework uses a Writing As Reasoning Policy (WARP), which enables models to dynamically revise outlines.<n>Experiments on DeepResearch Bench, DeepConsult, and DeepResearch Gym demonstrate that AgentCPM-Report outperforms leading closed-source systems.
- Score: 85.51475655916026
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Generating deep research reports requires large-scale information acquisition and the synthesis of insight-driven analysis, posing a significant challenge for current language models. Most existing approaches follow a plan-then-write paradigm, whose performance heavily depends on the quality of the initial outline. However, constructing a comprehensive outline itself demands strong reasoning ability, causing current deep research systems to rely almost exclusively on closed-source or online large models. This reliance raises practical barriers to deployment and introduces safety and privacy concerns for user-authored data. In this work, we present AgentCPM-Report, a lightweight yet high-performing local solution composed of a framework that mirrors the human writing process and an 8B-parameter deep research agent. Our framework uses a Writing As Reasoning Policy (WARP), which enables models to dynamically revise outlines during report generation. Under this policy, the agent alternates between Evidence-Based Drafting and Reasoning-Driven Deepening, jointly supporting information acquisition, knowledge refinement, and iterative outline evolution. To effectively equip small models with this capability, we introduce a Multi-Stage Agentic Training strategy, consisting of cold-start, atomic skill RL, and holistic pipeline RL. Experiments on DeepResearch Bench, DeepConsult, and DeepResearch Gym demonstrate that AgentCPM-Report outperforms leading closed-source systems, with substantial gains in Insight.
Related papers
- DeepSynth-Eval: Objectively Evaluating Information Consolidation in Deep Survey Writing [53.85037373860246]
We introduce Deep Synth-Eval, a benchmark designed to objectively evaluate information consolidation capabilities.<n>We propose a fine-grained evaluation protocol using General Checklists (for factual coverage) and Constraint Checklists (for structural organization)<n>Our results demonstrate that agentic plan-and-write significantly outperform single-turn generation.
arXiv Detail & Related papers (2026-01-07T03:07:52Z) - Step-DeepResearch Technical Report [90.50586290399683]
We introduce Step-DeepResearch, a cost-effective, end-to-end agent.<n>We propose a Data Synthesis Strategy Based on Atomic Capabilities to reinforce planning and report writing.<n>To bridge the evaluation gap in the Chinese domain, we establish ADR-Bench for realistic deep research scenarios.
arXiv Detail & Related papers (2025-12-23T16:32:27Z) - A Hierarchical Tree-based approach for creating Configurable and Static Deep Research Agent (Static-DRA) [0.0]
This paper introduces the Static Deep Research Agent (Static-DRA), a novel solution built upon a hierarchical Tree-based static workflow.<n>The core contribution is the integration of two user-tunable parameters, Depth and Breadth, which provide granular control over the research intensity.<n>The agent's architecture, comprising Supervisor, Independent, and Worker agents, facilitates effective multi-hop information retrieval.
arXiv Detail & Related papers (2025-12-03T15:37:13Z) - WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research [73.58638285105971]
This paper tackles textbfopen-ended deep research (OEDR), a complex challenge where AI agents must synthesize vast web-scale information into insightful reports.<n>We introduce textbfWebWeaver, a novel dual-agent framework that emulates the human research process.<n>Our framework establishes a new state-of-the-art across major OEDR benchmarks, including DeepResearch Bench, DeepConsult, and DeepResearchGym.
arXiv Detail & Related papers (2025-09-16T17:57:21Z) - WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learning [73.91893534088798]
WebSailor is a complete post-training methodology designed to instill this crucial capability.<n>Our approach involves generating novel, high-uncertainty tasks through structured sampling and information obfuscation.<n>WebSailor significantly outperforms all open-source agents in complex information-seeking tasks.
arXiv Detail & Related papers (2025-09-16T17:57:03Z) - Deep Research Agents: A Systematic Examination And Roadmap [109.53237992384872]
Deep Research (DR) agents are designed to tackle complex, multi-turn informational research tasks.<n>In this paper, we conduct a detailed analysis of the foundational technologies and architectural components that constitute DR agents.
arXiv Detail & Related papers (2025-06-22T16:52:48Z) - WebThinker: Empowering Large Reasoning Models with Deep Research Capability [109.8504165631888]
WebThinker is a deep research agent that empowers LRMs to autonomously search the web, navigate among web pages, and draft reports during the reasoning process.<n>It also employs an Autonomous Think-Search-and-Draft strategy, allowing the model to seamlessly interleave reasoning, information gathering, and report writing in real time.<n>Our approach enhances LRM reliability and applicability in complex scenarios, paving the way for more capable and versatile deep research systems.
arXiv Detail & Related papers (2025-04-30T16:25:25Z) - Towards Human-Level Understanding of Complex Process Engineering Schematics: A Pedagogical, Introspective Multi-Agent Framework for Open-Domain Question Answering [0.0]
In the chemical and process industries, Process Flow Diagrams (PFDs) and Piping and Instrumentation Diagrams (P&IDs) are critical for design, construction, and maintenance.
Recent advancements in Generative AI have shown promise in understanding and interpreting process diagrams for Visual Question Answering (VQA)
We propose a secure, on-premises enterprise solution using a hierarchical, multi-agent Retrieval Augmented Generation (RAG) framework.
arXiv Detail & Related papers (2024-08-24T19:34:04Z)
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.