Papers

FundingClaw:多智能体框架自动生成多机构基金申请书

FundingClaw: Automated Grant Proposal Writing Agents System

Why we picked it

写基金申请书的朋友可以看看这个:一套多智能体系统,同一份研究简报能自动套 NSFC、NSF、KAKENHI、ERC 的模板出稿,还带大纲先行和自审环节。论文评估说接近人类水平,代码录用后开源,先收藏等技术细节放出再判断。

研究团队发布 FundingClaw,一个面向基金申请书写作的多智能体系统,已在 10 个研究课题上用八维度评分标准完成评估,成绩超过基线并缩小了与人类水平的差距。相关工作以论文形式发布在 arXiv(编号 2611.19157),代码将在论文录用后开源。

Body

系统核心是模板驱动的技能选择机制:Template Parser 解析任意资助机构的规范,为各写作阶段匹配合适技能,使同一份研究简报无需改动生成逻辑即可产出符合 NSFC、NSF、KAKENHI 或 ERC 格式的申请书。写作采用 blueprint-skeleton 策略,先起草结构化大纲再写正文,缓解长文生成中的语义漂移。流水线分三个顺序阶段产出立项依据、研究内容与研究基础部分,并对负责人学术记录做多源验证,支持基于 PDF 的代表性成果抽取,另设可选的人类反馈检查点与闭环自审。

对经常向不同机构重复提交申请的研究者而言,这类工具能减少同一内容在不同模板间的重复编码成本;论文中的评估基于十个课题与八维度量表,尚未提供具体基准数值,代码也未开源,实际效果仍待验证。

Original · arXiv cs.AI

FundingClaw: Automated Grant Proposal Writing Agents System

Grant proposal writing remains a manual, labor-intensive bottleneck: proposals must satisfy rigid, agency-specific templates, and the same intellectual content must be repeatedly re-encoded into incompatible formats across funding organizations. We introduce FundingClaw, a multi-agent framework built on template-driven skill selection, where a Template Parser ingests any agency's specification and selects the appropriate writing skills for each stage, so that one research brief can produce compliant proposals for NSFC, NSF, KAKENHI, or ERC without modifying generation logic. A blueprint-skeleton strategy drafts a structured outline before any prose is written, mitigating the semantic drift that plagues long-form generation. Three sequential stages produce the rationale, research content, and research foundation sections, with multi-source verification of the PI's record and optional PDF-grounded extraction of representative works. Optional human feedback checkpoints and a closed-loop self-review complete the pipeline. Evaluated on ten research topics with an eight-dimension rubric, FundingClaw outperforms the baseline, narrowing the gap with human level for laborious funding proposal. The code will be released upon acceptance.

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Papers" desk. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include FundingClaw, NSFC, agents, academic writing.

Source attribution: curated from arXiv cs.AI (@Ruizhi Liu, Siru Ge, Siran Wang, Qianli Ma, Zhipeng Zhang).