FundingClaw: Automated Grant Proposal Writing Agents System
Organizations: Shanghai Jiao Tong University
Abstract
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.
Figures & tables
| Dim. | Focus | Pts |
| D1 | Rationale and scientific value | 13 |
| D2 | Research content and innovation | 16 |
| D3 | Plan and feasibility | 15 |
| D4 | Research foundation | 9 |
| D5 | Writing standards | 4 |
| D6 | Figure quality | 5 |
| Judge Generator | Sonnet 4.6 | GPT-5.5 | DeepSeek |
| Claude Sonnet 4.6 | 69.20% | 51.92% | 68.40% |
| GPT-5.5 | 68.42% | 48.21% | 67.37% |
| DeepSeek V4 Flash | 74.15% | 52.60% | 71.16% |
Appendix figures & tables2 assets
Supplementary material from the paper’s appendix.
Appendix
| Condition | Function of the removed or replaced component |
| C1 w/o Literature Prefetch | Assembles a candidate bibliography of at least 60 papers by issuing structured web search queries derived from the research brief, producing a per-direction literature memo that feeds all analytical and writing skills. |
| C2 w/o Significance Analysis | Decomposes the research motivation along a four-dimensional causal chain from observed phenomena, practical urgency, gaps in existing approaches, to the value of further study, producing a significance memo containing only citation-anchored factual observations. |
| C3 w/o Landscape Analysis | Maps competing research groups, constructs a claims-evidence matrix, and extracts concrete gap statements from the retrieved literature, grounding the survey in a structured view of the field. |
| C4 w/o All Pre-analysis (C2+C3) | Removes both the significance and the landscape analysis together, leaving only the raw prefetched literature memo without any structured analytical layer. |
| C5 w/o Figures | Generates the motivation and workflow figures and embeds them into the rationale and content sections, providing the visual argument that supports the written claims. |
| C6 w/o Auto-Review | Runs the closed-loop self-review that evaluates the draft across logical coherence, compliance, scientific merit, and feasibility, then applies iterative fixes before compilation. |
| System | Target Output | Planning Strategy | Template Adaptation | Literature & Analysis | Author Grounding | Human-in-the-Loop |
| ResearchAgent Baek et al. (2024) | Research Ideas | Iterative refinement | Fixed JSON schema | KG & entity-based search | N/A (Idea focus) | None (autonomous) |
| AutoSurvey Wang et al. (2024c) | Survey Papers | Hierarchical outline | Static L a T e X style | Topic-clustered RAG | N/A (Public literature) | Autonomous |
| CycleResearcher Weng et al. (2025) | Full Manuscripts | Section-sequential | Fixed conference style | ArXiv keyword search | N/A (Standard drafting) | Autonomous review |
| ARIS Yang et al. (2026) | Full Manuscripts | Modular skill graph | Predefined workflow | Reusable search skills | N/A (Experiment focus) | Multi-agent loop |
| FundingClaw (Ours) | Grant Proposals | Budgeted Blueprint | Decoupled Parser | Prefetch + Causal Memo | Multi-DB + PDF Parsing | Stage Checkpoints |
Text Generation
Text generation studies methods for producing coherent, useful language from prompts, data, and dialogue context.
See all 449 papers