A Compound AI Agent for Conversational Grant Discovery

2026-05-04

AI Summary

This work addresses the inefficiency researchers face when manually retrieving funding information across fragmented and heterogeneous grant portals. To overcome this challenge, the authors propose the first composite AI system tailored for scientific funding discovery, which innovatively integrates an LLM-driven web-browsing agent, the ReAct reasoning framework, and a hallucination-resistant hybrid search mechanism. The system automatically aggregates and structures metadata from nearly 12,000 funding opportunities, enabling multi-turn conversational queries and contextual parsing of PDF documents. Deployed to over 3,000 users, the system reduces average search time from 30–45 minutes to under 10 minutes, substantially enhancing both retrieval efficiency and result reliability.

Abstract

Research funding discovery remains fundamentally fragmented: researchers navigate disparate agency portals (e.g., in the United States, NSF, NIH, DARPA, Grants.gov, and many others) with heterogeneous interfaces, search capabilities, and data schemas. We present a compound AI system that unifies this landscape through two tightly coupled components: (1) an aggregation layer that autonomously collects, normalizes, and indexes almost 12,000 federal and nonprofit opportunities from fragmented sources via LLM-equipped browser agents, maintaining a biweekly-updated unified database; and (2) an agentic ReAct-based query processing layer that interprets research context (including from PDF documents) and employs hybrid search combining a structured index with selective web search to retrieve relevant opportunities - while avoiding LLM hallucination. The conversational interface supports iterative refinement through multi-turn interactions, allowing researchers to progressively apply constraints without reformulating their core research description. Results stream in real time with full transparency of intermediate reasoning, enabling appropriate calibration of user trust. Currently used by almost 3,000+ users, our approach demonstrates the feasibility of compound AI in reducing grant discovery time from 30--45 minutes (manual, fragmented portal searches) to under 10 minutes (unified, conversational search).

Problem

• grant discovery
• fragmented funding sources
• research funding
• heterogeneous interfaces
• information fragmentation

Innovation

• Compound AI
• Grant Discovery
• ReAct Agent
• Hybrid Search
• LLM Hallucination Mitigation