Agentic search over NASA EO-KG yields a 47k-pair benchmark where neural scoring plus LLM reranking raises MRR by over 5x then an additional 28%.
FinAgentBench: A Benchmark Dataset for Agentic Retrieval in Financial Question Answering
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
InKH architecture absorbs complexity into financial LLM agents, cutting latency 83%, token cost 82%, and stale knowledge 97% while raising task quality 0.108 on a 46k-episode synthetic benchmark versus baselines.
citing papers explorer
-
Absorbing Complexity: An Interaction-Native Knowledge Harness for Financial LLM Agents
InKH architecture absorbs complexity into financial LLM agents, cutting latency 83%, token cost 82%, and stale knowledge 97% while raising task quality 0.108 on a 46k-episode synthetic benchmark versus baselines.