# FISHNET: Financial Intelligence from Sub-querying, Harmonizing, Neural-Conditioning, Expert Swarms, and Task Planning

arXiv: https://arxiv.org/abs/2410.19727 · HTML: https://mlsanity.com/paper/2410.19727/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 42 references that are in the map.
- First posted on arXiv 25 Oct 2024.

## Builds on (most cited first, 24 of 24)

- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [Code as Policies: Language Model Programs for Embodied Control](https://mlsanity.com/paper/2209.07753/) (2022)
- [BloombergGPT: A Large Language Model for Finance](https://mlsanity.com/paper/2303.17564/) (2023)
- [Understanding the planning of LLM agents: A survey](https://mlsanity.com/paper/2402.02716/) (2024)
- [FinBERT: Financial Sentiment Analysis with Pre-trained Language Models](https://mlsanity.com/paper/1908.10063/) (2019)
- [On the Planning Abilities of Large Language Models : A Critical Investigation](https://mlsanity.com/paper/2305.15771/) (2023)
- [Large Language Models as Tool Makers](https://mlsanity.com/paper/2305.17126/) (2023)
- [Large Language Models Understand and Can be Enhanced by Emotional Stimuli](https://mlsanity.com/paper/2307.11760/) (2023)
- [ToolNet: Connecting Large Language Models with Massive Tools via Tool Graph](https://mlsanity.com/paper/2403.00839/) (2024)
- [Modular Visual Question Answering via Code Generation](https://mlsanity.com/paper/2306.05392/) (2023)
- [On the Prospects of Incorporating Large Language Models (LLMs) in Automated Planning and Scheduling (APS)](https://mlsanity.com/paper/2401.02500/) (2024)
- [FlowMind: Automatic Workflow Generation with LLMs](https://mlsanity.com/paper/2404.13050/) (2024)
- [NegativePrompt: Leveraging Psychology for Large Language Models Enhancement via Negative Emotional Stimuli](https://mlsanity.com/paper/2405.02814/) (2024)
- [Towards Faithful and Robust LLM Specialists for Evidence-Based Question-Answering](https://mlsanity.com/paper/2402.08277/) (2024)
- [On the Evolution of Knowledge Graphs: A Survey and Perspective](https://mlsanity.com/paper/2310.04835/) (2023)
- [BuDDIE: A Business Document Dataset for Multi-task Information Extraction](https://mlsanity.com/paper/2404.04003/) (2024)
- [Is There No Such Thing as a Bad Question? H4R: HalluciBot For Ratiocination, Rewriting, Ranking, and Routing](https://mlsanity.com/paper/2404.12535/) (2024)
- [HiddenTables & PyQTax: A Cooperative Game and Dataset For TableQA to Ensure Scale and Data Privacy Across a Myriad of Taxonomies](https://mlsanity.com/paper/2406.10803/) (2024)
- [Financial Table Extraction in Image Documents](https://mlsanity.com/paper/2405.05260/) (2024)
- [Towards Collective Superintelligence: Amplifying Group IQ using Conversational Swarms](https://mlsanity.com/paper/2401.15109/) (2024)
- [A Review of the Family of Artificial Fish Swarm Algorithms: Recent Advances and Applications](https://mlsanity.com/paper/2011.05700/) (2020)
- [Directed Criteria Citation Recommendation and Ranking Through Link Prediction](https://mlsanity.com/paper/2403.18855/) (2024)
- [Innovative Application of Artificial Intelligence Technology in Bank Credit Risk Management](https://mlsanity.com/paper/2404.18183/) (2024)

## Built on by (most cited first, 5 of 5)

- [LAW: Legal Agentic Workflows for Custody and Fund Services Contracts](https://mlsanity.com/paper/2412.11063/) (2024)
- [QueryBandits for Hallucination Mitigation: Exploiting Semantic Features for No-Regret Rewriting](https://mlsanity.com/paper/2508.16697/) (2025)
- [TASER: Table Agents for Schema-guided Extraction and Recommendation](https://mlsanity.com/paper/2508.13404/) (2025)
- [No One Size Fits All: QueryBandits for Hallucination Mitigation](https://mlsanity.com/paper/2602.20332/) (2026)
- [Institutional Equity Holdings Prediction Using Node Affinities of Dynamic Graphs](https://mlsanity.com/paper/2607.12067/) (2026)

## Abstract (arXiv)

Financial intelligence generation from vast data sources has typically relied on traditional methods of knowledge-graph construction or database engineering. Recently, fine-tuned financial domain-specific Large Language Models (LLMs), have emerged. While these advancements are promising, limitations such as high inference costs, hallucinations, and the complexity of concurrently analyzing high-dimensional financial data, emerge. This motivates our invention FISHNET (Financial Intelligence from Sub-querying, Harmonizing, Neural-Conditioning, Expert swarming, and Task planning), an agentic architecture that accomplishes highly complex analytical tasks for more than 98,000 regulatory filings that vary immensely in terms of semantics, data hierarchy, or format. FISHNET shows remarkable performance for financial insight generation (61.8% success rate over 5.0% Routing, 45.6% RAG R-Precision). We conduct rigorous ablations to empirically prove the success of FISHNET, each agent's importance, and the optimized performance of assembling all agents. Our modular architecture can be leveraged for a myriad of use-cases, enabling scalability, flexibility, and data integrity that are critical for financial tasks.