cd /news/artificial-intelligence/cifqa-a-deterministic-tool-grounded-… · home topics artificial-intelligence article
[ARTICLE · art-113770] src=arxiv.org ↗ pub= topic=artificial-intelligence verified=true sentiment=· neutral

CIFQA: A Deterministic Tool-Grounded Multi-Agent LLM Framework for Financial Query Answering

Researchers introduced CIFQA, a deterministic tool-grounded multi-agent LLM framework for financial query answering, achieving 95.54% accuracy on calculation-intensive queries and 90.87% overall accuracy on a fixed deposit benchmark, outperforming direct LLM baselines. The framework separates language understanding from numerical execution using specialized agents and Python-based tools, and a 17B open-source backbone within CIFQA outperformed larger frontier models, showing architectural design matters more than model scale.

read1 min views2 publishedAug 28, 2026

arXiv:2608.26114v1 Announce Type: new Abstract: Calculation-intensive financial question answering requires exact reasoning over structured rates, temporal conditions, numerical formulas, and rule-based constraints. Although Large Language Models (LLMs) perform strongly on natural language tasks, they often produce numerically incorrect yet plausible answers when solving multi-step financial calculations. To address this limitation, we introduce CIFQA (Calculation-Intensive Financial Query Answering), a deterministic tool-grounded multi-agent LLM framework for financial question answering. CIFQA separates language understanding from numerical execution by assigning specialized agents to query interpretation, routing, parameter extraction, computation planning, and response generation, while deterministic Python-based tools perform financial calculations and rule application. We instantiate CIFQA for fixed deposit query answering and evaluate it on a curated benchmark of fixed deposit queries. CIFQA achieves 95.54% accuracy on calculation-intensive queries and 90.87% overall accuracy, substantially outperforming direct LLM baselines even when provided with complete formulas, rate cards, and benchmark instructions. Ablation studies show that deterministic components such as exact rate lookup, tenure computation, rolling-year adjustment, and premature-withdrawal logic are critical contributors to performance. Notably, a 17B open-source backbone operating within CIFQA outperforms substantially larger frontier models evaluated with the same financial information, demonstrating that architectural design is a more important determinant of numerical reliability than model scale. While evaluated on fixed deposit queries, CIFQA provides a generalizable framework for calculation-intensive financial reasoning tasks.

── more in #artificial-intelligence 4 stories · sorted by recency
── more on @cifqa 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/cifqa-a-deterministi…] indexed:0 read:1min 2026-08-28 ·