Architecture Matters More Than Scale: A Comparative Study of Retrieval and Memory Augmentation for Financial QA Under SME Compute Constraints

• URL: http://arxiv.org/abs/2604.17979v1
• Date: Mon, 20 Apr 2026 08:59:41 GMT
• Title: Architecture Matters More Than Scale: A Comparative Study of Retrieval and Memory Augmentation for Financial QA Under SME Compute Constraints
• Abstract summary: We show how different large language models (LLMs) perform across realistic financial tasks.<n>We propose a hybrid deployment framework that dynamically selects reasoning strategies to balance numerical accuracy, auditability, and infrastructure efficiency.
• Score: 8.036549927091286
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The rapid adoption of artificial intelligence (AI) and large language models (LLMs) is transforming financial analytics by enabling natural language interfaces for reporting, decision support, and automated reasoning. However, limited empirical understanding exists regarding how different LLM-based reasoning architectures perform across realistic financial workflows, particularly under the cost, accuracy, and compliance constraints faced by small and medium-sized enterprises (SMEs). SMEs typically operate within severe infrastructure constraints, lacking cloud GPU budgets, dedicated AI teams, and API-scale inference capacity, making architectural efficiency a first-class concern. To ensure practical relevance, we introduce an explicit SME-constrained evaluation setting in which all experiments are conducted using a locally hosted 8B-parameter instruction-tuned model without cloud-scale infrastructure. This design isolates the impact of architectural choices within a realistic deployment environment. We systematically compare four reasoning architectures: baseline LLM, retrieval-augmented generation (RAG), structured long-term memory, and memory-augmented conversational reasoning across both FinQA and ConvFinQA benchmarks. Results reveal a consistent architectural inversion: structured memory improves precision in deterministic, operand-explicit tasks, while retrieval-based approaches outperform memory-centric methods in conversational, reference-implicit settings. Based on these findings, we propose a hybrid deployment framework that dynamically selects reasoning strategies to balance numerical accuracy, auditability, and infrastructure efficiency, providing a practical pathway for financial AI adoption in resource-constrained environments.

Related papers

• Reward-Driven LLM Agent Workflows: Synthesizing POMDP Routing and Self-Correction for Autonomous Decision-Making [0.0]
  This paper addresses key technical challenges in current large language model (LLM) agent applications, including long-horizon planning, sparse reward attribution, and dynamic environmental interaction.<n>The proposed architecture is based on the synthesis of core AI paradigms: Visual, Language, Generative, Graph, Multimodal, Reinforcement, and Agent Intelligence.<n>Ultimately, the resulting architecture offers a practical, scalable reference framework for developing artificial intelligence technologies in complex, multi-step autonomous systems.
  arXiv  Detail & Related papers  (2026-07-19T02:51:41Z)
• The Illusion of Multi-Agent Advantage [63.92466143571383]
  We show that expert-architected Multi-Agent Systems (MAS) consistently outperforms automatically generated architectures in raw performance and cost-efficiency.<n>Existing evaluation frameworks mask critical architectural gaps and inefficiencies by failing to account for the marginal utility of increased computational cost.
  arXiv  Detail & Related papers  (2026-06-11T07:39:24Z)
• Automatic Ontology Construction Using LLMs as an External Layer of Memory, Verification, and Planning for Hybrid Intelligent Systems [0.0]
  This paper presents a hybrid architecture for intelligent systems in which large language models (LLMs) are extended with an external ontological memory layer.<n>The proposed approach constructs and maintains a structured knowledge graph using RDF/OWL representations, enabling persistent, verifiable, and semantically grounded reasoning.
  arXiv  Detail & Related papers  (2026-04-22T17:19:43Z)
• Unifying Ontology Construction and Semantic Alignment for Deterministic Enterprise Reasoning at Scale [1.5446818009325962]
  We introduce the large ontology model (LOM), a unified framework that seamlessly integrates ontology construction, semantic alignment, and logical reasoning.<n>LOM employs a construct-align-reason (CAR) pipeline, leveraging its unified architecture across all three stages.<n>We evaluate LOM on a comprehensive benchmark constructed from diverse real-world enterprise datasets.
  arXiv  Detail & Related papers  (2026-03-11T09:45:17Z)
• Doc2AHP: Inferring Structured Multi-Criteria Decision Models via Semantic Trees with LLMs [7.026862437055361]
  We propose Doc2AHP, a novel structured inference framework guided by AHP principles.<n>We introduce a multi-agent weighting mechanism coupled with an adaptive consistency optimization strategy to ensure the numerical consistency of weight allocation.<n> Empirical results demonstrate that Doc2AHP not only empowers non-expert users to construct high-quality decision models from scratch but also significantly outperforms direct generative baselines in both logical completeness and downstream task accuracy.
  arXiv  Detail & Related papers  (2026-01-23T06:20:23Z)
• Agentic AI Reasoning for Mobile Edge General Intelligence: Fundamentals, Approaches, and Directions [74.35421055079655]
  Large language models (LLMs) have enabled an emergence of agentic artificial intelligence (AI) with powerful reasoning and autonomous decision-making capabilities.<n>Mobile Edge General Intelligence (MEGI) brings real-time, privacy-preserving reasoning to the network edge.<n>We propose a joint optimization framework for efficient LLM reasoning deployment in MEGI.
  arXiv  Detail & Related papers  (2025-09-27T10:53:48Z)
• Technical Report: Facilitating the Adoption of Causal Inference Methods Through LLM-Empowered Co-Pilot [44.336297829718795]
  We introduce CATE-B, an open-source co-pilot system that uses large language models (LLMs) within an agentic framework to guide users through treatment effect estimation.<n>CATE-B assists in (i) constructing a structural causal model via causal discovery and LLM-based edge orientation, (ii) identifying robust adjustment sets through a novel Minimal Uncertainty Adjustment Set criterion, and (iii) selecting appropriate regression methods tailored to the causal structure and dataset characteristics.
  arXiv  Detail & Related papers  (2025-08-14T12:20:51Z)
• Computational Reasoning of Large Language Models [51.629694188014064]
  We introduce textbfTuring Machine Bench, a benchmark to assess the ability of Large Language Models (LLMs) to execute reasoning processes.<n> TMBench incorporates four key features: self-contained and knowledge-agnostic reasoning, a minimalistic multi-step structure, controllable difficulty, and a theoretical foundation based on Turing machine.
  arXiv  Detail & Related papers  (2025-04-29T13:52:47Z)
• On The Planning Abilities of OpenAI's o1 Models: Feasibility, Optimality, and Generalizability [59.72892401927283]
  We evaluate the planning capabilities of OpenAI's o1 models across a variety of benchmark tasks. Our results reveal that o1-preview outperforms GPT-4 in adhering to task constraints.
  arXiv  Detail & Related papers  (2024-09-30T03:58:43Z)
• Cognitive LLMs: Towards Integrating Cognitive Architectures and Large Language Models for Manufacturing Decision-making [51.737762570776006]
  LLM-ACTR is a novel neuro-symbolic architecture that provides human-aligned and versatile decision-making. Our framework extracts and embeds knowledge of ACT-R's internal decision-making process as latent neural representations. Our experiments on novel Design for Manufacturing tasks show both improved task performance as well as improved grounded decision-making capability.
  arXiv  Detail & Related papers  (2024-08-17T11:49:53Z)
• Mechanistic Design and Scaling of Hybrid Architectures [114.3129802943915]
  We identify and test new hybrid architectures constructed from a variety of computational primitives. We experimentally validate the resulting architectures via an extensive compute-optimal and a new state-optimal scaling law analysis. We find MAD synthetics to correlate with compute-optimal perplexity, enabling accurate evaluation of new architectures.
  arXiv  Detail & Related papers  (2024-03-26T16:33:12Z)
• An ontology-aided, natural language-based approach for multi-constraint BIM model querying [0.0]
  This paper presents a novel ontology-aided semantic to automatically map natural language queries (NLQs) that contain different constraints into computer-readable codes for querying complex BIM models. A case study about the design-checking of a real-world residential building demonstrates the practical value of the proposed approach in the construction industry.
  arXiv  Detail & Related papers  (2023-03-27T11:35:40Z)
• Edge-assisted Democratized Learning Towards Federated Analytics [67.44078999945722]
  We show the hierarchical learning structure of the proposed edge-assisted democratized learning mechanism, namely Edge-DemLearn. We also validate Edge-DemLearn as a flexible model training mechanism to build a distributed control and aggregation methodology in regions.
  arXiv  Detail & Related papers  (2020-12-01T11:46:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.