EUVIMEDTutustu EUVIMEDiin
Crossref

Scoring-Driven Context Memory and Token Optimization for Rapid Prototyping of Scalable Multimodal Intelligent Agents: The MERIT Framework

Muthukumarapandian Chandrasekaran

Journal of Engineering Research and Sciences · 2026-11-19 · 5 (11) · 72-79

DOI: 10.55708/js0511005 ↗

At a glance

Journal article in Journal of Engineering Research and Sciences, published online on 2026-11-19. Written by Muthukumarapandian Chandrasekaran. 26 references.

TiivistelmäBibliografiset tiedotCiteRelated studies

Abstract (original language)

Frameworks such as AutoGen and CrewAI make it fast to assemble multi-agent systems built on large language models (LLMs), yet as a prototype scales the binding constraint shifts from reasoning quality to how context is selected, retained, and emitted under a finite token budget. This article extends a prior conference study that compared two prototyping frameworks and catalogued the open challenges of LLM-based agents. The conference work observed that coarse controls such as fixed conversation rounds and agent iteration limits bound context quantity without judging its value. We turn that observation into a design. We introduce MERIT, a scoring-driven framework with four components: Multi-Signal Value Scoring (MSVS), which scores each context item from recency, relevance, task criticality, provenance, and redundancy; Budget-Aware Retention Optimization (BARO), which selects a high-value subset under a token budget through a value-density knapsack; Stable-Prefix Emission (SPE), which orders retained items so that low-churn content forms a cache-reusable prefix; and a Prototype Scoring Loop (PSL), which ranks candidate configurations on a joint quality, cost, and latency objective using a successive-halving schedule. We provide the scoring model, pseudocode, complexity bounds, an integration design for existing substrates, an evaluation protocol, and a controlled synthetic study in which value-density retention holds about four times the ground-truth utility per token of recency truncation while stable-prefix emission recovers cross-turn cache reuse. MERIT replaces fixed round and iteration limits with a value-driven stopping rule and layers onto existing frameworks without changing their agent abstractions. Because MERIT reads each context item only through its token cost and its embedding, the same mechanisms apply to multimodal context such as images, audio, and document pages.

Cite

APA

Chandrasekaran, M. (2026). Scoring-Driven Context Memory and Token Optimization for Rapid Prototyping of Scalable Multimodal Intelligent Agents: The MERIT Framework. Journal of Engineering Research and Sciences, 5(11), 72-79. https://doi.org/10.55708/js0511005

Vancouver

Chandrasekaran M. Scoring-Driven Context Memory and Token Optimization for Rapid Prototyping of Scalable Multimodal Intelligent Agents: The MERIT Framework. Journal of Engineering Research and Sciences. 2026;5(11):72-79. doi:10.55708/js0511005

BibTeX
@article{Chandrasekaran2026,
  author = {Chandrasekaran, Muthukumarapandian},
  title = {Scoring-Driven Context Memory and Token Optimization for Rapid Prototyping of Scalable Multimodal Intelligent Agents: The MERIT Framework},
  journal = {Journal of Engineering Research and Sciences},
  year = {2026},
  volume = {5},
  number = {11},
  pages = {72--79},
  doi = {10.55708/js0511005}
}
Start for free →