# Watts and Debts of Agentic Frameworks: An Empirical Study (Registered Report)

arXiv: https://arxiv.org/abs/2606.10702 · HTML: https://mlsanity.com/paper/2606.10702/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 10 of its 35 references that are in the map.
- First posted on arXiv 9 Jun 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 10 of 10)

- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [AgentBench: Evaluating LLMs as Agents](https://mlsanity.com/paper/2308.03688/) (2023)
- [EffiBench: Benchmarking the Efficiency of Automatically Generated Code](https://mlsanity.com/paper/2402.02037/) (2024)
- [Agent Design Pattern Catalogue: A Collection of Architectural Patterns for Foundation Model based Agents](https://mlsanity.com/paper/2405.10467/) (2024)
- [Green AI: A Preliminary Empirical Study on Energy Consumption in DL Models Across Different Runtime Infrastructures](https://mlsanity.com/paper/2402.13640/) (2024)
- [An Empirical Study of Self-Admitted Technical Debt in Machine Learning Software](https://mlsanity.com/paper/2311.12019/) (2023)
- [SWEnergy: An Empirical Study on Energy Efficiency in Agentic Issue Resolution Frameworks with SLMs](https://mlsanity.com/paper/2512.09543/) (2025)
- [An Empirical Study on the Effectiveness of Large Language Models for SATD Identification and Classification](https://mlsanity.com/paper/2405.06806/) (2024)
- [PromptDebt: A Comprehensive Study of Technical Debt Across LLM Projects](https://mlsanity.com/paper/2509.20497/) (2025)
- [The Energy Footprint of LLM-Based Environmental Analysis: LLMs and Domain Products](https://mlsanity.com/paper/2604.00053/) (2026)

## Abstract (arXiv)

Context: Every agentic AI system shipped to production carries two hidden risks: accumulated Technical Debt (TD) and unmonitored runtime energy costs. While functional benchmarking is common, the empirical link between internal structural quality (specifically TD) and dynamic energy consumption during execution remains unexplored, creating a blind spot for practitioners and organizations managing sustainability and operational budgets at scale. Goal: We propose a confirmatory empirical study correlating Self-Admitted Technical Debt (SATD) with hardware-level runtime energy consumption across agentic frameworks, to determine whether code quality can drive energy-aware design decisions. Method: We will evaluate five open-source agentic frameworks by executing a standardized task suite in a strictly controlled environment. SATD will be extracted via automated Python-based comment mining and categorized via LLM-based classification using fine-tuned prompt, while runtime energy will be measured at the hardware level. Our study will investigate three core research questions: (RQ1) the presence of TD within these frameworks; (RQ2) the variance in runtime energy consumption across architectures; and (RQ3) the statistical correlation between a framework's TD and its task-level energy consumption. Conclusion: The findings will establish whether automated source code analysis can serve as a reliable, early-warning proxy for energy-efficient framework selection, thereby advancing both green software engineering and agentic AI quality research.