mlsanityData to 14 Oct 2026

CarbonCall: Sustainability-Aware Function Calling for Large Language Models on Edge Devices

arXiv 2504.20348 ↗First posted 29 Apr 2025cs.PF cs.AI cs.SYcited by 1

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

Large Language Models (LLMs) enable real-time function calling in edge AI systems but introduce significant computational overhead, leading to high power consumption and carbon emissions. Existing methods optimize for performance while neglecting sustainability, making them inefficient for energy-constrained environments. We introduce CarbonCall, a sustainability-aware function-calling framework that integrates dynamic tool selection, carbon-aware execution, and quantized LLM adaptation. CarbonCall adjusts power thresholds based on real-time carbon intensity forecasts and switches between model variants to sustain high tokens-per-second throughput under power constraints. Experiments on an NVIDIA Jetson AGX Orin show that CarbonCall reduces carbon emissions by up to 52%, power consumption by 30%, and execution time by 30%, while maintaining high efficiency.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 12 of its 20 references that are in the map. First posted on arXiv 29 Apr 2025.

Builds on

12 of 20 references.

References · 12

  1. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,947
  2. 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,332
  3. 2024The Faiss librarycited by 376
  4. 2018A Survey on Deep Learning for Named Entity Recognitioncited by 282
  5. 2021Sustainable AI: Environmental Implications, Challenges and Opportunitiescited by 242
  6. 2024LLM Inference Unveiled: Survey and Roofline Model Insightscited by 152
  7. 2024DynamoLLM: Designing LLM Inference Clusters for Performance and Energy Efficiencycited by 112
  8. 2024TinyAgent: Function Calling at the Edgecited by 58
  9. 2024LLMs in the Imaginarium: Tool Learning through Simulated Trial and Errorcited by 19
  10. 2023Clover: Toward Sustainable AI with Carbon-Aware Machine Learning Inference Servicecited by 17
  11. 2023GreenScale: Carbon-Aware Systems for Edge Computingcited by 9
  12. 2024LLM-dCache: Improving Tool-Augmented LLMs with GPT-Driven Localized Data Cachingcited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Carbon-Aware Routing for Function Calling in Edge-Cloud LLM Systemscited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2025Optimizing Large Language Models: Metrics, Energy Efficiency, and Case Study Insights
  2. 2024GreenLLM: Disaggregating Large Language Model Serving on Heterogeneous GPUs for Lower Carbon Emissions
  3. 2024Towards Sustainable Large Language Model Serving
  4. 2025EcoServe: Designing Carbon-Aware AI Inference Systems
  5. 2026Triple-Bottom-Line Sustainability of Language Models for Edge AI: A Comparison Between SLMs and Quantized LLMs
  6. 2024Less is More: Optimizing Function Calling for LLM Execution on Edge Devices
  7. 2026EnergyLens: Predictive Energy-Aware Exploration for Multi-GPU LLM Inference Optimization
  8. 2025Cache Your Prompt When It's Green: Carbon-Aware Caching for Large Language Model Serving