AgentDecarbonizer: Carbon-Aware Execution for AI Agents

arXiv 2608.20566 ↗First posted 20 Aug 2026cs.LGcited by 0

On the map: LLM agents and tool use → Software engineering coding agents

Abstract (arXiv)

AI agents extend large language models from single prompt-response interactions to long-running, goaldirected workflows that issue many model calls, invoke tools, and interact with external environments. These workflows enable tasks such as software repair, data analysis, and experiment management, but their repeated model invocations can incur substantial carbon emissions. This paper characterizes the carbon emissions of OpenClaw agent workloads using WildClawBench, and shows that emissions depend on token consumption, context cache reuse, and the carbon intensity of the grid. Our characterization identifies deadline flexibility as an opportunity for carbon-aware execution: agent tasks can wait for lower-carbon-intensity periods or shift to lower-carbon grids. However, doing so requires handling uncertain execution time for temporal shifting and cached context recomputation during spatial shifting. We present AgentDecarbonizer, a carbon optimizer for AI agents that runs alongside OpenClaw. Given a task prompt and user-specified deadline, AgentDecarbonizer conservatively estimates task duration and selects deadline-feasible execution schedules, while accounting for cache recomputation overhead during spatial shifting. Evaluated on WildClawBench workloads with 60 agent tasks across four grids, AgentDecarbonizer reduces carbon emissions by up to 57.9 % compared with a carbon-agnostic baseline and by up to 37.5 % compared with a baseline that selects the carbon-optimal grid at task start time.

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 43 of its 85 references that are in the map. First posted on arXiv 20 Aug 2026.

Builds on

43 of 85 references.

Closest ancestors · 4

Same direction, newest first

Other references · 39

2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,373
2023A Survey on Large Language Model based Autonomous Agentscited by 2,242
2023WebArena: A Realistic Web Environment for Building Autonomous Agentscited by 2,006
2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,947
2023Mind2Web: Towards a Generalist Agent for the Webcited by 1,242
2023Instruction-Following Evaluation for Large Language Modelscited by 1,228
2024OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environmentscited by 1,195
2018MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modellingcited by 766
2024Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Servecited by 526

27 more

2023MLAgentBench: Evaluating Language Agents on Machine Learning Experimentationcited by 366
2023Prompt Cache: Modular Attention Reuse for Low-Latency Inferencecited by 268
2024Data Interpreter: An LLM Agent For Data Sciencecited by 225
2024CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusioncited by 223
2023CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Servingcited by 203
2024Mooncake: A KVCache-centric Disaggregated Architecture for LLM Servingcited by 196
2024Cost-Efficient Large Language Model Serving for Multi-turn Conversations with CachedAttentioncited by 163
2024DynamoLLM: Designing LLM Inference Clusters for Performance and Energy Efficiencycited by 112
2025How Hungry is AI? Benchmarking Energy, Water, and Carbon Footprint of LLM Inferencecited by 76
2026AgentDyn: Are Your Agent Security Defenses Deployable in Real-World Dynamic Environments?cited by 59
2024DA-Code: Agent Data Science Code Generation Benchmark for Large Language Modelscited by 58
2026WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluationcited by 37
2024Fast State Restoration in LLM Serving with HCachecited by 33
2026How Do AI Agents Spend Your Money? Analyzing and Predicting Token Consumption in Agentic Coding Taskscited by 33
2022Carbon Explorer: A Holistic Approach for Designing Carbon Aware Datacenterscited by 32
2025Measuring the environmental impact of delivering AI at Google Scalecited by 32
2025EcoServe: Designing Carbon-Aware AI Inference Systemscited by 19
2023Clover: Toward Sustainable AI with Carbon-Aware Machine Learning Inference Servicecited by 17
2021Let's Wait Awhile: How Temporal Workload Shifting Can Reduce Carbon Emissions in the Cloudcited by 14
2024Towards Sustainable Large Language Model Servingcited by 12
2024GreenLLM: Disaggregating Large Language Model Serving on Heterogeneous GPUs for Lower Carbon Emissionscited by 10
2025TPS-Bench: Evaluating AI Agents' Tool Planning & Scheduling Abilities in Compounding Taskscited by 9
2023On the Limitations of Carbon-Aware Temporal and Spatial Workload Shifting in the Cloudcited by 8
2024CASPER: Carbon-Aware Scheduling and Provisioning for Distributed Web Servicescited by 8
2025ContextCache: Context-Aware Semantic Cache for Multi-Turn Queries in Large Language Modelscited by 7
2025EnsembleCI: Ensemble Learning for Carbon Intensity Forecastingcited by 5
2026Carbon-Aware Compute--Power Scheduling for AI Data Centers with Microgrid Prosumer Operationscited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way