AgentStop: Terminating Local AI Agents Early to Save Energy in Consumer Devices

TL;DR

AgentStop is a lightweight supervisor that predicts and terminates unlikely agent trajectories early, reducing energy consumption by 15-20% while maintaining high task success rates in local LLM-based agents.

Contribution

This work introduces AgentStop, a novel predictive early termination method that significantly improves energy efficiency of local LLM agents on consumer hardware.

Findings

AgentStop reduces energy use by 15-20% on consumer devices.

Early termination causes less than 5% drop in task utility.

AgentStop effectively balances efficiency and performance in web-based tasks.

Abstract

Autonomous agents powered by large language models (LLMs) are increasingly used to automate complex, multi-step tasks such as coding or web-based question answering. While remote, cloud-based agents offer scalability and ease of deployment, they raise privacy concerns, depend on network connectivity, and incur recurring API costs. Deploying agents locally on user devices mitigates these issues by preserving data privacy and eliminating usage-based fees. However, agentic workflows are far more resource-intensive than typical LLM interactions. Iterative reasoning, tool use, and failure retries substantially increase token consumption, often expending significant compute without successfully completing tasks. In this work, we investigate the time, token, and energy overhead of locally deployed LLM-based agents on consumer hardware. Our measurements show that agentic execution increases GPU power draw, temperature, and battery drain compared to single-inference workloads. To address this inefficiency, we introduce AgentStop, a lightweight efficiency supervisor that predicts and preemptively terminates trajectories unlikely to succeed. Leveraging low-cost execution signals, such as token-level log probabilities, AgentStop can reduce wasted energy by 15-20% with minimal impact on task performance (<5% utility drop) for challenging web-based question answering and coding benchmarks. These findings position predictive early termination as a practical mechanism for enabling sustainable, privacy-preserving LLM agents on user devices. Our project code and data are available at https://github.com/brave-experiments/AgentStop.