cs.AINov 9, 2026

System Optimizations for Cost-Efficient Agent Harnesses

Authors: Jongseok Park, Jiaxiang Yu, Eric Zhou, Tony Hong, Sunga Kim, Yusuf Afifi, Ian Wong, Ion Stoica, 

Organizations: University of California, Berkeley · Northwestern University · University of Illinois at Urbana-Champaign

Abstract

AI agent harnesses play the critical role of providing LLMs with an interface to a computing environment. Recent studies show that AI agents' task-execution accuracy depends mostly on the LLM used, while harness-side variances such as system prompts or tools have minimal impact. Rather, such harness-side variances show a larger impact on the cost of agent executions, achieving cost reductions up to 2.6 times on the same model and task. To further explore these harness-side cost optimization opportunities, we analyze the cost accumulation patterns across various agent traces and identify system opportunities to reduce token use and LLM calls without modifying the model or affecting task accuracy. Based on this analysis, we design Agency, a harness interposition platform that provides a unified abstraction and allows easy and portable implementation of harness-side system optimizations on existing off-the-shelf harnesses such as Claude Code or OpenAI Codex. Using Agency, we implement proof-of-concept optimization techniques based on our analysis and achieve cost reductions up to 35% across various real-world benchmarks on existing harnesses without compromising accuracy.

Figures & tables

Appendix figures & tables6 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. EnvOpt: Automated Optimization for Agent Environments

    Nov 5, 2026Mingxuan Li, Huanzhi Mao, Qiuyang Mang +3LLM AgentsLLM Agent Efficiency

  2. HarnessPro: Recursive Harness Self-Improvement with Pareto Optimization for Performance-Cost Trade-offs

    Oct 19, 2026Zhuoshi Pan, ZhiYuan Feng, Yukuo Cen +6Agent Harness OptimizationAgent Harness Self-Evolution