GA4GC: Greener Agent for Greener Code via Multi-Objective Configuration Optimization

• URL: http://arxiv.org/abs/2510.04135v1
• Date: Sun, 05 Oct 2025 10:34:30 GMT
• Title: GA4GC: Greener Agent for Greener Code via Multi-Objective Configuration Optimization
• Authors: Jingzhi Gong, Yixin Bian, Luis de la Cal, Giovanni Pinna, Anisha Uteem, David Williams, Mar Zamorano, Karine Even-Mendoza, W. B. Langdon, Hector Menendez, Federica Sarro,
• Abstract summary: This paper introduces GA4GC, the first framework to systematically optimize coding agent runtime (greener agent) and code performance (greener code) trade-offs.<n> Evaluation on the SWE-Perf benchmark demonstrates up to 135x hypervolume improvement, reducing agent runtime by 37.7% while improving correctness.
• Score: 3.3200397756832047
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Coding agents powered by LLMs face critical sustainability and scalability challenges in industrial deployment, with single runs consuming over 100k tokens and incurring environmental costs that may exceed optimization benefits. This paper introduces GA4GC, the first framework to systematically optimize coding agent runtime (greener agent) and code performance (greener code) trade-offs by discovering Pareto-optimal agent hyperparameters and prompt templates. Evaluation on the SWE-Perf benchmark demonstrates up to 135x hypervolume improvement, reducing agent runtime by 37.7% while improving correctness. Our findings establish temperature as the most critical hyperparameter, and provide actionable strategies to balance agent sustainability with code optimization effectiveness in industrial deployment.

Related papers

• SCOPE: Prompt Evolution for Enhancing Agent Effectiveness [53.75986399936395]
  Large Language Model (LLM) agents are increasingly deployed in environments that generate massive, dynamic contexts.<n>While agents have access to this context, their static prompts lack the mechanisms to manage it effectively.<n>We introduce textbfSCOPE (Self-evolving Context Optimization via Prompt Evolution)<n>We propose a Dual-Stream mechanism that balances tactical specificity (resolving immediate errors) with strategic generality (evolving long-term principles)
  arXiv  Detail & Related papers  (2025-12-17T12:25:05Z)
• SemOpt: LLM-Driven Code Optimization via Rule-Based Analysis [7.451702651736553]
  SemOpt is a framework that leverages static program analysis to precisely identify optimizable code segments, retrieve the corresponding optimization strategies, and generate the optimized results.<n>On our benchmark containing 151 optimization tasks, SemOpt demonstrates its effectiveness under different LLMs by increasing the number of successful optimizations by 1.38 to 28 times compared to the baseline.
  arXiv  Detail & Related papers  (2025-10-18T07:44:18Z)
• Curriculum-Guided Reinforcement Learning for Synthesizing Gas-Efficient Financial Derivatives Contracts [1.1565257196553245]
  This paper introduces a Reinforcement Learning framework to generate smart contracts directly from Common Domain Model (CDM) specifications.<n>We employ a Proximal Policy Optimization (PPO) agent that learns to select optimal code snippets from a pre-defined library.<n>Our empirical results show the RL agent learns to generate contracts with significant gas savings, achieving cost reductions of up to 35.59% on unseen test data.
  arXiv  Detail & Related papers  (2025-09-28T17:01:55Z)
• A Preference-Driven Methodology for High-Quality Solidity Code Generation [13.075308321845505]
  We propose PrefGen, a novel framework that extends standard DPO beyond human preferences to incorporate quantifiable blockchain-specific metrics.<n>Our framework introduces a comprehensive evaluation methodology with four complementary metrics: Pass@k (functional correctness), Compile@k (syntactic correctness), Gas@k (gas efficiency), and Secure@k (security assessment)<n>We demonstrate that PrefGen significantly outperforms existing approaches across all critical dimensions, achieving 66.7% Pass@5, 58.9% Gas@5, and 62.5% Secure@5.
  arXiv  Detail & Related papers  (2025-06-03T15:45:31Z)
• AegisLLM: Scaling Agentic Systems for Self-Reflective Defense in LLM Security [74.22452069013289]
  AegisLLM is a cooperative multi-agent defense against adversarial attacks and information leakage.<n>We show that scaling agentic reasoning system at test-time substantially enhances robustness without compromising model utility.<n> Comprehensive evaluations across key threat scenarios, including unlearning and jailbreaking, demonstrate the effectiveness of AegisLLM.
  arXiv  Detail & Related papers  (2025-04-29T17:36:05Z)
• Can We Make Code Green? Understanding Trade-Offs in LLMs vs. Human Code Optimizations [45.243401722182554]
  Large language models (LLMs) claim to assist developers in optimizing code for performance and energy efficiency.<n>This work focuses on software written in Matlab-widely used in both academia and industry for scientific and engineering applications.<n>We analyze energy-focused optimization on 400 scripts across 100 top GitHub repositories.
  arXiv  Detail & Related papers  (2025-03-26T00:27:29Z)
• ECO: An LLM-Driven Efficient Code Optimizer for Warehouse Scale Computers [13.56820317396104]
  This paper introduces ECO (Efficient Code), a system that automatically source code to improve performance at scale.<n>Over the past year, ECO has consistently resulted in significant performance savings every quarter.<n>On average, the savings produced per quarter are equivalent to over 500k normalized CPU cores.
  arXiv  Detail & Related papers  (2025-03-19T19:52:35Z)
• The Dual-use Dilemma in LLMs: Do Empowering Ethical Capacities Make a Degraded Utility? [54.18519360412294]
  Large Language Models (LLMs) must balance between rejecting harmful requests for safety and accommodating legitimate ones for utility.<n>This paper presents a Direct Preference Optimization (DPO) based alignment framework that achieves better overall performance.<n>We analyze experimental results obtained from testing DeepSeek-R1 on our benchmark and reveal the critical ethical concerns raised by this highly acclaimed model.
  arXiv  Detail & Related papers  (2025-01-20T06:35:01Z)
• Gödel Agent: A Self-Referential Agent Framework for Recursive Self-Improvement [112.04307762405669]
  G"odel Agent is a self-evolving framework inspired by the G"odel machine.<n>G"odel Agent can achieve continuous self-improvement, surpassing manually crafted agents in performance, efficiency, and generalizability.
  arXiv  Detail & Related papers  (2024-10-06T10:49:40Z)
• MADA: Meta-Adaptive Optimizers through hyper-gradient Descent [73.1383658672682]
  We introduce Meta-Adaptives (MADA), a unified framework that can generalize several known convergences and dynamically learn the most suitable one during training. We empirically compare MADA to other populars on vision and language tasks, and find that MADA consistently outperforms Adam and other populars. We also propose AVGrad, a modification of AMS that replaces the maximum operator with averaging, which is more suitable for hyper-gradient optimization.
  arXiv  Detail & Related papers  (2024-01-17T00:16:46Z)
• A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration [55.35849138235116]
  We propose automatically selecting a team of agents from candidates to collaborate in a dynamic communication structure toward different tasks and domains. Specifically, we build a framework named Dynamic LLM-Powered Agent Network ($textDyLAN$) for LLM-powered agent collaboration. We demonstrate that DyLAN outperforms strong baselines in code generation, decision-making, general reasoning, and arithmetic reasoning tasks with moderate computational cost.
  arXiv  Detail & Related papers  (2023-10-03T16:05:48Z)
• Learning Performance-Improving Code Edits [107.21538852090208]
  We introduce a framework for adapting large language models (LLMs) to high-level program optimization. First, we curate a dataset of performance-improving edits made by human programmers of over 77,000 competitive C++ programming submission pairs. For prompting, we propose retrieval-based few-shot prompting and chain-of-thought, and for finetuning, these include performance-conditioned generation and synthetic data augmentation based on self-play.
  arXiv  Detail & Related papers  (2023-02-15T18:59:21Z)
• Evolving Pareto-Optimal Actor-Critic Algorithms for Generalizability and Stability [67.8426046908398]
  Generalizability and stability are two key objectives for operating reinforcement learning (RL) agents in the real world. This paper presents MetaPG, an evolutionary method for automated design of actor-critic loss functions.
  arXiv  Detail & Related papers  (2022-04-08T20:46:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.