mlsanityData to 7 Oct 2026

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

arXiv 2510.04135 ↗First posted 5 Oct 2025cs.SE cs.AIcited by 3

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

Abstract (arXiv)

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.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. Builds on 9 of its 14 references that are in the map. First posted on arXiv 5 Oct 2025.

Builds on

9 of 14 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025Industrial LLM-based Code Optimization under Regulation: A Mixture-of-Agents Approach5 Aug

Other references · 8

  1. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  2. 2025Small Language Models are the Future of Agentic AIcited by 254
  3. 2025SWE-Perf: Can Language Models Optimize Code Performance on Real-World Repositories?cited by 33
  4. 2025Language Models for Code Optimization: Survey, Challenges and Future Directionscited by 15
  5. 2025Tuning LLM-based Code Optimization via Meta-Prompting: An Industrial Perspectivecited by 7
  6. 2025Generating Energy-Efficient Code via Large-Language Models -- Where are we now?cited by 5
  7. 2025GREEN-CODE: Learning to Optimize Energy Efficiency in LLM-based Code Generationcited by 3
  8. 2025Investigating the Role of LLMs Hyperparameter Tuning and Prompt Engineering to Support Domain Modelingcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Comparing AI Coding Agents: A Task-Stratified Analysis of Pull Request Acceptancecited by 3
  2. 2026How Do Practitioners Build SE Agents? Insights from a Mixed-Methods Studycited by 1
  3. 2026COMPAS: Difficulty-Aware Joint Search for Optimizing Code Generationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026PERFOPT-Bench: Evaluating Coding Agents on Software Performance Optimization
  2. 2026FormulaCode: Evaluating Agentic Optimization on Large Codebases
  3. 2025GitTaskBench: A Benchmark for Code Agents Solving Real-World Tasks Through Code Repository Leveraging
  4. 2025MARCO: Multi-Agent Code Optimization with Real-Time Knowledge Integration for High-Performance Computing
  5. 2024Self-Organized Agents: A LLM Multi-Agent Framework toward Ultra Large-Scale Code Generation and Optimization
  6. 2025NL2Repo-Bench: Towards Long-Horizon Repository Generation Evaluation of Coding Agents
  7. 2026LoopsBench: From Harness Engineering to Loop Engineering in Coding Agent Evaluation
  8. 2026Inside the Scaffold: A Source-Code Taxonomy of Coding Agent Architectures