Lune

ACL Findings2026

EET: Experience-Driven Early Termination for Cost-Efficient Software Engineering Agents

Yaoqi Guo, Ying Xiao, Jie M. Zhang, Mark Harman, Yiling Lou, Yang Liu, Zhenpeng Chen

Abstract

Software engineering (SE) agents powered by large language models are increasingly adopted in practice, yet they often incur substantial monetary cost. We introduce EET, an experiencedriven early termination approach that reduces the cost of SE agents while preserving task performance. EET extracts structured experience from prior issue-resolution executions and leverages it to guide early termination during patch generation and selection, reducing unproductive iterations. We evaluate EET on the SWE-bench Verified benchmark across three representative SE agents. EET consistently reduces total cost by 19%-55% (32% on average), with negligible loss in resolution rate (at most 0.2%). These efficiency gains are achieved, on average, by identifying earlytermination opportunities for 11% of issues and reducing API calls, input tokens, and output tokens by 21%, 30%, and 25%, respectively. We release the code, prompts, and data at https://github.com/IanWalls/EET.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

1 top-tier paper has cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Reflexion: language agents with verbal reinforcement learning cites Generative Agents: Interactive Simulacra of Human Behavior
  • SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering cites SWE-bench: Can Language Models Resolve Real-world Github Issues?
  • SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering cites Reflexion: language agents with verbal reinforcement learning
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers1

  1. TransAgent: Enhancing LLM-Based Code Translation via Fine-Grained Execution AlignmentZhiqiang Yuan, Weitong Chen, Hanlin Wang, Xin Peng et al.FSE 2026 · 4 citations

Builds on13

  1. Retrieval-Augmented Generation for Knowledge-Intensive NLP TasksPatrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni et al.NeurIPS 2020 · 19,162 citations
  2. Reflexion: language agents with verbal reinforcement learningNoah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan et al.NeurIPS 2023 · 5,828 citations
  3. SWE-bench: Can Language Models Resolve Real-world Github Issues?Carlos E. Jimenez, John Yang, Alexander Wettig, Shunyu Yao et al.ICLR 2024 · 2,082 citations
  4. SWE-agent: Agent-Computer Interfaces Enable Automated Software EngineeringJohn Yang, Carlos E. Jimenez, Alexander Wettig, Kilian Lieret et al.NeurIPS 2024 · 2,059 citations
  5. Generative Agents: Interactive Simulacra of Human BehaviorJoon Sung Park, Joseph C. O'Brien, Carrie Jun Cai, Meredith Ringel Morris et al.UIST 2023 · 1,882 citations

Related papers

  1. More with Less: An Empirical Study of Turn-Control Strategies for Efficient Coding AgentsPengfei Gao, Chao PengICSE 2026
  2. SE-Agent: Self-Evolution Trajectory Optimization in Multi-Step Reasoning with LLM-Based AgentsYifu Guo, Jiaye Lin, Huacan Wang, Yuzhen Han et al.NeurIPS 2025 · 73 citations
  3. Can Agent Fix Agent Issues?Alfin Wijaya Rahardja, Junwei Liu, Weitong Chen, Zhenpeng Chen et al.NeurIPS 2025 · 4 citations
  4. Agent-Based Ensemble Reasoning for Repository-Level Issue ResolutionZhao Tian, Pengfei Gao, Junjie Chen, Chao PengICSE 2026
  5. SWE-Search: Enhancing Software Agents with Monte Carlo Tree Search and Iterative RefinementAntonis Antoniades, Albert Örwall, Kexun Zhang, Yuxi Xie et al.ICLR 2025
Dusk over the sea between two cliffs drawn in fine vertical lines