EET: Experience-Driven Early Termination for Cost-Efficient Software Engineering Agents
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914490614808576 |
|---|---|
| author | Guo, Yaoqi Xiao, Ying Zhang, Jie M. Harman, Mark Lou, Yiling Liu, Yang Chen, Zhenpeng |
| author_facet | Guo, Yaoqi Xiao, Ying Zhang, Jie M. Harman, Mark Lou, Yiling Liu, Yang Chen, Zhenpeng |
| contents | 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 experience-driven 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 early-termination 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_05777 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | EET: Experience-Driven Early Termination for Cost-Efficient Software Engineering Agents Guo, Yaoqi Xiao, Ying Zhang, Jie M. Harman, Mark Lou, Yiling Liu, Yang Chen, Zhenpeng Software Engineering 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 experience-driven 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 early-termination 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. |
| title | EET: Experience-Driven Early Termination for Cost-Efficient Software Engineering Agents |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2601.05777 |