EET: Experience-Driven Early Termination for Cost-Efficient Software Engineering Agents
For practitioners deploying LLM-based SE agents, EET offers a cost-saving method with minimal performance trade-off.
EET reduces the monetary cost of LLM-based software engineering agents by 19%-55% (32% on average) with at most 0.2% loss in resolution rate, by using structured experience to guide early termination of patch generation and selection.
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.