cs.AINov 11, 2026

Termination Lag: Coding Agents Solve Early but Stop Late

Authors: Musa Cim, Burak Topcu, Mahmut Taylan Kandemir

Organizations: The Pennsylvania State University, University Park, PA, USA

Abstract

Coding agents can solve a task well before they stop working on it. We characterize termination lag--the number of steps between an agent's first correct patch and the end of its run--across five models, two agent frameworks, and three SWE-bench datasets by recording and testing every distinct repository patch generated during execution. Our analysis reveals that 38--82% of successful runs achieve a correct solution on their initial source-code edit. However, agents continue to expend substantial effort after correct patches, with post-solution steps accounting for a median of 35--37% for Qwen3-Coder and 54--60% for Laguna-XS.2 in successful runs on SWE-bench Verified and Multilingual. Agents spend most of these additional steps verifying their work and exploring the repository. In a small fraction of cases (1--8%), this continued activity leads agents to undo their earlier correct patch, leaving the final solution incorrect.

Figures & tables

Appendix figures & tables9 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Coherence Collapse: Diagnosing Why Code Agents Fail After Reaching the Right Code

    Mar 25, 2026Myeongsoo Kim, Dingmin Wang, Siwei Cui +6Agent Failure AnalysisAI Coding Agents

  2. PAUSE: Search-Free Steering of Coding Agents Before Their First Source-Code Edit

    Oct 21, 2026Viral Patel, Boyin Tan, Jason Xue +1Coding AgentsLLM Agent Workflow Optimization