SWE-Pruner Pro: The Coder LLM Already Knows What to Prune
2026-07-20 • Computation and Language
Computation and LanguageSoftware Engineering
AI summaryⓘ
The authors found that coding agents already have clues inside them to decide which parts of code are important. They created SWE-Pruner Pro, a tool that uses these internal hints to cut out unnecessary lines of code more efficiently. This method saves a lot of processing time and tokens without hurting performance. Their experiments show it works well across different setups and even improves some accuracy measures.
context pruningcoding agentsinternal representationstool outputtoken efficiencymulti-turn benchmarksprompt tokensinference overheadSWE-Pruner Pro
Authors
Yuhang Wang, Yuling Shi, Shaoqiu Zhang, Jialiang Liang, Shilin He, Siyu Ye, Yuting Chen, Kai Cai, Xiaodong Gu
Abstract
Pruning long context for coding agents has been a vital technology for efficient context management. While existing context pruning methods such as SWE-Pruner realize this by attaching a separate code classifier, we find the agent itself encodes internal representations indicating the relevance of code context when reading tool output. Based on this finding, we propose SWE-Pruner Pro, which prunes tool outputs directly inside the agent. Concretely, a small head turns the agent's own internal representations into a keep-or-prune label for each line, with a length-aware embedding keyed to each tool output's line count. Across two open-weight backbones and four multi-turn benchmarks, SWE-Pruner Pro saves up to 39% of prompt and completion tokens while preserving task quality, with bounded inference overhead. Notably, on MiMo-V2-Flash SWE-Pruner Pro additionally raises the SWE-Bench Verified resolve rate by +3.8% and the long-context Oolong accuracy by +2.2 points.