| title | SWE-Pruner Pro: The Coder LLM Already Knows What to Prune |
|---|---|
| authors | Yuhang Wang, Yuling Shi, Shaoqiu Zhang, Jialiang Liang, Shilin He, Siyu Ye, Yuting Chen, Kai Cai, Xiaodong Gu |
| date | 2026-07-20 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2607.18213 |
| affiliation | ByteDance |
| upvotes | 46 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| 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. |
cite
@misc{wang2026swe,
title={SWE-Pruner Pro: The Coder LLM Already Knows What to Prune},
author={Yuhang Wang and Yuling Shi and Shaoqiu Zhang and Jialiang Liang and Shilin He and Siyu Ye and Yuting Chen and Kai Cai and Xiaodong Gu},
year={2026},
eprint={2607.18213},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2607.18213}
}