Daily Paper Cast
SWE-Pruner Pro: The Coder LLM Already Knows What to Prune
22 July 2026 19:58 Jingwen Liang, Gengyu Wang
Listen to episode
About this episode
🤗 Upvotes: 65 | cs.CL, cs.SE
<strong>Authors:</strong><br />
Yuhang Wang, Yuling Shi, Shaoqiu Zhang, Jialiang Liang, Shilin He, Siyu Ye, Yuting Chen, Kai Cai, Xiaodong Gu</p>
<strong>Title:</strong><br />
SWE-Pruner Pro: The Coder LLM Already Knows What to Prune</p>
<strong>Arxiv:</strong><br />
<a href="http://arxiv.org/abs/2607.18213v1">http://arxiv.org/abs/2607.18213v1</a></p>
<strong>Abstract:</strong><br />
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
More AI podcast episodes
Browse all →Want to find AI jobs?
Join thousands of AI professionals finding their next opportunity