CLSEJul 20

SWE-Pruner Pro: The Coder LLM Already Knows What to Prune

arXiv:2607.1821321.3
Predicted impact top 18% in CL · last 90 daysOriginality Incremental advance
AI Analysis

For developers of coding agents, this method reduces context costs without sacrificing performance, offering a practical improvement over existing pruning approaches.

SWE-Pruner Pro prunes tool outputs inside a coding agent using its own internal representations, saving up to 39% of tokens while preserving task quality, and improving SWE-Bench Verified resolve rate by +3.8% and Oolong accuracy by +2.2 points.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes