{"slug": "swe-pruner-pro-the-coder-llm-already-knows-what-to-prune", "title": "SWE-Pruner Pro: The Coder LLM Already Knows What to Prune", "summary": "Researchers propose SWE-Pruner Pro, a method that prunes tool outputs directly inside a coding agent by using the agent's own internal representations to label each line as keep or prune, saving up to 39% of prompt and completion tokens while preserving task quality. On MiMo-V2-Flash, SWE-Pruner Pro raises the SWE-Bench Verified resolve rate by +3.8% and the long-context Oolong accuracy by +2.2 points.", "body_md": "arXiv:2607.18213v1 Announce Type: new\nAbstract: 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.", "url": "https://wpnews.pro/news/swe-pruner-pro-the-coder-llm-already-knows-what-to-prune", "canonical_source": "https://www.machinebrief.com/news/swe-pruner-pro-the-coder-llm-already-knows-what-to-prune-pyvx", "published_at": "2026-07-21 04:00:00+00:00", "updated_at": "2026-07-21 04:37:04.832732+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-agents", "ai-research"], "entities": ["SWE-Pruner Pro", "SWE-Pruner", "MiMo-V2-Flash", "SWE-Bench Verified", "Oolong"], "alternates": {"html": "https://wpnews.pro/news/swe-pruner-pro-the-coder-llm-already-knows-what-to-prune", "markdown": "https://wpnews.pro/news/swe-pruner-pro-the-coder-llm-already-knows-what-to-prune.md", "text": "https://wpnews.pro/news/swe-pruner-pro-the-coder-llm-already-knows-what-to-prune.txt", "jsonld": "https://wpnews.pro/news/swe-pruner-pro-the-coder-llm-already-knows-what-to-prune.jsonld"}}