SWE-Pruner Pro: The Coder LLM Already Knows What to Prune
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 t
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 52%Beyond grep: The case for a context-rich AI coding harness →
- PossiblePossibly related (embedding) · 51%DeepSeek Ecosystem Fills Programming Agent Gap: Open-Source Tool Deep Code Launches, Taking Aim at Claude Code - finance.biggo.com →
- FuzzyOverlapping authors or contributors · 62%bytedance/deer-flow →
“Shared author/contributor keys: wang”
- FuzzyOverlapping authors or contributors · 62%ray-project/ray →
“Shared author/contributor keys: wang”
- LinkedLinked via arxiv author · 85%Yuhang Wang →
“SWE-Pruner Pro: The Coder LLM Already Knows What to Prune”
- LinkedLinked via arxiv author · 85%Yuling Shi →
“SWE-Pruner Pro: The Coder LLM Already Knows What to Prune”
- LinkedLinked via arxiv author · 85%Shaoqiu Zhang →
“SWE-Pruner Pro: The Coder LLM Already Knows What to Prune”
- LinkedLinked via arxiv author · 85%Jialiang Liang →
“SWE-Pruner Pro: The Coder LLM Already Knows What to Prune”