Skip the Compressor: Coding Agents Fix More Issues When They Pick Whole Files

The paper investigates how coding agents handle large repositories when their context window is limited. It compares three strategies—prompt compression, code retrieval, and a simple file selector called CQ2-CARE—finding that allocating the token budget to selecting whole files verbatim enables the agent to fix more issues. CQ2-CARE outperforms both compressors and retrievers on a benchmark of 300 recent software‑engineering problems, achieving higher success rates with GPT‑5.6 and Claude Opus 5.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• llms
• agents
• efficiency
• benchmarks