CQ2-CARE: Coding Agents Fix More Issues by Picking Whole Files Over Compression
AI-Interpretability-illinois · hf · 2026-10-19
Research from Illinois challenges common context management for coding agents: instead of retrieval or compression, select exact whole files to include verbatim within a token budget. On 300 issues, CQ2-CARE resolves 43.7% with GPT-5.6 and 46.7% with Claude Opus 5, beating BM25/Dense chunk retrieval (22.7–34%), SweRank (43–45%), LongCodeZip, LLMLingua-family pruning and SWE-Pruner. Chunking truncates files so patches fail to apply; compression breaks syntax; whole files keep context usable.
More from coding & agent
- Qwen Code v0.25.3 Ships Managed-Agent Fixes and Web-Shell Tweaks — qwen-code-review-bot · 2026-10-19
- Amazon Paper: QA Scores Miss Agent Memory Failures by 16.8 Points, New FEB-30 Benchmark Fixes It — rohanpaul_ai · 2026-10-19
- How One Founder Used Grok Bot to Submit Backlinks to 4000+ Sites in a Single Day — sujingshen · 2026-10-19
- Netflix shares how it built a knowledge base for production AI agents — AxSaucedo · 2026-10-19
- Reverse Engineer Anything crosses 300k GitHub stars as a movement — FinanceYF5 · 2026-10-19
- Letting Claude Code fill out job applications without hitting Submit — Serious-Werewolf7613 · 2026-10-19