• SWE-bench — The standard benchmark for AI coding agents: real GitHub issues from real repositories, scored by whether the agent's patch passes the project's own tests.
• context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.

Retrieval for code agents is routinely tuned against recall@k, and this is direct evidence that optimizing that metric can cost you resolved issues when the context window is fixed.

• articleCodeGrep: An RL-Trained Retrieval Agent for LLM Coding AgentsWuya Chen, Yihao yang, Yang Cao, Yue Lin
• articleTry Again, Don't Look Back: Blind Resampling Outperforms Self-Repair in Small Code ModelsYuvraj Verma
• videoMemory Harnesses for Long-Running Research Agents — Stefania Druga, Sakana.aiAI Engineer

Sign in to comment.

Loading comments…