• RAG — Retrieval-augmented generation — fetching relevant documents first and pasting them into the model's context so it answers from your data instead of memory.
• 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.
• LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.

Retrieval-based code assistants serve stale facts about a third of the time when a value changes mid-session — a renamed function, a moved endpoint — and an LLM reranker doesn't fix it; supersession-aware memory does.

• articleThe Recall Trap: A Recall-Maximizing Retriever Configuration Reduces Issue Resolution in Fixed-Budget Code ContextAlexander Adkins, Teimuraz Trapaidze
• articleWhen Knowledge Changes: Metamorphic Testing of RAG Systems with MutationsJinhan Kim, Samuele Pasini, Paolo Tonella
• articleRefine After Generation: Toward Correct and Concise Patches in LLM-based Program RepairWenqiang Luo, Jacky Keung, Xiaoyu Shi, Yicheng Sun, Boyang Yang, Zhou Yang, Haoye Tian

Checking sign-in…

Loading comments…