AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

SRACG: A Code Generation Framework with Selective Retrieval Augmentation

Mengzhen Wang, Shukai Ma, Songwen Gong, Jiexin Wang, Ruolin Chen, Liuwen Cao, Yi Cai

AAAI 2026 · Large language models › Retrieval and knowledge · approach: RAG robustness and evaluation · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add necessity-aware intent selection (ablation)SRACG (GPT-3.5-Turbo) · HumanEval+Pass@1: 62.37 -> 66.88Improved
add necessity-aware intent selection (ablation)SRACG (DeepSeek-V3) · HumanEval+Pass@1: 82.11 -> 85.97Improved
add multi-objective retrieval (ablation)SRACG (GPT-3.5-Turbo) · HumanEval+Pass@1: 63.71 -> 66.88Improved
add preference consistency filtering (ablation)SRACG (GPT-3.5-Turbo) · HumanEval+Pass@1: 63.50 -> 66.88Improved
add preference consistency filtering (ablation)SRACG (DeepSeek-V3) · HumanEval+Pass@1: 83.11 -> 85.97Improved
add execution plan extraction (ablation)SRACG (GPT-3.5-Turbo) · HumanEval+Pass@1: 64.41 -> 66.88Improved
add execution plan extraction (ablation)SRACG (DeepSeek-V3) · HumanEval+Pass@1: 83.91 -> 85.97Improved
indiscriminate top-1 retrieval augmentation (RACG) vs no retrievalGPT-3.5-Turbo · HumanEval+Pass@1: 59.82 -> 56.21Hurt
indiscriminate top-1 retrieval augmentation (RACG) vs no retrievalDeepSeek-V3 · HumanEval+Pass@1: 82.80 -> 80.22Hurt
apply SRACG to base LLMGPT-3.5-Turbo · HumanEval+Pass@1: 59.82 -> 66.88Improved
apply SRACG to base LLMDeepSeek-V3 · HumanEval+Pass@1: 82.80 -> 85.97Improved
apply SRACG to base LLMGPT-3.5-Turbo · CodeContestsPass@1: 2.39 -> 5.61Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy