AI Paper Atlas

Research map / Large language models / Agents, code and math

RECODE: A Benchmark for Research Code DEvelopment with Interactive Human Feedback

Chunyu Miao, Henry Peng Zou, Yangning Li, Yankai Chen, Yibo Wang, Fangxin Wang, Yifan Li, Wooseong Yang, Bowei He, Xinni Zhang, Dianzhi Yu, Hanchen Yang and 17 more

ICLR 2026 · Large language models › Agents, code and math · approach: Software engineering agents

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
raise feedback from Level 0 to Level 1 (ablation)GPT-5 · RECODE-HRecall: 0.294 -> 0.451Improved
raise feedback from Level 0 to Level 4 (ablation)DeepSeek-V3.1 · RECODE-HRecall: 0.108 -> 0.706Improved
raise feedback from Level 0 to Level 4 (ablation)GPT-5 · RECODE-HRecall: 0.294 -> 0.716Improved
raise feedback from Level 2 to Level 3 (ablation)Claude-sonnet-4 · RECODE-HRecall: 0.333 -> 0.333No clear effect
raise feedback from Level 2 to Level 3 (ablation)DeepSeek-V3.1 · RECODE-Htest case pass rate: 0.606 -> 0.576Hurt
raise feedback from Level 3 to Level 4 (add correct code snippet) (ablation)GPT-5 · RECODE-Htest case pass rate: 0.837 -> 0.843Improved
raise feedback from Level 0 to Level 1 (ablation)GPT-5-mini · RECODE-HMRR: 0.127 -> 0.062Hurt
use GPT-5 instead of GPT-o3 as feedback model (ablation)GPT-5-mini · RECODE-Htest case pass rate: 0.27 -> 0.32Improved
use a larger GPT-5 model instead of GPT-5-nanoGPT-5-nano · RECODE-H Level 4Recall: 0.353 -> 0.716 (nano vs GPT-5)Improved
use Gemini-2.5-pro instead of Gemini-2.5-flashGemini-2.5 · RECODE-HRecall: L2: 0.343 vs 0.373Mixed
richer feedback increases adoptionClaude-sonnet-4 · RECODE-Hadoption rateHurt

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