AI Paper Atlas

Research map / Large language models / Alignment and preferences

AP2O-Coder: Adaptively Progressive Preference Optimization for Reducing Compilation and Runtime Errors in LLM-Generated Code

Jianqing Zhang, Wei Xia, Hande Dong, Qiang Lin, Jian Cao

AAAI 2026 · Large language models › Alignment and preferences · approach: Active and token-level preference learning · 1 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 adaptive error replay (ablation)AP2O-Coder (L2H), Qwen2.5-Coder-7B · EvalPlus MBPPpass@1: 82.7 -> 84.9Improved
add adaptive error replay (ablation)AP2O-Coder (H2L), Qwen2.5-Coder-7B · EvalPlus MBPPpass@1: 82.1 -> 85.4Improved
add adaptive error replay (ablation)AP2O-Coder (L2H), Qwen2.5-7B · EvalPlus MBPPpass@1: 81.6 -> 82.9Improved
add adaptive error replay (ablation)AP2O-Coder (H2L), Qwen2.5-7B · EvalPlus MBPPpass@1: 81.0 -> 82.2Improved
add adaptive error replay (ablation)AP2O-Coder (L2H and H2L), Qwen2.5-Coder-7B · LiveCodeBenchpass@1: 18.4 -> 18.8 (L2H), 18.5 -> 19.0 (H2L)Improved
add adaptive error replay (ablation)AP2O-Coder (L2H and H2L), Qwen2.5-7B · LiveCodeBenchpass@1: 14.2 -> 15.1 (L2H), 13.6 -> 14.4 (H2L)Improved
progressive error-type ordering plus replay instead of dynamic sampling (Dyn-DPO) (ablation)AP2O-Coder (H2L), Qwen2.5-Coder-7B · EvalPlus MBPPpass@1: 83.7 -> 85.4Improved
use AP2O-Coder (H2L) instead of DPO-CoderQwen2.5-Coder-7B · EvalPlus MBPPpass@1: 83.5 -> 85.4Improved
use L2H instead of H2L ordering (ablation)AP2O-Coder, Qwen2.5-Coder-0.5B · EvalPlus HumanEvalpass@1: 56.5 -> 61.5Improved
use H2L instead of L2H ordering (ablation)AP2O-Coder, CodeLlama-34B · EvalPlus HumanEvalpass@1: 47.9 -> 49.6Improved
use H2L instead of L2H ordering (ablation)AP2O-Coder, Qwen2.5-Coder-0.5B · LiveCodeBench v6pass@1: 3.3 -> 3.2No clear effect
curriculum ordering of DPO data (Curri-DPO-Coder) instead of DPO (ablation)Qwen2.5-Coder-7B · EvalPlus MBPPpass@1: 83.5 -> 81.7Hurt

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