AI Paper Atlas

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

Self-CriTeach: LLM Self-Teaching and Self-Critiquing for Improving Robotic Planning via Automated Domain Generation

Jinbang Huang, Zhiyuan Li, Yuanzhao Hu, Zhanguang Zhang, Mark Coates, Xingyue Quan, Yingxue Zhang

ICML 2026 · Large language models › Agents, code and math · approach: Agent instruction-following benchmarks

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 RL (CPO) with self-generated domain reward after SFT (ablation)SCT SFT-only · Overallplanning success rate: 0.43 -> 0.46Improved
add RL (CPO) with self-generated domain reward after SFT (ablation)SCT SFT-only · Overallprogress score: 0.67 -> 0.76Improved
add SFT before RL (ablation)SCT CPO-only · Overallplanning success rate: 0.31 -> 0.46Improved
add symbolic-to-CoT transformation to SFT data (ablation)SCT Symbol · Overallplanning success rate: 0.38 -> 0.46Improved
add symbolic-to-CoT transformation to SFT data (ablation)SCT Symbol · Prepare Experiment (unseen)planning success rate: 0.16 -> 0.45Improved
add symbolic-to-CoT transformation to SFT data (ablation)SCT Symbol · BW Align (seen)planning success rate: 0.84 -> 0.75Hurt
use CPO instead of DPO for RL (ablation)SCT DPO-only · Overallplanning success rate: 0.29 -> 0.31Improved
use LCCS instead of CPO for RL (ablation)SCT CPO-only · Overallprogress score: 0.69 -> 0.71Improved
apply Self-CriTeach to Qwen3-4BQwen3-4B · Overallplanning success rate: 0.26 -> 0.46Improved
apply Self-CriTeach to Qwen3-4BQwen3-4B · BW Hard (seen)planning success rate: 0.24 -> 0.45Improved
apply Self-CriTeach to Llama-3.1-8BLlama-3.1-8B · Overallplanning success rate: 0.003 -> 0.277Improved
apply Self-CriTeach to Qwen3-8BQwen3-8B · Overallplanning success rate: 0.35 -> 0.49Improved

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