AI Paper Atlas

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

R-Zero: Self-Evolving Reasoning LLM from Zero Data

Chengsong Huang, Wenhao Yu, Xiaoyang Wang, Hongming Zhang, Zongxia Li, Ruosen Li, Jiaxin Huang, Haitao Mi, Dong Yu

ICLR 2026 · Large language models › Agents, code and math · approach: LLMs for optimization and heuristics

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
train the Challenger with RL instead of using an untrained Challenger (ablation)R-Zero · Math average (Qwen3-4B-Base)average accuracy: 45.01 -> 49.93Improved
add repetition penalty to the Challenger reward (ablation)R-Zero · Math AVG (Qwen3-4B-Base)Math AVG: 45.76 -> 49.07Improved
add difficulty-based task filtering for Solver data (ablation)R-Zero · General AVG (Qwen3-4B-Base)General AVG: 26.69 -> 31.15Improved
add task filtering for Solver data (ablation)R-Zero · Math AVG (Qwen3-4B-Base)Math AVG: 47.35 -> 49.07Improved
separate Challenger and Solver into two independent models rather than one shared model (ablation)R-Zero · Math average (Qwen3-4B-Base)peak performance: Single-R-Zero 47.31 (peak) -> 49.12Improved
separate Challenger and Solver models (ablation)R-Zero · pseudo-label accuracy, iteration 1pseudo-label accuracy: 63.4% -> 71.0%Improved
run more co-evolution iterations (ablation)R-Zero · Math average, 0.6B to 4B Qwen3 modelsmath averageHurt
fine-tune R-Zero checkpoint on human-labeled data afterwardsR-Zero · Math average (Qwen3-4B-Base)average accuracy: +2.35 points over human-label-only baselineImproved
mix human-labeled data into the R-Zero training data instead of sequential SFT (ablation)R-Zero · Qwen3-4B-Base math and generalaccuracyMixed
pseudo-label accuracy declines as the Challenger makes harder questionsR-Zero · GPT-4o-checked question sets (Qwen3-4B-Base)pseudo-label accuracy: 79.0% -> 63.0%Hurt
remove the math-only constraint from the Challenger prompt (ablation)R-Zero · general benchmarks (Qwen3-8B)SuperGPQA: 31.38 -> 32.29Improved
remove the math-only constraint from the Challenger prompt (ablation)R-Zero · math and general benchmarks (Qwen3-4B)AMC: 57.27 -> 56.27No clear effect

Later papers that compared with this method

4 later accepted papers report R-Zero as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.

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