# G-Zero: Self-Play for Open-Ended Generation from Zero Data

arXiv: https://arxiv.org/abs/2605.09959 · HTML: https://mlsanity.com/paper/2605.09959/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Placed in Process reward models for reasoning, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 33 of its 39 references that are in the map.
- First posted on arXiv 11 May 2026.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Process reward models for reasoning](https://mlsanity.com/alignment/process-reward-models-for-reasoning/)
- Synthetic data and self-improvement for LLMs / [Self-evolving LLM agents](https://mlsanity.com/synth/self-evolving-llm-agents/)

## Builds on (most cited first, 30 of 33)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [Understanding R1-Zero-Like Training: A Critical Perspective](https://mlsanity.com/paper/2503.20783/) (2025)
- [Instruction-Following Evaluation for Large Language Models](https://mlsanity.com/paper/2311.07911/) (2023)
- [Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators](https://mlsanity.com/paper/2404.04475/) (2024)
- [Large Language Models Can Self-Improve](https://mlsanity.com/paper/2210.11610/) (2022)
- [Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models](https://mlsanity.com/paper/2401.01335/) (2024)
- [Absolute Zero: Reinforced Self-play Reasoning with Zero Data](https://mlsanity.com/paper/2505.03335/) (2025)
- [R-Zero: Self-Evolving Reasoning LLM from Zero Data](https://mlsanity.com/paper/2508.05004/) (2025)
- [Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Models](https://mlsanity.com/paper/2502.19417/) (2025)
- [Large Language Models for Data Annotation and Synthesis: A Survey](https://mlsanity.com/paper/2402.13446/) (2024)
- [A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systems](https://mlsanity.com/paper/2402.18013/) (2024)
- [MMC: Advancing Multimodal Chart Understanding with Large-scale Instruction Tuning](https://mlsanity.com/paper/2311.10774/) (2023)
- [A Survey on Self-Evolution of Large Language Models](https://mlsanity.com/paper/2404.14387/) (2024)
- [RLPR: Extrapolating RLVR to General Domains without Verifiers](https://mlsanity.com/paper/2506.18254/) (2025)
- [SPICE: Self-Play In Corpus Environments Improves Reasoning](https://mlsanity.com/paper/2510.24684/) (2025)
- [Reinforcing General Reasoning without Verifiers](https://mlsanity.com/paper/2505.21493/) (2025)
- [Self-Challenging Language Model Agents](https://mlsanity.com/paper/2506.01716/) (2025)
- [SeRL: Self-Play Reinforcement Learning for Large Language Models with Limited Data](https://mlsanity.com/paper/2505.20347/) (2025)
- [FIRST: A Framework for Optimizing Information Quality in Mobile Crowdsensing Systems](https://mlsanity.com/paper/1804.11147/) (2018)
- [VisPlay: Self-Evolving Vision-Language Models from Images](https://mlsanity.com/paper/2511.15661/) (2025)
- [SPC: Evolving Self-Play Critic via Adversarial Games for LLM Reasoning](https://mlsanity.com/paper/2504.19162/) (2025)
- [Learning to Solve and Verify: A Self-Play Framework for Code and Test Generation](https://mlsanity.com/paper/2502.14948/) (2025)
- [Guided Self-Evolving LLMs with Minimal Human Supervision](https://mlsanity.com/paper/2512.02472/) (2025)
- [Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges](https://mlsanity.com/paper/2604.13602/) (2026)
- [MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data](https://mlsanity.com/paper/2603.09206/) (2026)

## Built on by (most cited first, 17 of 17)

- [Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loops](https://mlsanity.com/paper/2607.07663/) (2026)
- [Dream-RSI: Recursive Self-Improvement through Evolving Worlds](https://mlsanity.com/paper/2609.14858/) (2026)
- [EnvHarness: Awakening Static Worlds for Agent Learning](https://mlsanity.com/paper/2608.19880/) (2026)
- [RRSI: Regularized Recursive Self-Improvement of Agent Harnesses](https://mlsanity.com/paper/2609.24972/) (2026)
- [SPADE: Self-Play in Adaptive Synthetic Executable Environments](https://mlsanity.com/paper/2608.19197/) (2026)
- [More Convincing, Not More Correct: Self-Play Reward Hacking of Reference-Free LLM Judges](https://mlsanity.com/paper/2607.05904/) (2026)
- [Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence](https://mlsanity.com/paper/2608.31075/) (2026)
- [SERPO: Self-Evolving Rubric Policy Optimization for Open-Ended Test-Time Reinforcement Learning](https://mlsanity.com/paper/2607.26873/) (2026)
- [It Takes Two to Match: Co-Evolving Generative Retriever with Reinforcement Learning](https://mlsanity.com/paper/2609.00638/) (2026)
- [Negative Self-Distillation: Learning to Reason by Avoiding Flaws](https://mlsanity.com/paper/2609.11699/) (2026)
- [J-Zero: Unified Challenger--Solver--Judge Self-Evolution from Zero Data](https://mlsanity.com/paper/2608.26582/) (2026)
- [Designer-RSI: Evolving Procedural Memory from User Traffic for Agentic Graphic Design](https://mlsanity.com/paper/2609.22086/) (2026)
- [Unsupervised Post-Training of Foundation Models: A Survey](https://mlsanity.com/paper/2608.24982/) (2026)
- [STRETCH the Boundaries: A Unified Self-Taught Framework for Progressive LLM Evolution](https://mlsanity.com/paper/2609.18642/) (2026)
- [When Updating Stops Being Learning: Rethinking LLM Self-Evolution via learnable information gain](https://mlsanity.com/paper/2609.36535/) (2026)
- [Questioning the Questions: Sustaining Self-Evolution in Reasoning Models](https://mlsanity.com/paper/2610.04299/) (2026)
- [From Existing Methods to New Research Ideas: Two Perspectives on Recursive Self-Improvement](https://mlsanity.com/paper/2610.14625/) (2026)

## Abstract (arXiv)

Self-evolving LLMs excel in verifiable domains but struggle in open-ended tasks, where reliance on proxy LLM judges introduces capability bottlenecks and reward hacking. To overcome this, we introduce G-Zero, a verifier-free, co-evolutionary framework for autonomous self-improvement. Our core innovation is Hint-δ, an intrinsic reward that quantifies the predictive shift between a Generator model's unassisted response and its response conditioned on a self-generated hint. Using this signal, a Proposer model is trained via GRPO to continuously target the Generator's blind spots by synthesizing challenging queries and informative hints. The Generator is concurrently optimized via DPO to internalize these hint-guided improvements. Theoretically, we prove a best-iterate suboptimality guarantee for an idealized standard-DPO version of G-Zero, provided that the Proposer induces sufficient exploration coverage and the data filteration keeps pseudo-label score noise low. By deriving supervision entirely from internal distributional dynamics, G-Zero bypasses the capability ceilings of external judges, providing a scalable, robust pathway for continuous LLM self-evolution across unverifiable domains.