# Writing-Zero: Bridge the Gap Between Non-verifiable Tasks and Verifiable Rewards

arXiv: https://arxiv.org/abs/2506.00103 · HTML: https://mlsanity.com/paper/2506.00103/

## Key facts

- Cited by 50 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 35 references that are in the map.
- First posted on arXiv 30 May 2025.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Process reward models for reasoning](https://mlsanity.com/alignment/process-reward-models-for-reasoning/)

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

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [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)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [Kimi k1.5: Scaling Reinforcement Learning with LLMs](https://mlsanity.com/paper/2501.12599/) (2025)
- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion](https://mlsanity.com/paper/2306.02561/) (2023)
- [Generative Verifiers: Reward Modeling as Next-Token Prediction](https://mlsanity.com/paper/2408.15240/) (2024)
- [InternLM2 Technical Report](https://mlsanity.com/paper/2403.17297/) (2024)
- [Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs](https://mlsanity.com/paper/2410.18451/) (2024)
- [Inference-Time Scaling for Generalist Reward Modeling](https://mlsanity.com/paper/2504.02495/) (2025)
- [Generative Judge for Evaluating Alignment](https://mlsanity.com/paper/2310.05470/) (2023)
- [Crossing the Reward Bridge: Expanding RL with Verifiable Rewards Across Diverse Domains](https://mlsanity.com/paper/2503.23829/) (2025)
- [RM-R1: Reward Modeling as Reasoning](https://mlsanity.com/paper/2505.02387/) (2025)
- [A Minimalist Approach to LLM Reasoning: from Rejection Sampling to Reinforce](https://mlsanity.com/paper/2504.11343/) (2025)
- [Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs](https://mlsanity.com/paper/2406.10216/) (2024)
- [WritingBench: A Comprehensive Benchmark for Generative Writing](https://mlsanity.com/paper/2503.05244/) (2025)
- [Unified Multimodal Chain-of-Thought Reward Model through Reinforcement Fine-Tuning](https://mlsanity.com/paper/2505.03318/) (2025)
- [JudgeLRM: Large Reasoning Models as a Judge](https://mlsanity.com/paper/2504.00050/) (2025)
- [J1: Incentivizing Thinking in LLM-as-a-Judge via Reinforcement Learning](https://mlsanity.com/paper/2505.10320/) (2025)
- [Foundational Autoraters: Taming Large Language Models for Better Automatic Evaluation](https://mlsanity.com/paper/2407.10817/) (2024)
- [R1-Reward: Training Multimodal Reward Model Through Stable Reinforcement Learning](https://mlsanity.com/paper/2505.02835/) (2025)
- [A Comprehensive Survey of Reward Models: Taxonomy, Applications, Challenges, and Future](https://mlsanity.com/paper/2504.12328/) (2025)
- [M-RewardBench: Evaluating Reward Models in Multilingual Settings](https://mlsanity.com/paper/2410.15522/) (2024)
- [CompassJudger-1: All-in-one Judge Model Helps Model Evaluation and Evolution](https://mlsanity.com/paper/2410.16256/) (2024)
- [Beyond Scalar Reward Model: Learning Generative Judge from Preference Data](https://mlsanity.com/paper/2410.03742/) (2024)

## Built on by (most cited first, 30 of 50)

- [Open Rubric System: Scaling Reinforcement Learning with Pairwise Adaptive Rubric](https://mlsanity.com/paper/2602.14069/) (2026)
- [CAPO: Towards Enhancing LLM Reasoning through Generative Credit Assignment](https://mlsanity.com/paper/2508.02298/) (2025)
- [Language Models that Think, Chat Better](https://mlsanity.com/paper/2509.20357/) (2025)
- [Benchmarking Reward Hack Detection in Code Environments via Contrastive Analysis](https://mlsanity.com/paper/2601.20103/) (2026)
- [Direct Reasoning Optimization: Token-Level Reasoning Reflectivity Meets Rubric Gates for Unverifiable Tasks](https://mlsanity.com/paper/2506.13351/) (2025)
- [ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking](https://mlsanity.com/paper/2601.06487/) (2026)
- [Reproducing, Analyzing, and Detecting Reward Hacking in Rubric-Based Reinforcement Learning](https://mlsanity.com/paper/2606.04923/) (2026)
- [Environment Scaling for Interactive Agentic Experience Collection: A Survey](https://mlsanity.com/paper/2511.09586/) (2025)
- [RLMR: Reinforcement Learning with Mixed Rewards for Creative Writing](https://mlsanity.com/paper/2508.18642/) (2025)
- [G2RPO-A: Guided Group Relative Policy Optimization with Adaptive Guidance](https://mlsanity.com/paper/2508.13023/) (2025)
- [TERMS-Bench: Diagnosing LLM Negotiation Agents Beyond Deal Rate](https://mlsanity.com/paper/2605.13909/) (2026)
- [DuPO: Enabling Reliable LLM Self-Verification via Dual Preference Optimization](https://mlsanity.com/paper/2508.14460/) (2025)
- [Escaping the Verifier: Learning to Reason via Demonstrations](https://mlsanity.com/paper/2511.21667/) (2025)
- [From Verifiable Dot to Reward Chain: Harnessing Verifiable Reference-based Rewards for Reinforcement Learning of Open-ended Generation](https://mlsanity.com/paper/2601.18533/) (2026)
- [Conversation for Non-verifiable Learning: Self-Evolving LLMs through Meta-Evaluation](https://mlsanity.com/paper/2601.21464/) (2026)
- [SPARD: Self-Paced Curriculum for RL Alignment via Integrating Reward Dynamics and Data Utility](https://mlsanity.com/paper/2604.07837/) (2026)
- [Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence](https://mlsanity.com/paper/2608.31075/) (2026)
- [Grounding the Score: Explicit Visual Premise Verification for Reliable Vision-Language Process Reward Models](https://mlsanity.com/paper/2603.16253/) (2026)
- [Rationale Matters: Learning Transferable Rubrics via Proxy-Guided Critique for VLM Reward Models](https://mlsanity.com/paper/2603.16600/) (2026)
- [Focal Reward: Balanced Reinforcement Learning under Rubric-Based Rewards](https://mlsanity.com/paper/2605.26579/) (2026)
- [PReMISE: Policy Rubrics as Measurement Specifications for LLM Judges](https://mlsanity.com/paper/2605.30803/) (2026)
- [From Holistic Evaluation to Structured Criteria: Rubrics Across the Evolving LLM Landscape](https://mlsanity.com/paper/2606.08625/) (2026)
- [Reasoning over mathematical objects: on-policy reward modeling and test time aggregation](https://mlsanity.com/paper/2603.18886/) (2026)
- [R2-Write: Reflection and Revision for Open-Ended Writing with Deep Reasoning](https://mlsanity.com/paper/2604.03004/) (2026)
- [Rewarding Creativity: A Human-Aligned Generative Reward Model for Reinforcement Learning in Storytelling](https://mlsanity.com/paper/2601.07149/) (2026)
- [DARL: Encouraging Diverse Answers for General Reasoning without Verifiers](https://mlsanity.com/paper/2601.14700/) (2026)
- [Teaching Language Models to Forecast Research Success Through Comparative Idea Evaluation](https://mlsanity.com/paper/2605.21491/) (2026)
- [Right in the Right Way: LM Training with Verifiable Rewards and Human Demonstrations](https://mlsanity.com/paper/2607.01181/) (2026)
- [IRPM: Intergroup Relative Preference Modeling for Pointwise Generative Reward Models](https://mlsanity.com/paper/2601.00677/) (2026)
- [PodBench: A Comprehensive Benchmark for Instruction-Aware Audio-Oriented Podcast Script Generation](https://mlsanity.com/paper/2601.14903/) (2026)

## Abstract (arXiv)

Reinforcement learning with verifiable rewards (RLVR) has enabled large language models (LLMs) to achieve remarkable breakthroughs in reasoning tasks with objective ground-truth answers, such as mathematics and code generation. However, a significant gap remains for non-verifiable tasks, like creative writing and open-ended dialogue, where quality assessment is inherently subjective and lacks definitive references. Existing approaches for these domains often rely on scalar reward models trained with human preferences, which suffer from limited generalization and are prone to reward hacking, such as over-explanation and length bias. In this work, we propose a unified RLVR-based training paradigm that bridges the gap between non-verifiable tasks and verifiable rewards. We introduce a writing-principle-based pairwise Generative Reward Model (GenRM) and a novel Bootstrapped Relative Policy Optimization (BRPO) algorithm. The pairwise writing GenRM leverages self-principled critique to transform subjective assessments into reliable, verifiable rewards, while BRPO enables dynamic, reference-free pairwise comparison by leveraging a bootstrapped response as temporary reference from within group rollouts during RL training. Our approach empowers LLMs to develop robust writing capabilities without supervised fine-tuning, as demonstrated by Writing-Zero, which shows consistent improvement and strong resistance to reward hacking compared to scalar reward baselines. Furthermore, our method achieves competitive results on both in-house and open-source writing benchmarks. Our findings suggest the potential to unify rule-based, reference-based, and reference-free reward modeling under the RLVR framework, thus paving the way for a comprehensive and scalable RL training paradigm applicable across all language tasks.