# CompassJudger-2: Towards Generalist Judge Model via Verifiable Rewards

arXiv: https://arxiv.org/abs/2507.09104 · HTML: https://mlsanity.com/paper/2507.09104/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 34 references that are in the map.
- First posted on arXiv 12 Jul 2025.

## Builds on (most cited first, 28 of 28)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions](https://mlsanity.com/paper/1905.10044/) (2019)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark](https://mlsanity.com/paper/2406.01574/) (2024)
- [Instruction-Following Evaluation for Large Language Models](https://mlsanity.com/paper/2311.07911/) (2023)
- [DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs](https://mlsanity.com/paper/1903.00161/) (2019)
- [Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators](https://mlsanity.com/paper/2404.04475/) (2024)
- [Enhancing Chat Language Models by Scaling High-quality Instructional Conversations](https://mlsanity.com/paper/2305.14233/) (2023)
- [From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline](https://mlsanity.com/paper/2406.11939/) (2024)
- [RewardBench: Evaluating Reward Models for Language Modeling](https://mlsanity.com/paper/2403.13787/) (2024)
- [CMMLU: Measuring massive multitask language understanding in Chinese](https://mlsanity.com/paper/2306.09212/) (2023)
- [JudgeLM: Fine-tuned Large Language Models are Scalable Judges](https://mlsanity.com/paper/2310.17631/) (2023)
- [JudgeBench: A Benchmark for Evaluating LLM-based Judges](https://mlsanity.com/paper/2410.12784/) (2024)
- [MT-Bench-101: A Fine-Grained Benchmark for Evaluating Large Language Models in Multi-Turn Dialogues](https://mlsanity.com/paper/2402.14762/) (2024)
- [Inference-Time Scaling for Generalist Reward Modeling](https://mlsanity.com/paper/2504.02495/) (2025)
- [WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild](https://mlsanity.com/paper/2406.04770/) (2024)
- [Generative Judge for Evaluating Alignment](https://mlsanity.com/paper/2310.05470/) (2023)
- [RM-R1: Reward Modeling as Reasoning](https://mlsanity.com/paper/2505.02387/) (2025)
- [AlignBench: Benchmarking Chinese Alignment of Large Language Models](https://mlsanity.com/paper/2311.18743/) (2023)
- [RMB: Comprehensively Benchmarking Reward Models in LLM Alignment](https://mlsanity.com/paper/2410.09893/) (2024)
- [xVerify: Efficient Answer Verifier for Reasoning Model Evaluations](https://mlsanity.com/paper/2504.10481/) (2025)
- [CompassJudger-1: All-in-one Judge Model Helps Model Evaluation and Evolution](https://mlsanity.com/paper/2410.16256/) (2024)
- [Improve LLM-as-a-Judge Ability as a General Ability](https://mlsanity.com/paper/2502.11689/) (2025)
- [Beyond Scalar Reward Model: Learning Generative Judge from Preference Data](https://mlsanity.com/paper/2410.03742/) (2024)

## Built on by (most cited first, 12 of 12)

- [SCI-Verifier: Scientific Verifier with Thinking](https://mlsanity.com/paper/2509.24285/) (2025)
- [Evaluating and Mitigating LLM-as-a-judge Bias in Communication Systems](https://mlsanity.com/paper/2510.12462/) (2025)
- [S2J: Bridging the Gap Between Solving and Judging Ability in Generative Reward Models](https://mlsanity.com/paper/2509.22099/) (2025)
- [Think-with-Rubrics: From External Evaluator to Internal Reasoning Guidance](https://mlsanity.com/paper/2605.07461/) (2026)
- [SCI-PRM: A Tool Aware Process Reward Model for Scientific Reasoning Verification](https://mlsanity.com/paper/2606.04579/) (2026)
- [TokenRatio: Principled Token-Level Preference Optimization via Ratio Matching](https://mlsanity.com/paper/2605.12288/) (2026)
- [JudgePanel: A Compact Judge with Panel Deliberation via Adaptive Multi-Reward Reinforcement Learning](https://mlsanity.com/paper/2608.29168/) (2026)
- [Representational alignment yields generalizable safety in language models](https://mlsanity.com/paper/2609.04022/) (2026)
- [UniRRM: Unified Reasoning Reward Models Across Languages and Evaluation Paradigms](https://mlsanity.com/paper/2609.05910/) (2026)
- [QVAC Genesis III: A Large-Scale, High-Quality Open Synthetic STEM Corpus for Efficient Language Model Pre-Training](https://mlsanity.com/paper/2609.19513/) (2026)
- [DCRL: Decoupling and Coupling Reinforcement Learning via Policy-Reward Manifold Alignment](https://mlsanity.com/paper/2609.27572/) (2026)
- [RM-OPD: On-Policy Distillation for Generative Reward Models](https://mlsanity.com/paper/2610.20174/) (2026)

## Abstract (arXiv)

Recently, the role of LLM-as-judge in evaluating large language models has gained prominence. However, current judge models suffer from narrow specialization and limited robustness, undermining their capacity for comprehensive evaluations. In this work, we present CompassJudger-2, a novel generalist judge model that overcomes these limitations via a task-driven, multi-domain data curation strategy. Central to our approach is supervising judgment tasks with verifiable rewards, guiding intrinsic critical reasoning through rejection sampling to foster robust, generalizable judgment capabilities. We introduce a refined learning objective with margin policy gradient loss to enhance performance. Empirically, CompassJudger-2 achieves superior results across multiple judge and reward benchmarks, and our 7B model demonstrates competitive judgment accuracy with significantly larger models like DeepSeek-V3 and Qwen3-235B-A22B. Additionally, we propose JudgerBenchV2, a comprehensive benchmark evaluating cross-domain judgment accuracy and rank consistency to standardize judge model evaluation. These contributions advance robust, scalable LLM judgment and establish new performance and evaluation standards.