Tag
The paper introduces LatentGRM, a latent evaluation framework that performs rubric-guided reward modeling in continuous latent space via semantics-preserving chunk compression, achieving competitive preference accuracy against SFT judges while compressing evaluation trajectories 8.9–9.2× and reducing inference time 6.1–7.0× at 4B/8B scales.
RubSE is a framework that uses rubric-guided self-evolution to enhance the stability of UI-to-code generation by mitigating visual repair coupling and trajectory collapse.
RoRo introduces a rubric-guided process reward framework for stepwise model routing in Large Reasoning Models, using process rewards alongside outcome rewards to train a routing policy via GRPO, outperforming baselines on reasoning benchmarks.
Co-ReAct introduces a rubric-guided action-selection framework that uses rubrics as step-level guidance during inference for ReAct agents, improving trajectory quality and outperforming baselines on DeepResearchBench and SQA-CS-V2.
This paper introduces RubricEM, a reinforcement learning framework that uses rubric-guided policy decomposition and reflection-based meta-policy evolution to train deep research agents for long-form tasks. The resulting RubricEM-8B model demonstrates strong performance on long-form research benchmarks by leveraging stage-aware planning and denser semantic feedback.