RISED: Rubrics for Agentic Multi-Environment Selection and Self-Distillation
RISED: Rubrics for Agentic Multi-Environment Selection and Self-Distillation
RISED 提出一套方法,透過評分準則引導智能體在多個互動環境中的資料選擇與策略監督。LLM 評判員以跨環境共用的預設評分準則為每次 rollout 標記,協助選取資料;正向評分準則為 on-policy 自我蒸餾教師提供額外的 token 級監督,負向評分準則則引導後續生成避開反覆出現的失敗模式。不同模型骨幹的測試中,RISED 的跨環境平均通過率最高,且在每個個別環境均排名第一或第二。
AuthorsJingtan Wang†**, Sirajul Salekin, Young mok Jung, Javier Movellan, Bryan Kian Hsiang Low†, Manjot Bilkhu
Training a single LLM agent jointly across diverse interactive environments has attracted increasing attention as a route to generalist agents. Existing curriculum and data-selection strategies often allocate training at the environment level or prioritize local reward-based signals, without explicitly considering relationships between current rollouts across environments for prompt-group selection. Meanwhile, as environments are learned at different rates, all-failure and all-success rollout groups can coexist within a batch, leaving those data without group-relative reward signals. Both challenges highlight limitations of relying solely on scalar rewards in multi-environment RL: they provide limited information about cross-environment relationships and no within-group reward contrast when rewards are identical. This motivates richer textual feedback, such as rubrics describing rollout behaviours, to guide learning. Beyond rubrics’ usage as reward, we repurpose rubrics to guide both online data selection and policy supervision. An LLM judge tags each rollout using a predefined rubric vocabulary shared across environments. The resulting profiles guide the selection of data that aligns with the overall behavioural composition of the mixed-environment batch while limiting overlap with already-selected data. Available positive rubrics (describing desired behaviours) provide privileged context for an on-policy self-distillation teacher, supplying additional token-level supervision, while negative rubrics (describing undesired behaviours) guide subsequent rollout generation away from recurring failure modes. Together, these components form RISED. Across model backbones, RISED achieves the highest mean pass rate across environments and ranks first or second in every individual environment. Rubric-based analysis of RISED can further characterize the behavioural changes accompanying these gains.
- † National University of Singapore
- ** Work done while at Apple
Related readings and updates.
Designing effective reward signals for open-domain question answering is challenging because high-quality responses must simultaneously satisfy multiple aspects of answer quality that are difficult to capture with a holistic scalar objective. We introduce a rubric-based reward framework that generates query-specific rubrics grounded in retrieved evidence and decomposed into multiple quality dimensions, providing fine-grained supervision during…
Dense image captioning is critical for cross-modal alignment in vision-language pretraining and text-to-image generation, but scaling expert-quality annotations is prohibitively expensive. While synthetic captioning via strong vision-language models (VLMs) is a practical alternative, supervised distillation often yields limited output diversity and weak generalization. Reinforcement learning (RL) could overcome these limitations, but its…
來源:Apple Machine Learning Research · machinelearning.apple.com