Not Every Rubric Teaches Equally: Policy-Aware Rubric Rewards for RLVR
The paper introduces POW3R, a policy-aware rubric reward framework for reinforcement learning with verifiable rewards. This framework adapts criterion-level reward weights during training to improve the effectiveness of rubric-based rewards. The authors demonstrate that POW3R significantly enhances performance across various policies and datasets compared to traditional methods.
- ▪POW3R preserves human weights and category balance while adapting rewards during training.
- ▪The framework emphasizes criteria that currently distinguish the policy's outputs.
- ▪POW3R outperformed vanilla GRPO with rubric rewards in 24 out of 30 comparisons.
arXiv cs.AI files mainly under ai research. We currently carry 1,128 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | arXiv cs.AI |
| Canonical URL | https://arxiv.org/abs/2605.20164 |
| Publication time | Wed, 20 May 2026 00:00:00 -0400 |
| Retrieval time | 2026-05-20T04:04:59.484Z |
| Last seen | 2026-05-20T04:04:59.484Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | L4VVWs6VevrP |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Computer Science > Artificial Intelligence arXiv:2605.20164 (cs) [Submitted on 19 May 2026] Title:Not Every Rubric Teaches Equally: Policy-Aware Rubric Rewards for RLVR Authors:Utkarsh Tyagi, Xingang Guo, MohammadHossein Rezaei, Daniel George, Anas Mahmoud, Jackson Lee, Bing Liu, Yunzhong He View a PDF of the paper titled Not Every Rubric Teaches Equally: Policy-Aware Rubric Rewards for RLVR, by Utkarsh Tyagi and 7 other authors View PDF HTML (experimental) Abstract:Reinforcement learning with verifiable rewards has made post-training highly effective when correctness can be checked automatically. However, many important model behaviors require satisfying several qualitative criteria at once.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv cs.AI.
Discussion
0 commentsMore from arXiv cs.AI
