Papersby GlyphNot Every Rubric Teaches Equally: Policy-Aware Rubric Rewards for RLVR research paper by Scale AI, 2026
Scale AI · Training and scaling · May 19, 2026 · 13 citations · 5 upvotes
What it shows
POW3R is a policy-aware framework for reinforcement learning with rubric-based rewards that adapts criterion weights during training to improve policy optimization while preserving human-defined criteria importance.
By Utkarsh Tyagi, Xingang Guo, MohammadHossein Rezaei and 5 more · arXiv 2605.20164 · PDF
Hugging Face's summary; not yet checked by hand.
More from Scale AI
All 25Root-Cause Attribution Is a Search Problem: Continual Search for Long-Horizon Agent FailuresContinual Search improves automated root-cause attribution in long agent execution traces by iteratively prompting diagnosis until unresolved evidence is found.
Scale AI5 upvotesRead →SteerDuplex: Steerable Duplex Speech Dialogue ModelsA full-duplex speech model that follows spoken instructions on tone, persona, pace and voice, with a benchmark of 390 prompts to test it.Scale AI3 citations6 upvotesRead →Studying Without a Syllabus: Task-Agnostic Environment PreprocessingAn agent can explore unfamiliar environments without task-specific guidance to build reusable artifacts that reduce later inference costs, though larger study budgets do not always improve results.Scale AI1 citations4 upvotesRead →HarnessOpt-Bench: Evaluating LLMs at Harness OptimizationHarnessOpt-Bench measures how well frontier LLMs iteratively improve agent harnesses under constrained evaluation budgets, revealing substantial variation across models and tasks.Scale AI12 citations35 upvotesRead →Model or Harness? An Interaction-Centric Taxonomy for Localizing Agent FailuresAn interaction-centric taxonomy localizes agent failures to specific component interactions to guide targeted repairs across diverse architectures.Scale AI11 citations10 upvotesRead →SWE-INTERACT: Reimagining SWE Benchmarks as User-Driven Long-Horizon Coding SessionsSWE-Interact presents a testbed that evaluates coding agents in realistic multi-turn, user-driven software engineering scenarios, revealing significant gaps between single-turn performance and interactive task completion.Scale AI23 citations7 upvotesRead →Reward Hacking in Rubric-Based Reinforcement LearningResearch examines reward hacking in rubric-based reinforcement learning, identifying verifier failure and rubric-design limitations as key sources of divergence between training and evaluation metrics.Scale AI33 citations4 upvotesRead →HiL-Bench (Human-in-Loop Benchmark): Do Agents Know When to Ask for Help?Frontier AI agents struggle with judgment calls about when to seek help, leading to poor performance on incomplete or ambiguous tasks despite having sufficient capabilities.Scale AI28 citations4 upvotesRead →
Other training and scaling papers
TopicLoRA: Low-Rank Adaptation of Large Language ModelsLoRA fine-tunes a large model by training small low-rank matrices, cutting trainable parameters by 10,000 times.
Microsoft25.6k citations66 upvotesRead →Scaling Laws for Neural Language ModelsLanguage model loss falls as a smooth power law as model size, data and compute grow.
OpenAI9,592 citations12 upvotesRead →Training Compute-Optimal Large Language ModelsChinchilla: for a fixed compute budget, train a smaller model on more data; parameters and tokens should grow together.
Google DeepMind4,035 citations13 upvotesRead →Megatron-LM: Training Multi-Billion Parameter Language Models Using Model ParallelismMegatron-LM splits each Transformer layer across GPUs to train models with billions of parameters.
NVIDIA3,387 citations5 upvotesRead →DeepSeek LLM: Scaling Open-Source Language Models with LongtermismDeepSeek LLM, an open-source language model project, develops a large dataset and employs SFT and DPO to achieve performance surpassing LLaMA-2 70B and GPT-3.5 in various benchmarks and open-ended evaluations.
DeepSeek872 citations56 upvotesRead →LoRA Learns Less and Forgets LessLoRA learns less than full fine-tuning on code and math, but forgets less of what the model already knew.
Databricks486 citations91 upvotesRead →
About this paper
- Venue
- arXiv.org
- Citations
- 13, 3 influential · Semantic Scholar
- Upvotes
- 5 · Hugging Face
- Lab
- Scale AI · on Companies · on Acquisitions · on awards · on breaches · on Attested · on Rounds · on Downtime · on labs · on Leaders · on marketplaces · on Allied · on Paydays · on quotes · on salaries · on Nines · on socials · on startups · on terms · on Titlewave
Changes
Citations rose from 12 to 13.
Influential citations rose from 2 to 3.
Citations rose from 10 to 12.
Influential citations rose from 1 to 2.
Citations rose from 9 to 10.
Influential citations rose from 0 to 1.
Citations rose from 6 to 9.
A first count of 0 influential citations.
A first count of 6 citations.
Added to the list.