Skip to content
Papers.

Not Every Rubric Teaches Equally: Policy-Aware Rubric Rewards for RLVR research paper by Scale AI, 2026

Scale AI · May 19, 2026 · Training and scaling · 5 upvotes 4 months ago

Read on arXiv

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.

Hugging Face's summary; not yet checked by hand.

More from Scale AI

All 25
PaperCitations
Root-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.Agents and evaluation · Sep 20262 weeks ago-
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.Multimodal and robotics · Sep 20262 weeks ago-
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.Agents and evaluation · Sep 20262 weeks ago-
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.Agents and evaluation · Aug 20267 weeks ago-
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.Agents and evaluation · Jul 20268 weeks ago-
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.Agents and evaluation · Jun 20262 months ago-
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.Reasoning · May 20264 months ago-
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.Agents and evaluation · Apr 20265 months ago-

Other training and scaling papers

Topic
PaperCitations
LoRA: 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.Microsoft · Jun 20215 years ago23.3k
Scaling Laws for Neural Language ModelsLanguage model loss falls as a smooth power law as model size, data and compute grow.OpenAI · Jan 20206 years ago9,065
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 DeepMind · Mar 20224 years ago3,756
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.NVIDIA · Sep 20197 years ago3,179
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.DeepSeek · Jan 2024 · Unverified2 years ago855
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.Databricks · May 20242 years ago407
About this paper
Authors
Utkarsh Tyagi, Xingang Guo, MohammadHossein Rezaei and 5 more
arXiv
2605.20164 · PDF
Citations
Not counted yet · Semantic Scholar
Upvotes
5 · Hugging Face
Lab
Scale AI · on Companies · on Acquisitions

Changes

What changed
New paperAdded to the listSep 26, 2026today

New papers by email

Monday afternoons, only in weeks with new papers from the labs.

Double opt-in. Unsubscribe any time.