AI News HubLIVE
Original source2 min read

BV-Blend: Uncertainty-Weighted Historical Baselines for Stable Critic-Free RL with Verifiable Rewards

Critic-free RL with verifiable rewards (RLVR) like GRPO avoids training a value function but can be unstable when all rollouts in a group receive identical rewards. BV-Blend stabilizes advantage estimation by combining prompt-local statistics with historical moments from semantic clusters, using a confidence weight derived from a standard error of the mean proxy. Experiments show improved stability and performance on verifiable reasoning benchmarks.

SourcearXiv AIAuthor: Yupeng Chang, Yuan Wu, Yi Chang

[2606.28707] BV-Blend: Uncertainty-Weighted Historical Baselines for Stable Critic-Free RL with Verifiable Rewards

[Submitted on 27 Jun 2026]

Title:BV-Blend: Uncertainty-Weighted Historical Baselines for Stable Critic-Free RL with Verifiable Rewards

View a PDF of the paper titled BV-Blend: Uncertainty-Weighted Historical Baselines for Stable Critic-Free RL with Verifiable Rewards, by Yupeng Chang and 2 other authors

View PDF HTML (experimental)

Abstract:Critic-free reinforcement learning with verifiable rewards (RLVR), exemplified by Group Relative Policy Optimization (GRPO), avoids training a value function (critic) and reduces memory and compute overhead relative to critic-based PPO pipelines for aligning large language models. However, GRPO-style advantage estimation depends on prompt-local (within-prompt-group) reward statistics and can be unstable. In particular, when all rollouts in a prompt group receive identical rewards, the within-group reward variance becomes zero, and group normalization yields zero advantages for that group, impeding learning in cold-start regimes with binary verifiers. We introduce BV-Blend, a critic-free framework that stabilizes advantage estimation by combining prompt-local on-policy statistics with semantic-cluster-conditioned historical moments. BV-Blend maintains EMA-tracked reward moments for each cluster, derives a confidence weight from a standard error of the mean (SEM) proxy, and uses this weight to blend historical and prompt-local baseline and variance statistics into a standardized advantage for PPO-style clipped updates. Experiments on verifiable reasoning benchmarks show that BV-Blend improves training stability and performance, and remains robust in regimes where group-normalized methods may stall.

Subjects:

Artificial Intelligence (cs.AI)

Cite as: arXiv:2606.28707 [cs.AI]

(or arXiv:2606.28707v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2606.28707

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Yupeng Chang [view email] [v1] Sat, 27 Jun 2026 03:25:53 UTC (1,292 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled BV-Blend: Uncertainty-Weighted Historical Baselines for Stable Critic-Free RL with Verifiable Rewards, by Yupeng Chang and 2 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.AI

new | recent | 2026-06

Change to browse by:

cs

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)