Olmo3-B3PO-7B-ESS1e10

📄 Paper: Parameter Exploration for RLVR via Variational Learning · arXiv:2608.09805

📦 Code: insait-institute/c3po

Olmo-3 7B fine-tuned with B3PO (Bayesian Perturbed Parameter Policy Optimization), from the paper "Parameter Exploration for RLVR via Variational Learning".

3PO is a family of parameter-space exploration strategies for Reinforcement Learning with Verifiable Rewards (RLVR). Instead of relying only on action-space heuristics (temperature, clipping, entropy bonuses), 3PO samples model weights from an approximate posterior learned with the variational optimizer IVON; the amount of weight noise becomes an extra control lever for exploration.

B3PO draws a single weight perturbation from the IVON posterior per gradient step and syncs it to the rollout engine, so each step explores from one perturbed parameter sample.

Note: This is the ESS ablation variant with λ = 1e10; the main run is Olmo3-B3PO-7B (λ = 1e9).

Training

Evaluation

Evaluated on AIME 2024–2026, MATH-500, AMC 2023, and Minerva. See the paper for full results.

Usage

Loads as a standard causal LM:

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("BayesRL/Olmo3-B3PO-7B-ESS1e10")
tok = AutoTokenizer.from_pretrained("BayesRL/Olmo3-B3PO-7B-ESS1e10")

Citation

@misc{venkatkrishna2026parameterexploration,
      title={Parameter Exploration for RLVR via Variational Learning}, 
      author={Vatsal Venkatkrishna and Nico Daheim and Iryna Gurevych},
      year={2026},
      eprint={2608.09805},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2608.09805}, 
}