---
license: apache-2.0
library_name: transformers
pipeline_tag: text-generation
base_model: meta-llama/Llama-3.1-8B-Instruct
---

# SPADER: Step-wise Peer Advantage with Diversity-Aware Exploration Rewards for Multi-Answer Question Answering

This repository contains the fine-tuned Llama-3.1-8B model checkpoint developed using the SPADER reinforcement learning framework, as presented in the paper [SPADER: Step-wise Peer Advantage with Diversity-Aware Exploration Rewards for Multi-Answer Question Answering](https://huggingface.co/papers/2606.00593).

## Model Description

SPADER is a reinforcement learning framework designed for long-horizon tool-use agents in Multi-Answer QA. It introduces:
- **Step-wise Peer Advantage (SPA)**: A critic-free step-level credit assignment mechanism that aligns parallel trajectories by decision step and estimates advantages from peer returns.
- **Diversity-Aware Exploration Reward**: Promotes long-tail entity discovery by upweighting rare findings and downweighting redundant ones.

This checkpoint represents the Llama-3.1-8B-Instruct base model trained with SPADER.

- **Repository:** [KhanCold/spader](https://github.com/KhanCold/spader)
- **Paper:** [arXiv:2606.00593](https://arxiv.org/abs/2606.00593)

## Citation

```bibtex
@misc{shi2026spaderstepwisepeeradvantage,
      title={SPADER: Step-wise Peer Advantage with Diversity-Aware Exploration Rewards for Multi-Answer Question Answering}, 
      author={Qiming Shi and Zhaolu Kang and Yunfan Zhou and Di Weng and Yingcai Wu},
      year={2026},
      eprint={2606.00593},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2606.00593}, 
}
```