# Algorineko/AgenticArXiv-RL

<https://repo.masters-masters.com/en/repos/Algorineko/AgenticArXiv-RL>

[Home](https://repo.masters-masters.com/en) › [Algorineko](https://repo.masters-masters.com/en/owners/Algorineko) › [AgenticArXiv-RL](https://repo.masters-masters.com/en/repos/Algorineko/AgenticArXiv-RL)

Algorineko/AgenticArXiv-RL has 231 stars on GitHub. Its RepoMasters card: Prototype tier. Staged SFT→DPO→GRPO/OPD reinforcement learning pipeline for training…

| Field | Value |
| --- | --- |
| Owner | [Algorineko](https://repo.masters-masters.com/en/owners/Algorineko) |
| Stars | 231 |
| Forks | 85 |
| Language | [Python](https://repo.masters-masters.com/en/languages/python) |
| License | MIT |
| Created | 2026 |
| Tier | [Prototype (100 to 249 ★)](https://repo.masters-masters.com/en/ranks/rush) |
| View on GitHub | [Algorineko/AgenticArXiv-RL](https://github.com/Algorineko/AgenticArXiv-RL) |

## Repository

Staged SFT→DPO→GRPO/OPD reinforcement learning pipeline for training a ReAct tool-use agent on arXiv paper retrieval tasks, with a deterministic snapshot-replay environment.

The tier for repos with 100 to 249 ★. Published odds per card pulled: 70%. Rarity: Common.

## Nearby in Python

- [ernie-research/NAVA · ★ 231 · Python · Prototype](https://repo.masters-masters.com/en/repos/ernie-research/NAVA)
- [Ropedia/ropedia-w0 · ★ 231 · Python · Prototype](https://repo.masters-masters.com/en/repos/Ropedia/ropedia-w0)
- [Balanov/verdict · ★ 231 · Python · Prototype](https://repo.masters-masters.com/en/repos/Balanov/verdict)
- [rspeer/ordered-set · ★ 231 · Python · Prototype](https://repo.masters-masters.com/en/repos/rspeer/ordered-set)
- [lxyu/weibo · ★ 231 · Python · Prototype](https://repo.masters-masters.com/en/repos/lxyu/weibo)
- [aldro61/pu-learning · ★ 231 · Python · Prototype](https://repo.masters-masters.com/en/repos/aldro61/pu-learning)

---
Data: GitHub · Illustration drawn by RepoMasters from the repo’s ID and its language color.