rlve
RLVE supports language model reinforcement learning with adaptive, verifiable environments for generating problems and evaluating model outputs.
Share on XLicense: MIT
Overview
RLVE is a research project for scaling reinforcement learning with language models using adaptive, verifiable environments. RLVE-Gym provides environments that generate problems from a random seed and difficulty parameters managed by an environment-specific controller. Developers can turn generated problems into prompts, score model outputs, and inspect verification details. Answer extraction can be configured with markers. The README documents setup with Docker and the slime framework, and links to the paper, code, data, and models.
Key features
- Generate problems from a random seed and controller-selected difficulty parameters.
- Create prompts from generated problems and score model outputs.
- Inspect verification details and configure markers for answer extraction.
Best for
Researchers and developers using verifiable problems to build or evaluate language model reinforcement learning workflows.
- Upstream
- Zhiyuan-Zeng/RLVE
- Fork on GitHub
- Guo-astro/rlve
- Upstream stars
- 249
- Category
- AI agents and LLM tools
- Language
- Python
- License
- MIT
- Forked
- 2026-10-17
- Sync status
- In syncLast synced 2026-10-17
More in AI agents and LLM tools
Provides modular Android development instructions for AI agents, helping them follow specialized workflows. Install individual skills or the full set with Android CLI.
Forked 2026-10-16Last synced 2026-10-17License: Apache-2.0AI agents and LLM toolsGitHub
Pi Agent is a local desktop app for using the Pi AI coding agent on macOS, Windows, and Linux. It helps you manage coding sessions, work with project files, and run saved prompts without setting up a terminal environment.
Forked 2026-10-15Last synced 2026-10-17License: MITAI agents and LLM toolsGitHub
A single-user AI assistant deployed in your Cloudflare account for chat, memory, tasks, notes, and scheduled reminders. It works without relying on a server or account run by the project developers.
Forked 2026-10-15Last synced 2026-10-17License: MITAI agents and LLM toolsGitHub
MiniMind is an open-source project for training a small language model from scratch and studying the LLM pipeline. It helps learners explore how models work through hands-on training and fine-tuning.
Forked 2026-10-14Last synced 2026-10-17License: Apache-2.0AI agents and LLM toolsGitHub