30 open-source projects similar to leaplabthu/absolute-zero-reasoner, ranked by shared indexed features. Tags may describe platforms or build tools rather than the same primary purpose. Check each project’s use case, license, and deployment requirements before treating it as a replacement.
This repository contains the official implementation for the paper "AutoLogi: Automated Generation of Logic Puzzles for Evaluating Reasoning Abilities of Large Language Models".
We introduce ReCall, a novel framework that trains LLMs to Reason with Tool Call via reinforcement learning—without requiring any supervised data on tool use trajectories or reasoning steps. ReCall empowers LLMs to agentically use and combine arbitrary tools like OpenAI o3, offering an…
Aligning Text and Embodied Environments for Interactive Learning Mohit Shridhar, Xingdi (Eric) Yuan, Marc-Alexandre Côté, Yonatan Bisk, Adam Trischler, Matthew Hausknecht ICLR 2021
We introduce Enigmata, the first comprehensive suite tailored for improving LLMs with puzzle reasoning skills, which integrates seamlessly with reinforcement learning using verifiable rule-based rewards.
G1: Bootstrapping Perception and Reasoning Abilities of Vision-Language Model via Reinforcement Learning
MLGym A New Framework and Benchmark for Advancing AI Research Agents
//: # (![Hugging Face Collection(https://img.shields.io/badge/Models-fcd022?style=for-the-badge&logo=huggingface&logoColor=000)]())
Optimus-3: Dual-Router Aligned Mixture-of-Experts Agent with Dual-Granularity Reasoning-Aware Policy Optimization Zaijing Li 1 2 , Yuquan Xie 1 , Rui Shao 1✉ , Gongwei Chen 1 , Weili Guan 1 , Dongmei Jiang 2 , Liqiang Nie 1✉ 1 Harbin Institute of…
💫SSR-Zero: Simple Self-Rewarding Reinforcement Learning for Machine Translation
Repository with environment and training scripts for paper Cross-Environment Cooperation Enables Zero-shot Multi-agent Coordination (Jha et. al, 2025)
A Collection of Competitive Text-Based Games for Language Model Evaluation and Reinforcement Learning
LMGame Bench and Gaming Agent 📜 Paper | 🏆 Leaderboard | 📺 Gallery | 🌐 Website
NeurIPS 2025 The official repo of SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond
MLE-Dojo: Interactive Environments for Empowering LLM Agents in Machine Learning Engineering
Trans0 aims to initialize a multilingual LLM as a translation agent via monolingual data. This is a public version with all in-house implementation replaced by huggingface trl.
NeurIPS 2025 Spotlight Reasoning Environments for Reinforcement Learning with Verifiable Rewards
We propose ZeroGUI, a fully automated online reinforcement learning framework that enables GUI agents to train and adapt in interactive environments at zero human cost.
📊 Main Results ✨ Getting Started • 📨 Contact • 🎈 Citation • 🌟 Star History
R2E-Gym: Procedural Environment Generation and Hybrid Verifiers for Scaling Open-Weights SWE Agents
Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning
This repository contains the code for PuzzleJAX, a GPU-accelerated implementation of PuzzleScript (https://www.puzzlescript.net)