A Collection of Competitive Text-Based Games for Language Model Evaluation and Reinforcement Learning
☆430Oct 5, 2026Updated last week
Alternatives and similar repositories for TextArena
Users that are interested in TextArena are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆119Apr 7, 2026Updated 6 months ago
- SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning☆208Mar 27, 2026Updated 6 months ago
- [NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards☆1,527Apr 17, 2026Updated 5 months ago
- ☆29May 30, 2026Updated 4 months ago
- Our library for RL environments + evals☆4,696Updated this week
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Benchmarking Agentic LLM and VLM Reasoning On Games☆273Apr 9, 2026Updated 6 months ago
- A Gym for Agentic LLMs☆510Jan 21, 2026Updated 8 months ago
- 🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.☆671Jan 29, 2026Updated 8 months ago
- ☆74Feb 4, 2026Updated 8 months ago
- ☆62May 21, 2025Updated last year
- Resources for the Enigmata Project.☆85Aug 13, 2025Updated last year
- SkyRL: A Modular Full-stack RL Library for LLMs☆2,406Updated this week
- ☆1,193Jan 10, 2026Updated 9 months ago
- [ICLR 2026] LLM/VLM gaming agents and model evaluation through games.☆990Nov 16, 2025Updated 10 months ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- Agentic RL Training at Scale☆2,156Updated this week
- Sotopia: an Open-ended Social Learning Environment (ICLR 2024 spotlight)☆335Jun 5, 2026Updated 4 months ago
- Code and implementations for the ACL 2025 paper "AgentGym: Evolving Large Language Model-based Agents across Diverse Environments" by Zhi…☆851May 30, 2026Updated 4 months ago
- Agent RL framework for LLM agents: multi-turn reinforcement learning with StarPO and reasoning-collapse diagnostics☆2,823Aug 23, 2026Updated last month
- Implementation of the Decrypto benchmark for multi-agent reasoning and theory of mind.☆24Jan 19, 2026Updated 8 months ago
- Code for Paper: Training Software Engineering Agents and Verifiers with SWE-Gym [ICML 2025]☆748Jul 29, 2025Updated last year
- A scalable asynchronous reinforcement learning implementation with in-flight weight updates.☆434Aug 5, 2026Updated 2 months ago
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Asy…☆10,081Oct 5, 2026Updated last week
- ☆117Jul 2, 2024Updated 2 years ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- The official starter-kit for NeurIPS 2025 mind games competition☆21May 5, 2026Updated 5 months ago
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆23,837Updated this week
- Benchmark and research code for the paper SWEET-RL Training Multi-Turn LLM Agents onCollaborative Reasoning Tasks☆272May 5, 2025Updated last year
- slime is an LLM post-training framework for RL Scaling.☆8,637Updated this week
- Democratizing Reinforcement Learning for LLMs☆5,860Updated this week
- Sotopia-RL: Reward Design for Social Intelligence☆54Apr 1, 2026Updated 6 months ago
- Storing long contexts in tiny caches with self-study☆340Mar 23, 2026Updated 6 months ago
- Manage scalable open LLM inference endpoints in Slurm clusters☆296Jul 11, 2024Updated 2 years ago
- Framework for evaluating and improving agents☆6,036Updated this week
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- ☆14Mar 5, 2024Updated 2 years ago
- [ICLR 2026] End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning☆406Mar 30, 2026Updated 6 months ago
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"☆94Oct 30, 2024Updated last year
- Official Repo for Open-Reasoner-Zero☆2,099Jun 2, 2025Updated last year
- [ICLR 2026] Learning to Reason without External Rewards☆426Jan 26, 2026Updated 8 months ago
- AllenAI's post-training codebase☆3,891Updated this week
- [ICLR'26] MARSHAL: Incentivizing Multi-Agent Reasoning via Self-Play with Strategic LLMs☆57Apr 17, 2026Updated 5 months ago