SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning
☆210Mar 27, 2026Updated 7 months ago
Alternatives and similar repositories for spiral
Users that are interested in spiral are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A Collection of Competitive Text-Based Games for Language Model Evaluation and Reinforcement Learning☆435Oct 5, 2026Updated 3 weeks ago
- 🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.☆674Jan 29, 2026Updated 9 months ago
- ☆120Apr 7, 2026Updated 6 months ago
- [ICLR'26] MARSHAL: Incentivizing Multi-Agent Reasoning via Self-Play with Strategic LLMs☆58Oct 13, 2026Updated 2 weeks ago
- ☆30May 30, 2026Updated 5 months ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Sotopia-RL: Reward Design for Social Intelligence☆54Apr 1, 2026Updated 7 months ago
- [ECCV 2026] VideoScience-Bench: Benchmarking Scientific Reasoning in Video Generations☆12Feb 13, 2026Updated 8 months ago
- A Gym for Agentic LLMs☆511Jan 21, 2026Updated 9 months ago
- ☆73Feb 4, 2026Updated 8 months ago
- Code for "Language Models Can Learn from Verbal Feedback Without Scalar Rewards"☆65Jan 5, 2026Updated 9 months ago
- Reinforcing General Reasoning without Verifiers☆103Jun 24, 2025Updated last year
- Defeating the Training-Inference Mismatch via FP16☆199Nov 14, 2025Updated 11 months ago
- Multi-Turn RL Training System with AgentTrainer for Language Model Game Reinforcement Learning☆67Dec 18, 2025Updated 10 months ago
- Resources for the Enigmata Project.☆86Aug 13, 2025Updated last year
- 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.
- Agent RL framework for LLM agents: multi-turn reinforcement learning with StarPO and reasoning-collapse diagnostics☆2,832Updated this week
- [ICLR 2026] Learning to Reason without External Rewards☆426Jan 26, 2026Updated 9 months ago
- Optimizing Anytime Reasoning via Budget Relative Policy Optimization☆54Jul 15, 2025Updated last year
- ☆15Oct 13, 2025Updated last year
- [ICLR 2026] Adaptive Social Learning via Mode Policy Optimization for Language Agents☆52Feb 2, 2026Updated 8 months ago
- ☆62May 21, 2025Updated last year
- Verlog: A Multi-turn RL framework for LLM agents☆74Aug 8, 2026Updated 2 months ago
- DSGBench is a game benchmark designed to evaluate LLM agents across diverse, dynamic environments, including games like StarCraft II and …☆10May 5, 2026Updated 5 months ago
- Research Code for "ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL"☆210Apr 17, 2025Updated last year
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- [NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards☆1,541Apr 17, 2026Updated 6 months ago
- The official repo for “Unleashing the Reasoning Potential of Pre-trained LLMs by Critique Fine-Tuning on One Problem” [EMNLP25]☆33Sep 1, 2025Updated last year
- [ICLR-2026] Official Implementation of our paper "THOR: Tool-Integrated Hierarchical Optimization via RL for Mathematical Reasoning".☆33Aug 4, 2026Updated 2 months ago
- A version of verl to support diverse tool use [TMLR 2026]☆1,051Jul 15, 2026Updated 3 months ago
- [NeurIPS 2026 Meta-Agents] PostTrainBench⁰ — Can LLM agents automate LLM post-training without gradients?☆16Sep 4, 2026Updated last month
- Regressing the Relative Future: Efficient Policy Optimization for Multi-turn RLHF☆25Oct 8, 2024Updated 2 years ago
- [COLM 2026] From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement.☆194Aug 12, 2026Updated 2 months ago
- ☆335May 31, 2025Updated last year
- [ICLR2026] codes for R-Zero: Self-Evolving Reasoning LLM from Zero Data (https://www.arxiv.org/pdf/2508.05004)☆861Feb 4, 2026Updated 8 months ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- SeRL: Self-Play Reinforcement Learning for Large Language Models with Limited Data☆26Jan 24, 2026Updated 9 months ago
- Dr. MAS is an end-to-end RL training framework for multi-agent LLM systems, supporting the co-training of multiple (heterogeneous) LLMs.☆172Sep 26, 2026Updated last month
- Natural Language Reinforcement Learning☆104Jul 30, 2025Updated last year
- ☆12Mar 10, 2024Updated 2 years ago
- [ICLR 2026] A Framework for LLM-based Multi-Agent Reinforced Training and Inference☆571Aug 20, 2026Updated 2 months ago
- ☆13Dec 19, 2024Updated last year
- SkyRL: A Modular Full-stack RL Library for LLMs☆2,480Updated this week