SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning
☆199Mar 27, 2026Updated 3 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☆411Updated this week
- 🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.☆667Jan 29, 2026Updated 5 months ago
- ☆120Apr 7, 2026Updated 3 months ago
- [ICLR'26] MARSHAL: Incentivizing Multi-Agent Reasoning via Self-Play with Strategic LLMs☆54Apr 17, 2026Updated 3 months ago
- ☆28May 30, 2026Updated last month
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Sotopia-RL: Reward Design for Social Intelligence☆52Apr 1, 2026Updated 3 months ago
- A Gym for Agentic LLMs☆502Jan 21, 2026Updated 6 months ago
- ☆70Feb 4, 2026Updated 5 months ago
- Multi-Turn RL Training System with AgentTrainer for Language Model Game Reinforcement Learning☆65Dec 18, 2025Updated 7 months ago
- Reinforcing General Reasoning without Verifiers☆102Jun 24, 2025Updated last year
- Defeating the Training-Inference Mismatch via FP16☆197Nov 14, 2025Updated 8 months ago
- [ICLR 2026] Learning to Reason without External Rewards☆417Jan 26, 2026Updated 5 months ago
- Code for "Language Models Can Learn from Verbal Feedback Without Scalar Rewards"☆65Jan 5, 2026Updated 6 months ago
- Resources for the Enigmata Project.☆82Aug 13, 2025Updated 11 months 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.
- RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.☆2,753Apr 14, 2026Updated 3 months ago
- Optimizing Anytime Reasoning via Budget Relative Policy Optimization☆54Jul 15, 2025Updated last year
- ☆60May 21, 2025Updated last year
- ☆15Oct 13, 2025Updated 9 months ago
- [ICLR 2026] Adaptive Social Learning via Mode Policy Optimization for Language Agents☆51Feb 2, 2026Updated 5 months ago
- Regressing the Relative Future: Efficient Policy Optimization for Multi-turn RLHF☆25Oct 8, 2024Updated last year
- [ICLR 2026] Vision-Zero: Scalable VLM Self-Improvement via Strategic Gamified Self-Play.☆136Feb 6, 2026Updated 5 months ago
- Verlog: A Multi-turn RL framework for LLM agents☆73Apr 28, 2026Updated 2 months ago
- [NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards☆1,463Apr 17, 2026Updated 3 months ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- [ICLR-2026] Official Implementation of our paper "THOR: Tool-Integrated Hierarchical Optimization via RL for Mathematical Reasoning".☆33Feb 26, 2026Updated 4 months ago
- SeRL: Self-Play Reinforcement Learning for Large Language Models with Limited Data☆24Jan 24, 2026Updated 5 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 10 months ago
- A version of verl to support diverse tool use [TMLR 2026]☆1,021Updated this week
- [ICLR2026] codes for R-Zero: Self-Evolving Reasoning LLM from Zero Data (https://www.arxiv.org/pdf/2508.05004)☆824Feb 4, 2026Updated 5 months ago
- ☆21Apr 16, 2025Updated last year
- Sotopia: an Open-ended Social Learning Environment (ICLR 2024 spotlight)☆317Jun 5, 2026Updated last month
- [arxiv: 2604.14142] From P(y|x) to P(y): Investigating Reinforcement Learning in Pre-train Space☆17Apr 16, 2026Updated 3 months ago
- SkyRL: A Modular Full-stack RL Library for LLMs☆2,085Updated 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.
- verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in…☆2,140Jun 9, 2026Updated last month
- A Framework for LLM-based Multi-Agent Reinforced Training and Inference☆538Apr 14, 2026Updated 3 months ago
- [ICLR 2026] RuleReasoner: Reinforced Rule-based Reasoning via Domain-aware Dynamic Sampling☆39Feb 25, 2026Updated 4 months ago
- [ICML 2026 Spotlight] On the Interplay of Pre-Training, Mid-Training, and RL on Reasoning Language Models☆162Jun 8, 2026Updated last month
- [ArXiv 2025] Denial-of-Service Poisoning Attacks on Large Language Models☆23Oct 22, 2024Updated last year
- [NeurIPS'25 Spotlight] ARM: Adaptive Reasoning Model☆68Apr 6, 2026Updated 3 months ago
- ☆336May 31, 2025Updated last year