Cover Image

SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Bo, Guertler, Leon, Yu, Simon, Liu, Zichen, Qi, Penghui, Balcells, Daniel, Liu, Mickel, Tan, Cheston, Shi, Weiyan, Lin, Min, Lee, Wee Sun, Jaques, Natasha
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

TextArena
by: Guertler, Leon, et al.
Published: (2025)

Chasing Moving Targets with Online Self-Play Reinforcement Learning for Safer Language Models
by: Liu, Mickel, et al.
Published: (2025)

STLM Engineering Report: Dropout
by: Hillier, Dylan, et al.
Published: (2024)

Consistently Simulating Human Personas with Multi-Turn Reinforcement Learning
by: Abdulhai, Marwa, et al.
Published: (2025)

Super Tiny Language Models
by: Hillier, Dylan, et al.
Published: (2024)

Enhancing Personalized Multi-Turn Dialogue with Curiosity Reward
by: Wan, Yanming, et al.
Published: (2025)

Multi Agent Reinforcement Learning for Sequential Satellite Assignment Problems
by: Holder, Joshua, et al.
Published: (2024)

Learning to summarize user information for personalized reinforcement learning from human feedback
by: Nam, Hyunji, et al.
Published: (2025)

Zero-Shot Visual Reasoning by Vision-Language Models: Benchmarking and Analysis
by: Nagar, Aishik, et al.
Published: (2024)

MARSHAL: Incentivizing Multi-Agent Reasoning via Self-Play with Strategic LLMs
by: Yuan, Huining, et al.
Published: (2025)

Optimizing Anytime Reasoning via Budget Relative Policy Optimization
by: Qi, Penghui, et al.
Published: (2025)

Cross-environment Cooperation Enables Zero-shot Multi-agent Coordination
by: Jha, Kunal, et al.
Published: (2025)

MEMO: Memory-Augmented Model Context Optimization for Robust Multi-Turn Multi-Agent LLM Games
by: Xie, Yunfei, et al.
Published: (2026)

Adaptive Stopping for Multi-Turn LLM Reasoning
by: Zhou, Xiaofan, et al.
Published: (2026)

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning
by: Ning, Yansong, et al.
Published: (2025)

High-Resolution Visual Reasoning via Multi-Turn Grounding-Based Reinforcement Learning
by: Huang, Xinyu, et al.
Published: (2025)

Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Agents
by: Li, Xu, et al.
Published: (2026)

SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning
by: Xue, Zhenghai, et al.
Published: (2025)

Understanding R1-Zero-Like Training: A Critical Perspective
by: Liu, Zichen, et al.
Published: (2025)

An Efficient Open World Environment for Multi-Agent Social Learning
by: Ye, Eric, et al.
Published: (2025)

SPIRAL: Self-Play Incremental Racing Algorithm for Learning in Multi-Drone Competitions
by: Akgün, Onur
Published: (2025)

TangramSR: Can Vision-Language Models Reason in Continuous Geometric Space?
by: Zong, Yikun, et al.
Published: (2026)

Efficacy of Language Model Self-Play in Non-Zero-Sum Games
by: Liao, Austen, et al.
Published: (2024)

AllReduce Scheduling with Hierarchical Deep Reinforcement Learning
by: Wei, Yufan, et al.
Published: (2025)

Leveraging Team Correlation for Approximating Equilibrium in Two-Team Zero-Sum Games
by: Liu, Naming, et al.
Published: (2024)

GeoZero: Incentivizing Reasoning from Scratch on Geospatial Scenes
by: Wang, Di, et al.
Published: (2025)

Multi-Player Zero-Sum Markov Games with Networked Separable Interactions
by: Park, Chanwoo, et al.
Published: (2023)

Computing Ex Ante Equilibrium in Heterogeneous Zero-Sum Team Games
by: Liu, Naming, et al.
Published: (2024)

TRACER: Turn-level Regret Matching with Inner Reinforcement Credit for Cooperative Multi-LLM Reasoning
by: Li, Chusen, et al.
Published: (2026)

Fast and Furious Symmetric Learning in Zero-Sum Games: Gradient Descent as Fictitious Play
by: Lazarsfeld, John, et al.
Published: (2025)

Offline Two-Player Zero-Sum Markov Games with KL Regularization
by: Chen, Claire, et al.
Published: (2026)

STUPD: A Synthetic Dataset for Spatial and Temporal Relation Reasoning
by: Agrawal, Palaash, et al.
Published: (2023)

Automatic Identification of Samples in Hip-Hop Music via Multi-Loss Training and an Artificial Dataset
by: Cheston, Huw, et al.
Published: (2025)

Reinforcing Multi-Turn Reasoning in LLM Agents via Turn-Level Reward Design
by: Wei, Quan, et al.
Published: (2025)

Triplet-Structured Knowledge Integration for Multi-Turn Medical Reasoning
by: Meng, Zhaohan, et al.
Published: (2025)

Learning to Reason Iteratively and Parallelly for Complex Visual Reasoning Scenarios
by: Jaiswal, Shantanu, et al.
Published: (2024)

Model-Based Reinforcement Learning for Offline Zero-Sum Markov Games
by: Yan, Yuling, et al.
Published: (2022)

Continual Reinforcement Learning by Planning with Online World Models
by: Liu, Zichen, et al.
Published: (2025)

Multi-Garment Customized Model Generation
by: Liu, Yichen, et al.
Published: (2024)

Multi-Agent Reinforcement Learning for Sample-Efficient Deep Neural Network Mapping
by: Krishnan, Srivatsan, et al.
Published: (2025)