Imagen de Portada

ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhang, Qiang, Chen, Boli, Zhang, Fanrui, Ding, Ruixue, Wang, Shihang, Wang, Qiuchen, Huang, Yinfeng, Zhang, Haonan, Zhu, Rongxiang, Wang, Pengyong, Ren, Ailin, Li, Xin, Xie, Pengjun, Liu, Jiawei, Guo, Ning, Zhou, Jingren, Zha, Zheng-Jun
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning
por: Wang, Qiuchen, et al.
Publicado: (2025)

VimRAG: Navigating Massive Visual Context in Retrieval-Augmented Generation via Multimodal Memory Graph
por: Wang, Qiuchen, et al.
Publicado: (2026)

EvoRubric: Self-Evolving Rubric-Driven RL for Open-Ended Generation
por: Guan, Xin, et al.
Publicado: (2026)

ViDoRAG: Visual Document Retrieval-Augmented Generation via Dynamic Iterative Reasoning Agents
por: Wang, Qiuchen, et al.
Publicado: (2025)

Hierarchical Information Enhancement Network for Cascade Prediction in Social Networks
por: Zhang, Fanrui, et al.
Publicado: (2024)

Multi-perspective Memory Enhanced Network for Identifying Key Nodes in Social Networks
por: Zhang, Qiang, et al.
Publicado: (2024)

Tournament-GRPO: Group-Wise Tournament Rewards for Reinforcement Learning in Open-Ended Long-Form Generation
por: Yang, Zixuan, et al.
Publicado: (2026)

Geo-Encoder: A Chunk-Argument Bi-Encoder Framework for Chinese Geographic Re-Ranking
por: Cao, Yong, et al.
Publicado: (2023)

O-Researcher: An Open Ended Deep Research Model via Multi-Agent Distillation and Agentic RL
por: Yao, Yi, et al.
Publicado: (2026)

WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research
por: Li, Zijian, et al.
Publicado: (2025)

PyVision-RL: Forging Open Agentic Vision Models via RL
por: Zhao, Shitian, et al.
Publicado: (2026)

WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agent
por: Geng, Xinyu, et al.
Publicado: (2025)

RaFe: Ranking Feedback Improves Query Rewriting for RAG
por: Mao, Shengyu, et al.
Publicado: (2024)

ForgeryGPT: A Multimodal LLM for Interpretable Image Forgery Detection and Localization
por: Zhang, Fanrui, et al.
Publicado: (2024)

ContextRL: Enhancing MLLM's Knowledge Discovery Efficiency with Context-Augmented RL
por: Lu, Xingyu, et al.
Publicado: (2026)

Think in Parallel, Answer as One: Logit Averaging for Open-Ended Reasoning
por: Wang, Haonan, et al.
Publicado: (2025)

PromptRL: Prompt Matters in RL for Flow-Based Image Generation
por: Wang, Fu-Yun, et al.
Publicado: (2026)

MindSpeed RL: Distributed Dataflow for Scalable and Efficient RL Training on Ascend NPU Cluster
por: Feng, Laingjun, et al.
Publicado: (2025)

LoongRL: Reinforcement Learning for Advanced Reasoning over Long Contexts
por: Wang, Siyuan, et al.
Publicado: (2025)

OpenClaw-RL: Train Any Agent Simply by Talking
por: Wang, Yinjie, et al.
Publicado: (2026)

Agent RL Scaling Law: Agent RL with Spontaneous Code Execution for Mathematical Problem Solving
por: Mai, Xinji, et al.
Publicado: (2025)

The Two-Stage Decision-Sampling Hypothesis: Understanding the Emergence of Self-Reflection in RL-Trained LLMs
por: Zhao, Zibo, et al.
Publicado: (2026)

Knowledge is Not Enough: Injecting RL Skills for Continual Adaptation
por: Tang, Pingzhi, et al.
Publicado: (2026)

VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learning
por: Lu, Guanxing, et al.
Publicado: (2025)

On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting
por: Zhang, Wenhao, et al.
Publicado: (2025)

RL Tango: Reinforcing Generator and Verifier Together for Language Reasoning
por: Zha, Kaiwen, et al.
Publicado: (2025)

Embed-RL: Reinforcement Learning for Reasoning-Driven Multimodal Embeddings
por: Jiang, Haonan, et al.
Publicado: (2026)

Deep RL Needs Deep Behavior Analysis: Exploring Implicit Planning by Model-Free Agents in Open-Ended Environments
por: Simmons-Edler, Riley, et al.
Publicado: (2025)

Model-Based RL for Mean-Field Games is not Statistically Harder than Single-Agent RL
por: Huang, Jiawei, et al.
Publicado: (2024)

Open-Det: An Efficient Learning Framework for Open-Ended Detection
por: Cao, Guiping, et al.
Publicado: (2025)

Central Limit Theorem for Two-Time-Scale Approximate Distributionally Robust RL
por: Wang, Shengbo, et al.
Publicado: (2026)

Vero: An Open RL Recipe for General Visual Reasoning
por: Sarch, Gabriel, et al.
Publicado: (2026)

An Empirical Study on the Effectiveness of Incorporating Offline RL As Online RL Subroutines
por: Su, Jianhai, et al.
Publicado: (2025)

Dynamic Vocabulary Pruning: Stable LLM-RL by Taming the Tail
por: Li, Yingru, et al.
Publicado: (2025)

Autobidding Arena: unified evaluation of the classical and RL-based autobidding algorithms
por: Pudovikov, Andrey, et al.
Publicado: (2025)

SCOPE-RL: Stable and Quantitative Control of Policy Entropy in RL Post-Training
por: Wang, Chen, et al.
Publicado: (2025)

Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL
por: Wang, Sudong, et al.
Publicado: (2026)

Fact-R1: Towards Explainable Video Misinformation Detection with Deep Reasoning
por: Zhang, Fanrui, et al.
Publicado: (2025)

Miner:Mining Intrinsic Mastery for Data-Efficient RL in Large Reasoning Models
por: Jiang, Shuyang, et al.
Publicado: (2026)

MIST-RL: Mutation-based Incremental Suite Testing via Reinforcement Learning
por: Zhu, Sicheng, et al.
Publicado: (2026)