Imagen de Portada

Scaling up Multi-Turn Off-Policy RL and Multi-Agent Tree Search for LLM Step-Provers

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Xin, Ran, Zheng, Zeyu, Nie, Yanchen, Yuan, Kun, Xiao, Xia
Formato:	Preprint
Publicado:	2025
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

BFS-Prover: Scalable Best-First Tree Search for LLM-based Automatic Theorem Proving
por: Xin, Ran, et al.
Publicado: (2025)

TSR: Trajectory-Search Rollouts for Multi-Turn RL of LLM Agents
por: Djuhera, Aladin, et al.
Publicado: (2026)

OptProver: Bridging Olympiad and Optimization through Continual Training in Formal Theorem Proving
por: Li, Chenyi, et al.
Publicado: (2026)

ProRL Agent: Rollout-as-a-Service for RL Training of Multi-Turn LLM Agents
por: Zhang, Hao, et al.
Publicado: (2026)

AgentRL: Scaling Agentic Reinforcement Learning with a Multi-Turn, Multi-Task Framework
por: Zhang, Hanchen, et al.
Publicado: (2025)

When Does Multi-Agent RL Improve LLM Workflows? Workflow, Scale, and Policy-Sharing Tradeoffs
por: Zeng, Yifan, et al.
Publicado: (2026)

SkyRL-Agent: Efficient RL Training for Multi-turn LLM Agent
por: Cao, Shiyi, et al.
Publicado: (2025)

Information Gain-based Policy Optimization: A Simple and Effective Approach for Multi-Turn Search Agents
por: Wang, Guoqing, et al.
Publicado: (2025)

Evaluating Multi-Turn Bargain Skills in LLM-Based Seller Agent
por: Wang, Issue Yishu, et al.
Publicado: (2025)

InternLM2.5-StepProver: Advancing Automated Theorem Proving via Critic-Guided Search
por: Wu, Zijian, et al.
Publicado: (2024)

StepFun-Prover Preview: Let's Think and Verify Step by Step
por: Shang, Shijie, et al.
Publicado: (2025)

Leanabell-Prover: Posttraining Scaling in Formal Reasoning
por: Zhang, Jingyuan, et al.
Publicado: (2025)

SLEA-RL: Step-Level Experience Augmented Reinforcement Learning for Multi-Turn Agentic Training
por: Wang, Prince Zizhuang, et al.
Publicado: (2026)

PAG: Multi-Turn Reinforced LLM Self-Correction with Policy as Generative Verifier
por: Jiang, Yuhua, et al.
Publicado: (2025)

AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning
por: Xi, Zhiheng, et al.
Publicado: (2025)

MPS-Prover: Advancing Stepwise Theorem Proving by Multi-Perspective Search and Data Curation
por: Liang, Zhenwen, et al.
Publicado: (2025)

EvoEmo: Towards Evolved Emotional Policies for Adversarial LLM Agents in Multi-Turn Price Negotiation
por: Long, Yunbo, et al.
Publicado: (2025)

Adaptive Layerwise Perturbation: Unifying Off-Policy Corrections for LLM RL
por: Ye, Chenlu, et al.
Publicado: (2026)

ATPO: Adaptive Tree Policy Optimization for Multi-Turn Medical Dialogue
por: Cao, Ruike, et al.
Publicado: (2026)

General Modular Harness for LLM Agents in Multi-Turn Gaming Environments
por: Zhang, Yuxuan, et al.
Publicado: (2025)

Towards Trustworthy Multi-Turn LLM Agents via Behavioral Guidance
por: Gürsun, Gonca
Publicado: (2025)

Soft Policy Optimization: Online Off-Policy RL for Sequence Models
por: Cohen, Taco, et al.
Publicado: (2025)

Beyond the Strongest LLM: Multi-Turn Multi-Agent Orchestration vs. Single LLMs on Benchmarks
por: Tian, Aaron Xuxiang, et al.
Publicado: (2025)

Consolidation via Policy Information Regularization in Deep RL for Multi-Agent Games
por: Malloy, Tailia, et al.
Publicado: (2020)

CM2: Reinforcement Learning with Checklist Rewards for Multi-Turn and Multi-Step Agentic Tool Use
por: Zhang, Zhen, et al.
Publicado: (2026)

Stabilizing Off-Policy Training for Long-Horizon LLM Agent via Turn-Level Importance Sampling and Clipping-Triggered Normalization
por: Li, Chenliang, et al.
Publicado: (2025)

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

Mitigating Conversational Inertia in Multi-Turn Agents
por: Wan, Yang, et al.
Publicado: (2026)

ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL
por: Zhou, Yifei, et al.
Publicado: (2024)

ZipRL: Adaptive Multi-Turn Context Compression with Hindsight Response Replay
por: Hu, Zhexin, et al.
Publicado: (2026)

Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions
por: Hu, Yuanzhe, et al.
Publicado: (2025)

Evaluating LLM-based Agents for Multi-Turn Conversations: A Survey
por: Guan, Shengyue, et al.
Publicado: (2025)

OOM-RL: Out-of-Money Reinforcement Learning Market-Driven Alignment for LLM-Based Multi-Agent Systems
por: Liu, Kun, et al.
Publicado: (2026)

Offline Policy Evaluation of Multi-Turn LLM Health Coaching with Real Users
por: Ozolcer, Melik, et al.
Publicado: (2025)

Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RL
por: Gao, Jiaxuan, et al.
Publicado: (2025)

Proximity-Based Multi-Turn Optimization: Practical Credit Assignment for LLM Agent Training
por: Fang, Yangyi, et al.
Publicado: (2026)

Off-Policy Correction For Multi-Agent Reinforcement Learning
por: Zawalski, Michał, et al.
Publicado: (2021)

LLM Collaboration With Multi-Agent Reinforcement Learning
por: Liu, Shuo, et al.
Publicado: (2025)

Incentive-Aligned Multi-Source LLM Summaries
por: Jiang, Yanchen, et al.
Publicado: (2025)

Data-to-Dashboard: Multi-Agent LLM Framework for Insightful Visualization in Enterprise Analytics
por: Zhang, Ran, et al.
Publicado: (2025)