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

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Xin, Ran, Zheng, Zeyu, Nie, Yanchen, Yuan, Kun, Xiao, Xia
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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