Imagen de Portada

SPPO: Sequence-Level PPO for Long-Horizon Reasoning Tasks

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wang, Tianyi, Li, Yixia, Li, Long, Chen, Yibiao, Huang, Shaohan, Chen, Yun, Li, Peng, Liu, Yang, Chen, Guanhua
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Anchored Policy Optimization: Mitigating Exploration Collapse Via Support-Constrained Rectification
por: Wang, Tianyi, et al.
Publicado: (2026)

SeTAR: Out-of-Distribution Detection with Selective Low-Rank Approximation
por: Li, Yixia, et al.
Publicado: (2024)

Recurrent Reasoning with Vision-Language Models for Estimating Long-Horizon Embodied Task Progress
por: Zhang, Yuelin, et al.
Publicado: (2026)

Segmental Advantage Estimation: Enhancing PPO for Long-Context LLM Training
por: Gong, Xue, et al.
Publicado: (2026)

When to Re-Commit: Temporal Abstraction Discovery for Long-Horizon Vision-Language Reasoning
por: Li, Chen, et al.
Publicado: (2026)

Heterogeneous Multi-Expert Reinforcement Learning for Long-Horizon Multi-Goal Tasks in Autonomous Forklifts
por: Chen, Yun, et al.
Publicado: (2026)

AgentFugue: Agent Scaling for Long-Horizon Tasks through Collective Reasoning
por: Hu, Yuyang, et al.
Publicado: (2026)

GUI-Shepherd: Reliable Process Reward and Verification for Long-Sequence GUI Tasks
por: Chen, Cong, et al.
Publicado: (2025)

Learning Agent-Compatible Context Management for Long-Horizon Tasks
por: Yi, Lu, et al.
Publicado: (2026)

ClothPPO: A Proximal Policy Optimization Enhancing Framework for Robotic Cloth Manipulation with Observation-Aligned Action Spaces
por: Yang, Libing, et al.
Publicado: (2024)

RLVMR: Reinforcement Learning with Verifiable Meta-Reasoning Rewards for Robust Long-Horizon Agents
por: Zhang, Zijing, et al.
Publicado: (2025)

Co-Evolving LLM Decision and Skill Bank Agents for Long-Horizon Tasks
por: Wu, Xiyang, et al.
Publicado: (2026)

No More Stale Feedback: Co-Evolving Critics for Open-World Agent Learning
por: Li, Zhicong, et al.
Publicado: (2026)

STRUCTUREDAGENT: Planning with AND/OR Trees for Long-Horizon Web Tasks
por: Lobo, ELita, et al.
Publicado: (2026)

SAG-Agent: Enabling Long-Horizon Reasoning in Strategy Games via Dynamic Knowledge Graphs
por: Tang, Chenwei, et al.
Publicado: (2025)

SeeUPO: Sequence-Level Agentic-RL with Convergence Guarantees
por: Hu, Tianyi, et al.
Publicado: (2026)

VisCodex: Unified Multimodal Code Generation via Merging Vision and Coding Models
por: Jiang, Lingjie, et al.
Publicado: (2025)

Rethinking the Role of Entropy in Optimizing Tool-Use Behaviors for Large Language Model Agents
por: Li, Zeping, et al.
Publicado: (2026)

RoboClaw: An Agentic Framework for Scalable Long-Horizon Robotic Tasks
por: Li, Ruiying, et al.
Publicado: (2026)

GTA: Generating Long-Horizon Tasks for Web Agents at Scale
por: Huang, Tenghao, et al.
Publicado: (2026)

MemOCR: Layout-Aware Visual Memory for Efficient Long-Horizon Reasoning
por: Shi, Yaorui, et al.
Publicado: (2026)

Optimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-Horizon Tasks
por: Li, Zaijing, et al.
Publicado: (2024)

DETACH: Cross-domain Learning for Long-Horizon Tasks via Mixture of Disentangled Experts
por: Shen, Yutong, et al.
Publicado: (2025)

Towards Fair and Comprehensive Evaluation of Routers in Collaborative LLM Systems
por: Wu, Wanxing, et al.
Publicado: (2026)

Thinking in Text and Images: Interleaved Vision--Language Reasoning Traces for Long-Horizon Robot Manipulation
por: Liu, Jinkun, et al.
Publicado: (2026)

LifeBench: A Benchmark for Long-Horizon Multi-Source Memory
por: Cheng, Zihao, et al.
Publicado: (2026)

From Abstract to Contextual: What LLMs Still Cannot Do in Mathematics
por: Cao, Bowen, et al.
Publicado: (2026)

ELHPlan: Efficient Long-Horizon Task Planning for Multi-Agent Collaboration
por: Ling, Shaobin, et al.
Publicado: (2025)

SkillTree: Explainable Skill-Based Deep Reinforcement Learning for Long-Horizon Control Tasks
por: Wen, Yongyan, et al.
Publicado: (2024)

NaturalGAIA: A Verifiable Benchmark and Hierarchical Framework for Long-Horizon GUI Tasks
por: Zheng, Zihan, et al.
Publicado: (2025)

Beyond Entangled Planning: Task-Decoupled Planning for Long-Horizon Agents
por: Li, Yunfan, et al.
Publicado: (2026)

Enhancing Large Language Model Reasoning via Selective Critical Token Fine-Tuning
por: Ruan, Zhiwen, et al.
Publicado: (2025)

Non-Markovian Long-Horizon Robot Manipulation via Keyframe Chaining
por: Chen, Yipeng, et al.
Publicado: (2026)

SKETCH: Semantic Key-Point Conditioning for Long-Horizon Vessel Trajectory Prediction
por: Gan, Linyong, et al.
Publicado: (2026)

Self-Rewarding PPO: Aligning Large Language Models with Demonstrations Only
por: Zhang, Qingru, et al.
Publicado: (2025)

Can LLM Agents Be CFOs? Benchmarking Long-Horizon Resource Allocation in an Uncertain Enterprise Environment
por: Han, Yi, et al.
Publicado: (2026)

Interaction as Intelligence Part II: Asynchronous Human-Agent Rollout for Long-Horizon Task Training
por: Fu, Dayuan, et al.
Publicado: (2025)

Distract Large Language Models for Automatic Jailbreak Attack
por: Xiao, Zeguan, et al.
Publicado: (2024)

LongSeeker: Elastic Context Orchestration for Long-Horizon Search Agents
por: Lu, Yijun, et al.
Publicado: (2026)

TOPPO: Rethinking PPO for Multi-Task Reinforcement Learning with Critic Balancing
por: Li, Yuanpeng, et al.
Publicado: (2026)