Imagen de Portada

Aligning Agents via Planning: A Benchmark for Trajectory-Level Reward Modeling

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wang, Jiaxuan, Hu, Yulan, Yang, Wenjin, Pan, Zheng, Li, Xin, Guo, Lan-Zhe
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

TRACE: Distilling Where It Matters via Token-Routed Self On-Policy Alignment
por: Wang, Jiaxuan, et al.
Publicado: (2026)

Multi-Stakeholder LLM Alignment: Decomposing Estimation from Aggregation
por: Zheng, Lulu, et al.
Publicado: (2026)

Beyond Itinerary Planning-A Real-World Benchmark for Multi-Turn and Tool-Using Travel Tasks
por: Cheng, Xiang, et al.
Publicado: (2025)

Aligning Crowd Feedback via Distributional Preference Reward Modeling
por: Li, Dexun, et al.
Publicado: (2024)

VoiceAgentEval: A Dual-Dimensional Benchmark for Expert-Level Intelligent Voice-Agent Evaluation of Xbench's Professional-Aligned Series
por: Xu, Pengyu, et al.
Publicado: (2025)

Aligning Progress and Feasibility: A Neuro-Symbolic Dual Memory Framework for Long-Horizon LLM Agents
por: Wen, Bin, et al.
Publicado: (2026)

Real-Time Aligned Reward Model beyond Semantics
por: Huang, Zixuan, et al.
Publicado: (2026)

Coarse-to-Fine Process Reward Modeling for Mathematical Reasoning
por: Hu, Yulan, et al.
Publicado: (2025)

Scaling Autonomous Agents via Automatic Reward Modeling And Planning
por: Chen, Zhenfang, et al.
Publicado: (2025)

Redundant or Necessary? A Benchmark for Detecting Redundant Steps in Agent Trajectories
por: Hu, Minyang, et al.
Publicado: (2026)

NeSy-Route: A Neuro-Symbolic Benchmark for Constrained Route Planning in Remote Sensing
por: Yang, Ming, et al.
Publicado: (2026)

RRO: LLM Agent Optimization Through Rising Reward Trajectories
por: Wang, Zilong, et al.
Publicado: (2025)

A Framework for Benchmarking and Aligning Task-Planning Safety in LLM-Based Embodied Agents
por: Huang, Yuting, et al.
Publicado: (2025)

Agent-RewardBench: Towards a Unified Benchmark for Reward Modeling across Perception, Planning, and Safety in Real-World Multimodal Agents
por: Men, Tianyi, et al.
Publicado: (2025)

GUNDAM: Aligning Large Language Models with Graph Understanding
por: Ouyang, Sheng, et al.
Publicado: (2024)

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

TROJail: Trajectory-Level Optimization for Multi-Turn Large Language Model Jailbreaks with Process Rewards
por: Xiong, Xiqiao, et al.
Publicado: (2025)

Reward Bound for Behavioral Guarantee of Model-based Planning Agents
por: An, Zhiyu, et al.
Publicado: (2024)

AMAP Agentic Planning Technical Report
por: AMAP AI Agent Team, et al.
Publicado: (2025)

Towards Comprehensive Preference Data Collection for Reward Modeling
por: Hu, Yulan, et al.
Publicado: (2024)

TreeEval: Benchmark-Free Evaluation of Large Language Models through Tree Planning
por: Li, Xiang, et al.
Publicado: (2024)

ChinaTravel: An Open-Ended Travel Planning Benchmark with Compositional Constraint Validation for Language Agents
por: Shao, Jie-Jing, et al.
Publicado: (2024)

StructVRM: Aligning Multimodal Reasoning with Structured and Verifiable Reward Models
por: Zhang, Xiangxiang, et al.
Publicado: (2025)

ATBench: A Diverse and Realistic Agent Trajectory Benchmark for Safety Evaluation and Diagnosis
por: Li, Yu, et al.
Publicado: (2026)

Intra-Trajectory Consistency for Reward Modeling
por: Zhou, Chaoyang, et al.
Publicado: (2025)

MTRec: Learning to Align with User Preferences via Mental Reward Models
por: Zhao, Mengchen, et al.
Publicado: (2025)

AlignCoder: Aligning Retrieval with Target Intent for Repository-Level Code Completion
por: Jiang, Tianyue, et al.
Publicado: (2026)

GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents
por: Wu, Xiongbin, et al.
Publicado: (2026)

ALaRM: Align Language Models via Hierarchical Rewards Modeling
por: Lai, Yuhang, et al.
Publicado: (2024)

Reinforced Imitative Trajectory Planning for Urban Automated Driving
por: Zeng, Di, et al.
Publicado: (2024)

AlignDiff: Aligning Diverse Human Preferences via Behavior-Customisable Diffusion Model
por: Dong, Zibin, et al.
Publicado: (2023)

Aligning Vision Models with Human Aesthetics in Retrieval: Benchmarks and Algorithms
por: Zhang, Miaosen, et al.
Publicado: (2024)

RED: Unleashing Token-Level Rewards from Holistic Feedback via Reward Redistribution
por: Li, Jiahui, et al.
Publicado: (2024)

Beyond Trajectory Rewards: Step-level Credit Assignment for Agentic Search via Graph Modeling
por: Liu, Yuchen, et al.
Publicado: (2026)

WebUncertainty: Dual-Level Uncertainty Driven Planning and Reasoning For Autonomous Web Agent
por: Zhang, Lingfeng, et al.
Publicado: (2026)

StoryAlign: Evaluating and Training Reward Models for Story Generation
por: Xia, Haotian, et al.
Publicado: (2026)

nuPlan-R: A Closed-Loop Planning Benchmark for Autonomous Driving via Reactive Multi-Agent Simulation
por: Peng, Mingxing, et al.
Publicado: (2025)

GTPO and GRPO-S: Token and Sequence-Level Reward Shaping with Policy Entropy
por: Tan, Hongze, et al.
Publicado: (2025)

Structurally Aligned Subtask-Level Memory for Software Engineering Agents
por: Shen, Kangning, et al.
Publicado: (2026)

EVA: Aligning Video World Models with Executable Robot Actions via Inverse Dynamics Rewards
por: Wang, Ruixiang, et al.
Publicado: (2026)