Imagen de Portada

AGPO: Asymmetric Group Policy Optimization for Verifiable Reasoning and Search Ads Relevance at JD

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Xu, Yang, Yao, Kun, Deng, Yiming, Fang, Zheng, Ting, Kai Ming, Pang, Ming
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

AGPO: Adaptive Group Policy Optimization with Dual Statistical Feedback
por: Hu, Miaobo, et al.
Publicado: (2026)

LiveBrowseComp: Are Search Agents Searching, or Just Verifying What They Already Know?
por: Fan, HuiMing, et al.
Publicado: (2026)

GRPO-VPS: Enhancing Group Relative Policy Optimization with Verifiable Process Supervision for Effective Reasoning
por: Wang, Jingyi, et al.
Publicado: (2026)

DRPO: Efficient Reasoning via Decoupled Reward Policy Optimization
por: Li, Gang, et al.
Publicado: (2025)

ADORE: Autonomous Domain-Oriented Relevance Engine for E-commerce
por: Fang, Zheng, et al.
Publicado: (2025)

NP-Engine: Empowering Optimization Reasoning in Large Language Models with Verifiable Synthetic NP Problems
por: Li, Xiaozhe, et al.
Publicado: (2025)

SHE: Stepwise Hybrid Examination Reinforcement Learning Framework for E-commerce Search Relevance
por: Jiao, Pengkun, et al.
Publicado: (2025)

EvolVE: Evolutionary Search for LLM-based Verilog Generation and Optimization
por: Hsin, Wei-Po, et al.
Publicado: (2026)

TSPO: Breaking the Double Homogenization Dilemma in Multi-turn Search Policy Optimization
por: Ma, Shichao, et al.
Publicado: (2026)

TaoSR1: The Thinking Model for E-commerce Relevance Search
por: Dong, Chenhe, et al.
Publicado: (2025)

Group Sequence Policy Optimization
por: Zheng, Chujie, et al.
Publicado: (2025)

Async Learned User Embeddings for Ads Delivery Optimization
por: Tang, Mingwei, et al.
Publicado: (2024)

InfEngine: A Self-Verifying and Self-Optimizing Intelligent Engine for Infrared Radiation Computing
por: Ding, Kun, et al.
Publicado: (2026)

Fuse, Reason and Verify: Geometry Problem Solving with Parsed Clauses from Diagram
por: Zhang, Ming-Liang, et al.
Publicado: (2024)

PhySe-RPO: Physics and Semantics Guided Relative Policy Optimization for Diffusion-Based Surgical Smoke Removal
por: Fang, Zining, et al.
Publicado: (2026)

Optimizing Generative Ranking Relevance via Reinforcement Learning in Xiaohongshu Search
por: Zeng, Ziyang, et al.
Publicado: (2025)

Historically Relevant Event Structuring for Temporal Knowledge Graph Reasoning
por: Zhang, Jinchuan, et al.
Publicado: (2024)

CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models
por: Lin, Zhihang, et al.
Publicado: (2025)

Enhancing Mathematical Reasoning in Large Language Models with Self-Consistency-Based Hallucination Detection
por: Liu, MingShan, et al.
Publicado: (2025)

Sonar-TS: Search-Then-Verify Natural Language Querying for Time Series Databases
por: Tan, Zhao, et al.
Publicado: (2026)

Policy Guided Tree Search for Enhanced LLM Reasoning
por: Li, Yang
Publicado: (2025)

Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing
por: Li, Gengsheng, et al.
Publicado: (2026)

Distribution-Based Feature Attribution for Explaining the Predictions of Any Classifier
por: Li, Xinpeng, et al.
Publicado: (2025)

Enhancing LLM-based Search Agents via Contribution Weighted Group Relative Policy Optimization
por: Wang, Junzhe, et al.
Publicado: (2026)

Inverse Knowledge Search over Verifiable Reasoning: Synthesizing a Scientific Encyclopedia from a Long Chains-of-Thought Knowledge Base
por: Li, Yu, et al.
Publicado: (2025)

Random Policy Valuation is Enough for LLM Reasoning with Verifiable Rewards
por: He, Haoran, et al.
Publicado: (2025)

G$^2$RPO-A: Guided Group Relative Policy Optimization with Adaptive Guidance
por: Guo, Yongxin, et al.
Publicado: (2025)

TaoSR-AGRL: Adaptive Guided Reinforcement Learning Framework for E-commerce Search Relevance
por: Yang, Jianhui, et al.
Publicado: (2025)

APO: Enhancing Reasoning Ability of MLLMs via Asymmetric Policy Optimization
por: Hong, Minjie, et al.
Publicado: (2025)

Optimizing Anytime Reasoning via Budget Relative Policy Optimization
por: Qi, Penghui, et al.
Publicado: (2025)

Verifiable Process Rewards for Agentic Reasoning
por: Yuan, Huining, et al.
Publicado: (2026)

Grounding Multi-Hop Reasoning in Structural Causal Models via Group Relative Policy Optimization
por: Bu, Yunhan, et al.
Publicado: (2026)

VeRA: Verified Reasoning Data Augmentation at Scale
por: Cheng, Zerui, et al.
Publicado: (2026)

GEPO: Group Expectation Policy Optimization for Stable Heterogeneous Reinforcement Learning
por: Zhang, Han, et al.
Publicado: (2025)

An Efficient Rubric-based Generative Verifier for Search-Augmented LLMs
por: Ma, Linyue, et al.
Publicado: (2025)

Breaking $\textit{Winner-Takes-All}$: Cooperative Policy Optimization Improves Diverse LLM Reasoning
por: Chen, Haoxuan, et al.
Publicado: (2026)

Group Orthogonalized Policy Optimization:Group Policy Optimization as Orthogonal Projection in Hilbert Space
por: Zixian, Wang
Publicado: (2026)

Asymmetric Proximal Policy Optimization: mini-critics boost LLM reasoning
por: Liu, Jiashun, et al.
Publicado: (2025)

Perceptual Group Tokenizer: Building Perception with Iterative Grouping
por: Deng, Zhiwei, et al.
Publicado: (2023)

Searching Meta Reasoning Skeleton to Guide LLM Reasoning
por: Zhang, Ziying, et al.
Publicado: (2025)