Cover Image

When LLM Reward Design Fails: Diagnostic-Driven Refinement for Sparse Structured RL

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Youting, Tang, Yuan, Liu, Bowen, Liu, Xuan, Shang, Dingyan
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence Information Retrieval
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Not All Queries Need Rewriting: When Prompt-Only LLM Refinement Helps and Hurts Dense Retrieval
by: Kotte, Varun
Published: (2026)

ProSpec RL: Plan Ahead, then Execute
by: Liu, Liangliang, et al.
Published: (2024)

MemoryBench: A Benchmark for Memory and Continual Learning in LLM Systems
by: Ai, Qingyao, et al.
Published: (2025)

RL-MPCA: A Reinforcement Learning Based Multi-Phase Computation Allocation Approach for Recommender Systems
by: Zhou, Jiahong, et al.
Published: (2023)

RRCM: Ranking-Driven Retrieval over Collaborative and Meta Memories for LLM Recommendation
by: Li, Shijun, et al.
Published: (2026)

LINK-KG: LLM-Driven Coreference-Resolved Knowledge Graphs for Human Smuggling Networks
by: Meher, Dipak, et al.
Published: (2025)

Trust by Design: Skill Profiles for Transparent, Cost-Aware LLM Routing
by: Okamoto, Mika, et al.
Published: (2026)

Streamlining Conformal Information Retrieval via Score Refinement
by: Intrator, Yotam, et al.
Published: (2024)

Refined Edge Usage of Graph Neural Networks for Edge Prediction
by: Jin, Jiarui, et al.
Published: (2022)

Learning Retrieval Models with Sparse Autoencoders
by: Formal, Thibault, et al.
Published: (2026)

Learning Time Slot Preferences via Mobility Tree for Next POI Recommendation
by: Huang, Tianhao, et al.
Published: (2024)

Preference Discerning with LLM-Enhanced Generative Retrieval
by: Paischer, Fabian, et al.
Published: (2024)

CuriousLLM: Elevating Multi-Document Question Answering with LLM-Enhanced Knowledge Graph Reasoning
by: Yang, Zukang, et al.
Published: (2024)

Bridging Stepwise Lab-Informed Pretraining and Knowledge-Guided Learning for Diagnostic Reasoning
by: Hu, Pengfei, et al.
Published: (2024)

Sparse Autoencoders for Sequential Recommendation Models: Interpretation and Flexible Control
by: Klenitskiy, Anton, et al.
Published: (2025)

Refine-POI: Reinforcement Fine-Tuned Large Language Models for Next Point-of-Interest Recommendation
by: Li, Peibo, et al.
Published: (2025)

TOBUGraph: Knowledge Graph-Based Retrieval for Enhanced LLM Performance Beyond RAG
by: Kashmira, Savini, et al.
Published: (2024)

BGM-HAN: A Hierarchical Attention Network for Accurate and Fair Decision Assessment on Semi-Structured Profiles
by: Liu, Junhua, et al.
Published: (2025)

When Search Engine Services meet Large Language Models: Visions and Challenges
by: Xiong, Haoyi, et al.
Published: (2024)

Enhancing Talent Search Ranking with Role-Aware Expert Mixtures and LLM-based Fine-Grained Job Descriptions
by: Li, Jihang, et al.
Published: (2025)

CSRv2: Unlocking Ultra-Sparse Embeddings
by: Guo, Lixuan, et al.
Published: (2026)

No More K-means: Single-Stage Sparse Coding for Efficient Multi-Vector Retrieval
by: Guo, Lixuan, et al.
Published: (2026)

Modeling User Exploration Saturation: When Recommender Systems Should Stop Pushing Novelty
by: Ayiku, Enock O., et al.
Published: (2026)

Mixture of Structural-and-Textual Retrieval over Text-rich Graph Knowledge Bases
by: Lei, Yongjia, et al.
Published: (2025)

Dynamic Sparse Causal-Attention Temporal Networks for Interpretable Causality Discovery in Multivariate Time Series
by: Zerkouk, Meriem, et al.
Published: (2025)

LiDDA: Data Driven Attribution at LinkedIn
by: Bencina, John, et al.
Published: (2025)

LARGER: Lexically Anchored Repository Graph Exploration and Retrieval
by: Hu, Yuntong, et al.
Published: (2026)

Hierarchical LoRA MoE for Efficient CTR Model Scaling
by: Zeng, Zhichen, et al.
Published: (2025)

Pseudo Label NCF for Sparse OHC Recommendation: Dual Representation Learning and the Separability Accuracy Trade off
by: Barman, Pronob Kumar, et al.
Published: (2026)

Generating Query-Relevant Document Summaries via Reinforcement Learning
by: Yadav, Nitin, et al.
Published: (2025)

DiffGRM: Diffusion-based Generative Recommendation Model
by: Liu, Zhao, et al.
Published: (2025)

Sequential LLM Framework for Fashion Recommendation
by: Liu, Han, et al.
Published: (2024)

LLM-assisted Vector Similarity Search
by: Riyadh, Md, et al.
Published: (2024)

BRIDGE: Bundle Recommendation via Instruction-Driven Generation
by: Bui, Tuan-Nghia, et al.
Published: (2024)

Multi-Modality Collaborative Learning for Sentiment Analysis
by: Wang, Shanmin, et al.
Published: (2025)

R1-Ranker: Teaching LLM Rankers to Reason
by: Feng, Tao, et al.
Published: (2025)

Aligning Dense Retrievers with LLM Utility via Distillation
by: Sandhu, Rajinder, et al.
Published: (2026)

STRUM-LLM: Attributed and Structured Contrastive Summarization
by: Gunel, Beliz, et al.
Published: (2024)

Rank and Align: Towards Effective Source-free Graph Domain Adaptation
by: Luo, Junyu, et al.
Published: (2024)

Evaluating Podcast Recommendations with Profile-Aware LLM-as-a-Judge
by: Fabbri, Francesco, et al.
Published: (2025)