DS
Daiting Shi
cs.IRcs.CLcs.AIcs.LG
On Valency
published · living versionsW_z79fk6fr·v1 · currentpublished
MemBubble: Benchmarking How Agent Memory Shapes LLM Response Diversity
with Jiajun Tan, Fei Sun, Xinyu Ma, Shixuan Zhang +4
1 version
Preprints & journals
22 papers in the corpus · 2021–2026MemBubble: Benchmarking How Agent Memory Shapes LLM Response Diversity2610.25127v1 · Jiajun Tan, Fei Sun, Xinyu Ma et al.2026 · 0 citationsarXivon Valency
Experimental Experience Modeling for Autonomous Research2609.39392v1 · Wenda Wei, Yingchen Zhang, Ruqing Zhang et al.2026 · 0 citationsarXiv
From Ranked Documents to Reliable Contexts: An Answer-Oriented Context Construct Framework for AI Search2609.23354v3 · Yunfei Zhong, Yinqiong Cai, Lixin Su et al.2026 · 0 citationsarXiv
FDR: A Fine-Grained Full-Pipeline Reward Framework for DeepSearch Workflows2609.19827v2 · Bojian Xiong, Wentao Ding, Yujing Lu et al.2026 · 0 citationsarXiv
Token-Level Credit Assignment Optimization for Generative Document Retrieval2608.12049v2 · Xinpeng Zhao, Yang Liu, Ran Chen et al.2026 · 0 citationsarXiv
Querit-Reranker: Training Compact Multilingual Rerankers via Efficient Label-Free Distribution Adaptation2606.19037v3 · Yunfei Zhong, Jun Yang, Wei Huang et al.2026 · 0 citationsarXiv
Beyond Imitation: Reflective On-Policy Self-Distillation for LLM Reasoning2605.28014v2 · Ziqi Zhao, Xinyu Ma, Liu Yang et al.2026 · 0 citationsarXiv
Large Language Model-Powered Query-Driven Event Timeline Summarization in Industrial Search2605.27066v1 · Mingyue Wang, Xingyu Xie, Hang Yang et al.2026 · 0 citationsarXiv
RAG-Enhanced Large Language Models for Dynamic Content Expiration Prediction in Web Search2605.13052v1 · Tingyu Chen, Wenkai Zhang, Li Gao et al.2026 · 0 citationsarXiv
ConsistRM: Improving Generative Reward Models via Consistency-Aware Self-Training2604.07484v2 · Yu Liang, Liangxin Liu, Longzheng Wang et al.2026 · 0 citationsarXiv
ReflectRM: Boosting Generative Reward Models via Self-Reflection within a Unified Judgment Framework2604.07506v2 · Kai Qin, Liangxin Liu, Yu Liang et al.2026 · 0 citationsarXiv
UniCreative: Unifying Long-form Logic and Short-form Sparkle via Reference-Free Reinforcement Learning2604.05517v1 · Xiaolong Wei, Zerun Zhu, Simin Niu et al.2026 · 0 citationsarXiv
Reconstructing Content with Collaborative Attention for Universal Multimodal Representation Learning2603.01471v3 · Jiahan Chen, Da Li, Hengran Zhang et al.2026 · 0 citationsarXiv
Bagging-Based Model Merging for Robust General Text Embeddings2602.05787v2 · Hengran Zhang, Keping Bi, Jiafeng Guo et al.2026 · 0 citationsarXiv
Agentic-R: Learning to Retrieve for Agentic Search2601.11888v1 · Wenhan Liu, Xinyu Ma, Yutao Zhu et al.2026 · 1 citationarXiv
Reinforced Efficient Reasoning via Semantically Diverse Exploration2601.05053v2 · Ziqi Zhao, Zhaochun Ren, Jiahong Zou et al.2026 · 0 citationsarXiv
Utility-Focused LLM Annotation for Retrieval and Retrieval-Augmented Generation2504.05220v5 · Hengran Zhang, Minghao Tang, Keping Bi et al.2025 · 5 citationsarXiv
GenCRF: Generative Clustering and Reformulation Framework for Enhanced Intent-Driven Information Retrieval2409.10909v1 · Wonduk Seo, Haojie Zhang, Yueyang Zhang et al.2024 · 0 citationsarXiv
TourRank: Utilizing Large Language Models for Documents Ranking with a Tournament-Inspired Strategy2406.11678v2 · Yiqun Chen, Qi Liu, Yi Zhang et al.2024 · 15 citationsarXiv
MA4DIV: Multi-Agent Reinforcement Learning for Search Result Diversification2403.17421v3 · Yiqun Chen, Jiaxin Mao, Yi Zhang et al.2024 · 5 citationsarXiv
Pre-trained Language Model for Web-scale Retrieval in Baidu Search2106.03373v4 · Yiding Liu, Guan Huang, Jiaxiang Liu et al.2021 · 56 citationsarXiv
Pre-trained Language Model based Ranking in Baidu Search2105.11108v3 · Lixin Zou, Shengqiang Zhang, Hengyi Cai et al.2021 · 57 citationsarXiv
Career total: 36 works. 22 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.