ZD
Zhongxiang Dai
cs.LGcs.AIcs.CLstat.MLcs.CRGraph theoryConnectomecs.CYcs.MAFunctional connectivity
On Valency
published · living versionsW_jkukqffk·v2 · currentpublished
Bridging Exploration and Persona: Information-Directed Dueling for Test-Time Agent Personalization
with Jie Mao, Pingchen Lu, Xiangyi Wang, Hengquan Huang +2
2 versions
W_8hhbrqwy·v1published
Preprints & journals
65 papers in the corpus · 2016–2026IF-MAP: Influence-Function-Inspired Agent Prioritization in Multi-Agent Systems2610.24383v1 · Jie Mao, Pingchen Lu, Zikun Qu et al.2026 · 0 citationsarXivon Valency
Bridging Exploration and Persona: Information-Directed Dueling for Test-Time Agent Personalization2610.24385v2 · Jie Mao, Pingchen Lu, Xiangyi Wang et al.2026 · 0 citationsarXivon Valency
MARS: Memory-Aware Routing for Session-Level LLM Assistants2610.23583v1 · Minghan Wang, Jinhang Zuo, Zhongxiang Dai et al.2026 · 0 citationsarXiv
Provably Efficient Risk-Sensitive Offline Reinforcement Learning via Optimized Certainty Equivalents2610.21870v1 · Hanzhen Wang, Boxiang Lyu, Zhongxiang Dai et al.2026 · 0 citationsarXiv
CB-Orchestrator: Adaptive Workflow Optimization for LLM Agents via Contextual Bandits2610.13064v1 · Jiahang Sun, Zhiwei Shang, Zhipiao Liu et al.2026 · 0 citationsarXiv
Fusion is the New Mutation: Bandit-Guided Evolution on Workflow Graphs2610.05284v1 · Zhiwei Shang, Jiahang Sun, Mingrong Gong et al.2026 · 0 citationsarXiv
MESH-Harness: Self-Improving Agent Harnesses via Bandit-Guided Compositional Evolution2610.05300v1 · Zhiwei Shang, Yu Huo, Mingrong Gong et al.2026 · 0 citationsarXiv
From Preference to Reciprocity: Decentralized Matching with Empirically Grounded LLM-agent Based Modeling2609.34679v1 · Wangxuan Fan, Xiaoyu Nie, Zhoutian Shi et al.2026 · 0 citationsarXiv
COBRA-Skills: Contextual Bandit-Guided Evolution for Agent Skill Optimization2609.11682v1 · Pingchen Lu, Xiangyi Wang, Xiang Li et al.2026 · 0 citationsarXiv
SPOT: Sparse Probing and Outcome Calibration for On-Policy Distillation2608.04419v2 · Zikun Qu, Min Zhang, Mingze Kong et al.2026 · 0 citationsarXiv
DemoPSD: Disagreement-Modulated Policy Self-Distillation2607.02502v3 · Yunhe Li, Hao Shi, Wenhao Liu et al.2026 · 0 citationsarXiv
Harness-MU: A Safe, Governed, and Effective Harness for Multi-User LLM Agents2606.21856v1 · Wangxuan Fan, Xiaoyu Nie, Zhongxiang Dai2026 · 0 citationsarXiv
MetaForge: A Self-Evolving Multimodal Agent that Retrieves, Adapts, and Forges Tools On Demand2606.01801v1 · Shouang Wei, Houcheng Min, Xinpeng Dong et al.2026 · 0 citationsarXiv
UniScale: Adaptive Unified Inference Scaling via Online Joint Optimization of Model Routing and Test-Time Scaling2605.30898v1 · Kaiyu Huang, Xingyu Wang, Mingze Kong et al.2026 · 0 citationsarXiv
DRIFT: Decoupled Rollouts and Importance-Weighted Fine-Tuning for Efficient Multi-Turn Optimization2605.31455v1 · Jian Mu, Tianyi Lin, Chengwei Qin et al.2026 · 0 citationsarXiv
Linear and Neural Dueling Bandits with Delayed Feedback2605.26554v1 · Xiangyi Wang, Pingchen Lu, Jie Mao et al.2026 · 0 citationsarXiv
ALSO: Adversarial Online Strategy Optimization for Social Agents2605.15768v2 · Xiang Li, Liping Yi, Mingze Kong et al.2026 · 0 citationsarXiv
Why Zeroth-Order Adaptation May Forget Less: A Randomized Shaping Theory2605.10658v1 · Yao Shu, Jian Mu, Zhongxiang Dai2026 · 0 citationsarXiv
Learning to Reason with Insight for Informal Theorem Proving2604.16278v2 · Yunhe Li, Hao Shi, Bowen Deng et al.2026 · 0 citationsarXiv
MASPOB: Bandit-Based Prompt Optimization for Multi-Agent Systems with Graph Neural Networks2603.02630v2 · Zhi Hong, Qian Zhang, Jiahang Sun et al.2026 · 0 citationsarXiv
Words & Weights: Streamlining Multi-Turn Interactions via Co-Adaptation2603.01375v2 · Chenxing Wei, Hong Wang, Ying He et al.2026 · 0 citationsarXiv
CASTLE: A Comprehensive Benchmark for Evaluating Student-Tailored Personalized Safety in Large Language Models2602.05633v2 · Rui Jia, Ruiyi Lan, Fengrui Liu et al.2026 · 0 citationsarXiv
Real-Time Aligned Reward Model beyond Semantics2601.22664v4 · Zixuan Huang, Xin Xia, Yuxi Ren et al.2026 · 0 citationsarXiv
Dual-Robust Cross-Domain Offline Reinforcement Learning Against Dynamics Shifts2512.02486v2 · Zhongjian Qiao, Rui Yang, Jiafei Lyu et al.2025 · 0 citationsarXiv
T-POP: Test-Time Personalization with Online Preference Feedback2509.24696v2 · Zikun Qu, Min Zhang, Mingze Kong et al.2025 · 0 citationsarXiv
FedPOB: Sample-Efficient Federated Prompt Optimization via Bandits2509.24701v1 · Pingchen Lu, Zhi Hong, Zhiwei Shang et al.2025 · 0 citationsarXiv
Adaptive Batch-Wise Sample Scheduling for Direct Preference Optimization2506.17252v4 · Zixuan Huang, Yikun Ban, Lean Fu et al.2025 · 0 citationsarXiv
ActiveDPO: Active Direct Preference Optimization for Sample-Efficient Alignment2505.19241v2 · Xiaoqiang Lin, Arun Verma, Zhongxiang Dai et al.2025 · 0 citationsarXiv
Convergence Rates of Constrained Expected Improvement2505.11323v2 · Haowei Wang, Jingyi Wang, Zhongxiang Dai et al.2025 · 0 citationsarXiv
Active Human Feedback Collection via Neural Contextual Dueling Bandits2504.12016v2 · Arun Verma, Xiaoqiang Lin, Zhongxiang Dai et al.2025 · 0 citationsarXiv
Online Clustering of Dueling Bandits2502.02079v1 · Zhiyong Wang, Jiahang Sun, Mingze Kong et al.2025 · 0 citationsarXiv
Refining Adaptive Zeroth-Order Optimization at Ease2502.01014v2 · Yao Shu, Qixin Zhang, Kun He et al.2025 · 0 citationsarXiv
Meta-Prompt Optimization for LLM-Based Sequential Decision Making2502.00728v2 · Mingze Kong, Zhiyong Wang, Yao Shu et al.2025 · 0 citationsarXiv
Data-Centric AI in the Age of Large Language Models2406.14473v1 · Xinyi Xu, Zhaoxuan Wu, Rui Qiao et al.2024 · 1 citationarXiv
Prompt Optimization with Human Feedback2405.17346v1 · Xiaoqiang Lin, Zhongxiang Dai, Arun Verma et al.2024 · 5 citationsarXiv
Prompt Optimization with EASE? Efficient Ordering-aware Automated Selection of Exemplars2405.16122v2 · Zhaoxuan Wu, Xiaoqiang Lin, Zhongxiang Dai et al.2024 · 4 citationsarXiv
Robustifying and Boosting Training-Free Neural Architecture Search2403.07591v1 · Zhenfeng He, Yao Shu, Zhongxiang Dai et al.2024 · 0 citationsarXiv
Use Your INSTINCT: INSTruction optimization for LLMs usIng Neural bandits Coupled with Transformers2310.02905v3 · Xiaoqiang Lin, Zhaoxuan Wu, Zhongxiang Dai et al.2023 · 3 citationsarXiv
Source Attribution for Large Language Model-Generated Data2310.00646v2 · Jingtan Wang, Xinyang Lu, Zitong Zhao et al.2023 · 5 citationsarXiv
Federated Zeroth-Order Optimization using Trajectory-Informed Surrogate Gradients2308.04077v1 · Yao Shu, Xiaoqiang Lin, Zhongxiang Dai et al.2023 · 1 citationarXiv
Training-Free Neural Active Learning with Initialization-Robustness Guarantees2306.04454v1 · Apivich Hemachandra, Zhongxiang Dai, Jasraj Singh et al.2023 · 1 citationarXiv
FedHQL: Federated Heterogeneous Q-Learning2301.11135v1 · Flint Xiaofeng Fan, Yining Ma, Zhongxiang Dai et al.2023 · 4 citationsarXiv
Bayesian Optimization under Stochastic Delayed Feedback2206.09341v1 · Arun Verma, Zhongxiang Dai, Bryan Kian Hsiang Low2022 · 4 citationsarXiv
On Provably Robust Meta-Bayesian Optimization2206.06872v2 · Zhongxiang Dai, Yizhou Chen, Haibin Yu et al.2022 · 1 citationarXiv
Federated Neural Bandits2205.14309v2 · Zhongxiang Dai, Yao Shu, Arun Verma et al.2022 · 3 citationsarXiv
Adjusted Expected Improvement for Cumulative Regret Minimization in Noisy Bayesian Optimization2205.04901v3 · Shouri Hu, Haowei Wang, Zhongxiang Dai et al.2022 · 2 citationsarXiv
Differentially Private Federated Bayesian Optimization with Distributed Exploration2110.14153v1 · Zhongxiang Dai, Bryan Kian Hsiang Low, Patrick Jaillet2021 · 25 citationsarXiv
Fault-Tolerant Federated Reinforcement Learning with Theoretical Guarantee2110.14074v2 · Flint Xiaofeng Fan, Yining Ma, Zhongxiang Dai et al.2021 · 39 citationsarXiv
Neural Ensemble Search via Bayesian Sampling2109.02533v2 · Yao Shu, Yizhou Chen, Zhongxiang Dai et al.2021 · 0 citationsarXiv
NASI: Label- and Data-agnostic Neural Architecture Search at Initialization2109.00817v2 · Yao Shu, Shaofeng Cai, Zhongxiang Dai et al.2021 · 18 citationsarXiv
Career total: 83 works. 65 are in this corpus.Showing the 50 most recent.
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.