Author name cluster

John C.S. Lui

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

6 papers

1 author row

AAAI Conference 2026 Conference Paper

A Multi-Agent Conversational Bandit Approach to Online Evaluation and Selection of User-Aligned LLM Responses

Xiangxiang Dai
Yuejin Xie
Maoli Liu
Xuchuang Wang
Zhuohua Li
Huanyu Wang
John C.S. Lui

Prompt-based offline methods are commonly used to optimize large language model (LLM) responses, but evaluating these responses is computationally intensive and often fails to accommodate diverse response styles. This study introduces a novel online evaluation framework that employs a multi-agent conversational bandit model to select optimal responses while aligning with user preferences dynamically. To tackle challenges such as high-dimensional features, large response sets, adaptive conversational needs, and multi-device access, we propose MACO, Multi-Agent Conversational Online Learning, which comprises two key components: (1) MACO-A: Executed by local agents, it employs an online elimination mechanism to filter out low-quality responses. (2) MACO-S: Executed by the cloud server, it adaptively adjusts selection strategies based on aggregated preference data. An adaptive preference mechanism triggers asynchronous conversations to enhance alignment efficiency. Theoretical analysis demonstrates that MACO achieves near-optimal regret bounds, matching state-of-the-art performance in various degenerate cases. Extensive experiments utilizing Google and OpenAI text embedding models on the real-world datasets with different response styles, combined with Llama and GPT-4o, show that MACO consistently outperforms baseline methods by at least 8.29% across varying response set sizes and numbers of agents.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Online Multi-LLM Selection via Contextual Bandits Under Unstructured Context Evolution

Manhin Poon
Xiangxiang Dai
Xutong Liu
Fang Kong
John C.S. Lui
Jinhang Zuo

Large language models (LLMs) exhibit diverse response behaviors, costs, and strengths, making it challenging to select the most suitable LLM for a given user query. We study the problem of adaptive multi-LLM selection in an online setting, where the learner interacts with users through multi-step query refinement and must choose LLMs sequentially without access to offline datasets or model internals. A key challenge arises from unstructured context evolution: the prompt dynamically changes in response to previous model outputs via a black-box process, which cannot be simulated, modeled, or learned. To address this, we propose the first contextual bandit framework for sequential LLM selection under unstructured prompt dynamics. We formalize a notion of myopic regret and develop a LinUCB-based algorithm that provably achieves sublinear regret without relying on future context prediction. We further introduce budget-aware and positionally-aware (favoring early-stage satisfaction) extensions to accommodate variable query costs and user preferences for early high-quality responses. Our algorithms are theoretically grounded and require no offline fine-tuning or dataset-specific training. Experiments on diverse benchmarks demonstrate that our methods outperform existing LLM routing strategies in both accuracy and cost-efficiency, validating the power of contextual bandits for real-time, adaptive LLM selection.

PDF Details DOI

AAAI Conference 2025 Conference Paper

An Enhanced Levenberg--Marquardt Method via Gram Reduction

Chengchang Liu
Luo Luo
John C.S. Lui

This paper studies the problem of solving the system of nonlinear equations. We propose the Gram-reduced Levenberg--Marquardt method, which reuses the Gram matrix. Our method has a global convergence guarantee without relying on any step of line-search or solving sub-problems. We show that our method takes a smaller computational complexity than existing Levenberg--Marquardt methods to find the stationary point of the square norm of the equations. We also show that the proposed method enjoys a local superlinear convergence rate under the non-degenerate assumption. Experiments are conducted on real-world applications in scientific computing and machine learning, which validate the efficiency of our method.

PDF Details DOI

AAAI Conference 2025 Conference Paper

Quantum Best Arm Identification with Quantum Oracles

Xuchuang Wang
Yu-Zhen Janice Chen
Matheus Guedes de Andrade
Jonathan Allcock
Mohammad Hajiesmaili
John C.S. Lui
Don Towsley

Best arm identification (BAI) is a key problem in stochastic multi-armed bandits, where K arms each has an associated reward distribution, and the objective is to minimize the number of queries needed to identify the best arm with high confidence. In this paper, we explore BAI using quantum oracles. For the case where each query probes only one arm (m=1), we devise a quantum algorithm with a query complexity upper bound of O((K/Delta)log(1/delta)), where delta is the confidence parameter and Delta is the reward gap between best and second best arms. This improves on the classical bound by a factor of 1/Delta. For the general case where a single query can probe m arms (1<= m<= K) simultaneously, we propose an algorithm with an upper bound of O((K/(Delta x sqrt(m))) log(1/delta)), improving by a factor of sqrt(m) compared to the m=1 case. We also provide query complexity lower bounds for both scenarios, which match the upper bounds up to logarithmic factors, and validate our theoretical results with Qiskit-based simulations.

PDF Details DOI

AAAI Conference 2019 Conference Paper

Submodular Optimization over Streams with Inhomogeneous Decays

Junzhou Zhao
Shuo Shang
Pinghui Wang
John C.S. Lui
Xiangliang Zhang

Cardinality constrained submodular function maximization, which aims to select a subset of size at most k to maximize a monotone submodular utility function, is the key in many data mining and machine learning applications such as data summarization and maximum coverage problems. When data is given as a stream, streaming submodular optimization (SSO) techniques are desired. Existing SSO techniques can only apply to insertion-only streams where each element has an infinite lifespan, and sliding-window streams where each element has a same lifespan (i. e. , window size). However, elements in some data streams may have arbitrary different lifespans, and this requires addressing SSO over streams with inhomogeneous-decays (SSO-ID). This work formulates the SSO-ID problem and presents three algorithms: BASIC- STREAMING is a basic streaming algorithm that achieves an (1/2 − ) approximation factor; HISTAPPROX improves the efficiency significantly and achieves an (1/3 − ) approximation factor; HISTSTREAMING is a streaming version of HISTAPPROX and uses heuristics to further improve the efficiency. Experiments conducted on real data demonstrate that HISTSTREAMING can find high quality solutions and is up to two orders of magnitude faster than the naive GREEDY algorithm.

PDF Details

AAAI Conference 2019 Conference Paper

Understanding Persuasion Cascades in Online Product Rating Systems

Hong Xie
Yongkun Li
John C.S. Lui

Online product rating systems have become an indispensable component for numerous web services such as Amazon, eBay, Google play store and TripAdvisor. One functionality of such systems is to uncover the product quality via product ratings (or reviews) contributed by consumers. However, a well-known psychological phenomenon called “messagebased persuasion” lead to “biased” product ratings in a cascading manner (we call this the persuasion cascade). This paper investigates: (1) How does the persuasion cascade influence the product quality estimation accuracy? (2) Given a real-world product rating dataset, how to infer the persuasion cascade and analyze it to draw practical insights? We first develop a mathematical model to capture key factors of a persuasion cascade. We formulate a high-order Markov chain to characterize the opinion dynamics of a persuasion cascade and prove the convergence of opinions. We further bound the product quality estimation error for a class of rating aggregation rules including the averaging scoring rule, via the matrix perturbation theory and the Chernoff bound. We also design a maximum likelihood algorithm to infer parameters of the persuasion cascade. We conduct experiments on the data from Amazon and TripAdvisor, and show that persuasion cascades notably exist, but the average scoring rule has a small product quality estimation error under practical scenarios.

PDF Details