arXiv subjects

Flint Xiaofeng Fan

Publications and source records attributed to Flint Xiaofeng Fan.

15 recordsLinked to original sources

arXiv2026

Authority-Preserving Evaluation of Medical Vision-Language Assistants

Medical vision-language models can propose how urgently a skin lesion should be reviewed, but the local service retains authority to accept or replace that proposal under referral policy, capacity, and locally held patient context. Proposal quality and selected-action quality are therefore distinct evaluation targets, and benchmark evidence transfers between them only when local review preserves the expected action score. We introduce AuthEval, a logging and evaluation framework that records both actions, scores the selected action under declared local criteria, and, where feasible, scores the declined proposal under the same rule. It reports the resulting authority gap only when the record supports it. Because the gap is the product of the proposal-change rate and the mean score change on changed cases, that rate alone determines neither its magnitude nor its sign. On ISIC 2019, with MedGemma and simulated local review, two constraint regimes with similar change rates produced an optimistic image-equal gap under capacity ($+0.744$ simulator units) but no detectable gap under safety. The declared evaluation unit also mattered: under mixed constraints the gap reversed from $+0.374$ to $-0.206$ when weighting shifted from image to lesion-aware cluster. AuthEval thus clarifies whether a study's records support claims about the model, the workflow, or both.

cs.CV↗

arXiv2026

FedPref: Federated Preference Learning for Structured Radiology Report Extraction

Radiology reports describe findings and locations in free text, but downstream search and analysis require these relations in a fixed schema. Learning this extraction requires labels that are unevenly distributed across institutions: smaller hospitals have less local evidence, and pooling data may be infeasible. We introduce FedPref: frozen public language models propose alternative JSON extractions, local annotations rank them, and sites collaboratively train compact Qwen3-8B adapters while sharing only model updates. A heterogeneous teacher pool provides cross-model contrast when repeated single-model samples collapse. On development data from six simulated hospitals with unequal data volume and disease prevalence, FedPref improves client-mean F1 by 2.49 points and worst-site F1 by 9.10 points compared with training each site in isolation, with the largest gains at the sites holding the least data. Central training on the pooled preference-pair union is 2.66 points higher on client-mean F1. On a locked, 400-report manually validated gold test set, FedPref reaches 68.68 F1 and pooled training 71.67, preserving that same ordering. FedPref thus lets institutions with unequal, unpooled data benefit from collaboration without ever sharing reports or annotations.

cs.AI↗

arXiv2026

Why Do We Suffer for Fun? Ordeal Pleasure in Souls-like Games

Souls-like games exemplify how digital play can produce radical forms of pleasure through sustained challenge: players voluntarily invest tens or hundreds of hours in experiences designed to kill them repeatedly. This paper theorizes ordeal pleasure as a community-level phenomenon that emerges most fully when three mechanisms reinforce one another: Ludic Cultivation (mastery through fair adversity), Aspirational Deferment (delayed gratification oriented toward future growth), and Communal Mythopoesis (collective construction of shared meaning). Drawing on game design analysis, empirical player studies, and community discourse, we show how Souls-like games produce pleasure by coordinating difficulty, temporal structure, and social meaning-making. Comparative analysis (Elden Ring, Hollow Knight, Lords of the Fallen, The Surge) illustrates how specific design choices enable or undermine ordeal pleasure. The framework adds a temporal dimension to motivation theory and specifies social mechanisms beyond generic relatedness. It also offers design principles for designers seeking to create challenging games that transform suffering into complex satisfaction.

cs.CY↗

arXiv2026

Information Fidelity in Tool-Using LLM Agents: A Martingale Analysis of the Model Context Protocol

As AI agents powered by large language models (LLMs) increasingly use external tools for high-stakes decisions, a critical reliability question arises: how do errors propagate across sequential tool calls? We introduce the first theoretical framework for analyzing error accumulation in Model Context Protocol (MCP) agents, proving that cumulative distortion exhibits linear growth and high-probability deviations bounded by $O(\sqrt{T})$. This concentration property ensures predictable system behavior and rules out exponential failure modes. We develop a hybrid distortion metric combining discrete fact matching with continuous semantic similarity, then establish martingale concentration bounds on error propagation through sequential tool interactions. Experiments across Qwen2-7B, Llama-3-8B, and Mistral-7B validate our theoretical predictions, showing empirical distortion tracks the linear trend with deviations consistently within $O(\sqrt{T})$ envelopes. Key findings include: semantic weighting reduces distortion by 80\%, and periodic re-grounding approximately every 9 steps suffices for error control. We translate these concentration guarantees into actionable deployment principles for trustworthy agent systems.

cs.AI↗

arXiv2025

Diversifying Policy Behaviors with Extrinsic Behavioral Curiosity

Imitation learning (IL) has shown promise in various applications (e.g. robot locomotion) but is often limited to learning a single expert policy, constraining behavior diversity and robustness in unpredictable real-world scenarios. To address this, we introduce Quality Diversity Inverse Reinforcement Learning (QD-IRL), a novel framework that integrates quality-diversity optimization with IRL methods, enabling agents to learn diverse behaviors from limited demonstrations. This work introduces Extrinsic Behavioral Curiosity (EBC), which allows agents to receive additional curiosity rewards from an external critic based on how novel the behaviors are with respect to a large behavioral archive. To validate the effectiveness of EBC in exploring diverse locomotion behaviors, we evaluate our method on multiple robot locomotion tasks. EBC improves the performance of QD-IRL instances with GAIL, VAIL, and DiffAIL across all included environments by up to 185%, 42%, and 150%, even surpassing expert performance by 20% in Humanoid. Furthermore, we demonstrate that EBC is applicable to Gradient-Arborescence-based Quality Diversity Reinforcement Learning (QD-RL) algorithms, where it substantially improves performance and provides a generic technique for learning behavioral-diverse policies. The source code of this work is provided at https://github.com/vanzll/EBC.

cs.LG↗

arXiv2025

Position Paper: Rethinking Privacy in RL for Sequential Decision-making in the Age of LLMs

The rise of reinforcement learning (RL) in critical real-world applications demands a fundamental rethinking of privacy in AI systems. Traditional privacy frameworks, designed to protect isolated data points, fall short for sequential decision-making systems where sensitive information emerges from temporal patterns, behavioral strategies, and collaborative dynamics. Modern RL paradigms, such as federated RL (FedRL) and RL with human feedback (RLHF) in large language models (LLMs), exacerbate these challenges by introducing complex, interactive, and context-dependent learning environments that traditional methods do not address. In this position paper, we argue for a new privacy paradigm built on four core principles: multi-scale protection, behavioral pattern protection, collaborative privacy preservation, and context-aware adaptation. These principles expose inherent tensions between privacy, utility, and interpretability that must be navigated as RL systems become more pervasive in high-stakes domains like healthcare, autonomous vehicles, and decision support systems powered by LLMs. To tackle these challenges, we call for the development of new theoretical frameworks, practical mechanisms, and rigorous evaluation methodologies that collectively enable effective privacy protection in sequential decision-making systems.

cs.LG↗

arXiv2025

FedRLHF: A Convergence-Guaranteed Federated Framework for Privacy-Preserving and Personalized RLHF

In the era of increasing privacy concerns and demand for personalized experiences, traditional Reinforcement Learning with Human Feedback (RLHF) frameworks face significant challenges due to their reliance on centralized data. We introduce Federated Reinforcement Learning with Human Feedback (FedRLHF), a novel framework that decentralizes the RLHF process. FedRLHF enables collaborative policy learning across multiple clients without necessitating the sharing of raw data or human feedback, thereby ensuring robust privacy preservation. Leveraging federated reinforcement learning, each client integrates human feedback locally into their reward functions and updates their policies through personalized RLHF processes. We establish rigorous theoretical foundations for FedRLHF, providing convergence guarantees, and deriving sample complexity bounds that scale efficiently with the number of clients. Empirical evaluations on the MovieLens and IMDb datasets demonstrate that FedRLHF not only preserves user privacy but also achieves performance on par with centralized RLHF, while enhancing personalization across diverse client environments.

cs.LG↗

arXiv2025

FedHPD: Heterogeneous Federated Reinforcement Learning via Policy Distillation

Federated Reinforcement Learning (FedRL) improves sample efficiency while preserving privacy; however, most existing studies assume homogeneous agents, limiting its applicability in real-world scenarios. This paper investigates FedRL in black-box settings with heterogeneous agents, where each agent employs distinct policy networks and training configurations without disclosing their internal details. Knowledge Distillation (KD) is a promising method for facilitating knowledge sharing among heterogeneous models, but it faces challenges related to the scarcity of public datasets and limitations in knowledge representation when applied to FedRL. To address these challenges, we propose Federated Heterogeneous Policy Distillation (FedHPD), which solves the problem of heterogeneous FedRL by utilizing action probability distributions as a medium for knowledge sharing. We provide a theoretical analysis of FedHPD's convergence under standard assumptions. Extensive experiments corroborate that FedHPD shows significant improvements across various reinforcement learning benchmark tasks, further validating our theoretical findings. Moreover, additional experiments demonstrate that FedHPD operates effectively without the need for an elaborate selection of public datasets.

cs.LG↗

arXiv2024

SUBER: An RL Environment with Simulated Human Behavior for Recommender Systems

Reinforcement learning (RL) has gained popularity in the realm of recommender systems due to its ability to optimize long-term rewards and guide users in discovering relevant content. However, the successful implementation of RL in recommender systems is challenging because of several factors, including the limited availability of online data for training on-policy methods. This scarcity requires expensive human interaction for online model training. Furthermore, the development of effective evaluation frameworks that accurately reflect the quality of models remains a fundamental challenge in recommender systems. To address these challenges, we propose a comprehensive framework for synthetic environments that simulate human behavior by harnessing the capabilities of large language models (LLMs). We complement our framework with in-depth ablation studies and demonstrate its effectiveness with experiments on movie and book recommendations. Using LLMs as synthetic users, this work introduces a modular and novel framework to train RL-based recommender systems. The software, including the RL environment, is publicly available on GitHub.

cs.IR↗

arXiv2024

CAESAR: Enhancing Federated RL in Heterogeneous MDPs through Convergence-Aware Sampling with Screening

In this study, we delve into Federated Reinforcement Learning (FedRL) in the context of value-based agents operating across diverse Markov Decision Processes (MDPs). Existing FedRL methods typically aggregate agents' learning by averaging the value functions across them to improve their performance. However, this aggregation strategy is suboptimal in heterogeneous environments where agents converge to diverse optimal value functions. To address this problem, we introduce the Convergence-AwarE SAmpling with scReening (CAESAR) aggregation scheme designed to enhance the learning of individual agents across varied MDPs. CAESAR is an aggregation strategy used by the server that combines convergence-aware sampling with a screening mechanism. By exploiting the fact that agents learning in identical MDPs are converging to the same optimal value function, CAESAR enables the selective assimilation of knowledge from more proficient counterparts, thereby significantly enhancing the overall learning efficiency. We empirically validate our hypothesis and demonstrate the effectiveness of CAESAR in enhancing the learning efficiency of agents, using both a custom-built GridWorld environment and the classical FrozenLake-v1 task, each presenting varying levels of environmental heterogeneity.

cs.LG↗

arXiv2024

Decentralized Federated Policy Gradient with Byzantine Fault-Tolerance and Provably Fast Convergence

In Federated Reinforcement Learning (FRL), agents aim to collaboratively learn a common task, while each agent is acting in its local environment without exchanging raw trajectories. Existing approaches for FRL either (a) do not provide any fault-tolerance guarantees (against misbehaving agents), or (b) rely on a trusted central agent (a single point of failure) for aggregating updates. We provide the first decentralized Byzantine fault-tolerant FRL method. Towards this end, we first propose a new centralized Byzantine fault-tolerant policy gradient (PG) algorithm that improves over existing methods by relying only on assumptions standard for non-fault-tolerant PG. Then, as our main contribution, we show how a combination of robust aggregation and Byzantine-resilient agreement methods can be leveraged in order to eliminate the need for a trusted central entity. Since our results represent the first sample complexity analysis for Byzantine fault-tolerant decentralized federated non-convex optimization, our technical contributions may be of independent interest. Finally, we corroborate our theoretical results experimentally for common RL environments, demonstrating the speed-up of decentralized federations w.r.t. the number of participating agents and resilience against various Byzantine attacks.

cs.LG↗

arXiv2023

Action and Trajectory Planning for Urban Autonomous Driving with Hierarchical Reinforcement Learning

Reinforcement Learning (RL) has made promising progress in planning and decision-making for Autonomous Vehicles (AVs) in simple driving scenarios. However, existing RL algorithms for AVs fail to learn critical driving skills in complex urban scenarios. First, urban driving scenarios require AVs to handle multiple driving tasks of which conventional RL algorithms are incapable. Second, the presence of other vehicles in urban scenarios results in a dynamically changing environment, which challenges RL algorithms to plan the action and trajectory of the AV. In this work, we propose an action and trajectory planner using Hierarchical Reinforcement Learning (atHRL) method, which models the agent behavior in a hierarchical model by using the perception of the lidar and birdeye view. The proposed atHRL method learns to make decisions about the agent's future trajectory and computes target waypoints under continuous settings based on a hierarchical DDPG algorithm. The waypoints planned by the atHRL model are then sent to a low-level controller to generate the steering and throttle commands required for the vehicle maneuver. We empirically verify the efficacy of atHRL through extensive experiments in complex urban driving scenarios that compose multiple tasks with the presence of other vehicles in the CARLA simulator. The experimental results suggest a significant performance improvement compared to the state-of-the-art RL methods.

cs.RO↗

arXiv2023

Federated Neural Bandits

Recent works on neural contextual bandits have achieved compelling performances due to their ability to leverage the strong representation power of neural networks (NNs) for reward prediction. Many applications of contextual bandits involve multiple agents who collaborate without sharing raw observations, thus giving rise to the setting of federated contextual bandits. Existing works on federated contextual bandits rely on linear or kernelized bandits, which may fall short when modeling complex real-world reward functions. So, this paper introduces the federated neural-upper confidence bound (FN-UCB) algorithm. To better exploit the federated setting, FN-UCB adopts a weighted combination of two UCBs: $\text{UCB}^{a}$ allows every agent to additionally use the observations from the other agents to accelerate exploration (without sharing raw observations), while $\text{UCB}^{b}$ uses an NN with aggregated parameters for reward prediction in a similar way to federated averaging for supervised learning. Notably, the weight between the two UCBs required by our theoretical analysis is amenable to an interesting interpretation, which emphasizes $\text{UCB}^{a}$ initially for accelerated exploration and relies more on $\text{UCB}^{b}$ later after enough observations have been collected to train the NNs for accurate reward prediction (i.e., reliable exploitation). We prove sub-linear upper bounds on both the cumulative regret and the number of communication rounds of FN-UCB, and empirically demonstrate its competitive performance.

cs.LG↗

arXiv2023

FedHQL: Federated Heterogeneous Q-Learning

Federated Reinforcement Learning (FedRL) encourages distributed agents to learn collectively from each other's experience to improve their performance without exchanging their raw trajectories. The existing work on FedRL assumes that all participating agents are homogeneous, which requires all agents to share the same policy parameterization (e.g., network architectures and training configurations). However, in real-world applications, agents are often in disagreement about the architecture and the parameters, possibly also because of disparate computational budgets. Because homogeneity is not given in practice, we introduce the problem setting of Federated Reinforcement Learning with Heterogeneous And bLack-box agEnts (FedRL-HALE). We present the unique challenges this new setting poses and propose the Federated Heterogeneous Q-Learning (FedHQL) algorithm that principally addresses these challenges. We empirically demonstrate the efficacy of FedHQL in boosting the sample efficiency of heterogeneous agents with distinct policy parameterization using standard RL tasks.

cs.LG↗

arXiv2022

Fault-Tolerant Federated Reinforcement Learning with Theoretical Guarantee

The growing literature of Federated Learning (FL) has recently inspired Federated Reinforcement Learning (FRL) to encourage multiple agents to federatively build a better decision-making policy without sharing raw trajectories. Despite its promising applications, existing works on FRL fail to I) provide theoretical analysis on its convergence, and II) account for random system failures and adversarial attacks. Towards this end, we propose the first FRL framework the convergence of which is guaranteed and tolerant to less than half of the participating agents being random system failures or adversarial attackers. We prove that the sample efficiency of the proposed framework is guaranteed to improve with the number of agents and is able to account for such potential failures or attacks. All theoretical results are empirically verified on various RL benchmark tasks.

cs.LG↗