Guojun Xiong

Jimin Huang, Mengxi Xiao, Dong Li et al.

Financial LLMs hold promise for advancing financial tasks and domain-specific applications. However, they are limited by scarce corpora, weak multimodal capabilities, and narrow evaluations, making them less suited for real-world application. To address this, we introduce \textit{Open-FinLLMs}, the first open-source multimodal financial LLMs designed to handle diverse tasks across text, tabular, time-series, and chart data, excelling in zero-shot, few-shot, and fine-tuning settings. The suite includes FinLLaMA, pre-trained on a comprehensive 52-billion-token corpus; FinLLaMA-Instruct, fine-tuned with 573K financial instructions; and FinLLaVA, enhanced with 1.43M multimodal tuning pairs for strong cross-modal reasoning. We comprehensively evaluate Open-FinLLMs across 14 financial tasks, 30 datasets, and 4 multimodal tasks in zero-shot, few-shot, and supervised fine-tuning settings, introducing two new multimodal evaluation datasets. Our results show that Open-FinLLMs outperforms afvanced financial and general LLMs such as GPT-4, across financial NLP, decision-making, and multi-modal tasks, highlighting their potential to tackle real-world challenges. To foster innovation and collaboration across academia and industry, we release all codes (https://anonymous.4open.science/r/PIXIU2-0D70/B1D7/LICENSE) and models under OSI-approved licenses.

Kaixuan Liu, Guojun Xiong, Weinan Zhang et al.

Evaluating large language model (LLM) agents in multi-turn interactive environments is expensive and risky, as it requires online environment interaction. We propose ADWM (Autoregressive Diffusion World Model), an evaluation framework that estimates the performance of a new LLM agent policy purely from pre-collected trajectories. The core idea is to learn a latent diffusion world model that simulates how the environment responds to the evaluation policy, without ever executing it in the real environment. Existing diffusion-based OPE methods guide full trajectories in a single pass by jointly diffusing states and actions, an assumption that breaks down for LLM agents whose actions are discrete text that must be sampled from the policy after observing the environment. Unlike autoregressive world models that suffer from compounding errors, ADWM models each transition as an independent denoising process, enabling reliable step-by-step rollouts where the world model and agent alternate in causal order. Crucially, the LLM agent under evaluation directly guides the diffusion generation at each step via a policy-conditioned score function, ensuring that simulated trajectories accurately reflect its decision-making patterns. Empirically, ADWM achieves accurate value estimates and evaluation reliability across diverse multi-turn agent tasks, demonstrating its promise as a practical framework for offline LLM agent evaluation.

Yangyang Yu, Zhiyuan Yao, Haohang Li et al.

Large language models (LLMs) have demonstrated notable potential in conducting complex tasks and are increasingly utilized in various financial applications. However, high-quality sequential financial investment decision-making remains challenging. These tasks require multiple interactions with a volatile environment for every decision, demanding sufficient intelligence to maximize returns and manage risks. Although LLMs have been used to develop agent systems that surpass human teams and yield impressive investment returns, opportunities to enhance multi-sourced information synthesis and optimize decision-making outcomes through timely experience refinement remain unexplored. Here, we introduce the FinCon, an LLM-based multi-agent framework with CONceptual verbal reinforcement tailored for diverse FINancial tasks. Inspired by effective real-world investment firm organizational structures, FinCon utilizes a manager-analyst communication hierarchy. This structure allows for synchronized cross-functional agent collaboration towards unified goals through natural language interactions and equips each agent with greater memory capacity than humans. Additionally, a risk-control component in FinCon enhances decision quality by episodically initiating a self-critiquing mechanism to update systematic investment beliefs. The conceptualized beliefs serve as verbal reinforcement for the future agent's behavior and can be selectively propagated to the appropriate node that requires knowledge updates. This feature significantly improves performance while reducing unnecessary peer-to-peer communication costs. Moreover, FinCon demonstrates strong generalization capabilities in various financial tasks, including single stock trading and portfolio management.

Guojun Xiong, Jian Li

Multi-player multi-armed bandit is an increasingly relevant decision-making problem, motivated by applications to cognitive radio systems. Most research for this problem focuses exclusively on the settings that players have \textit{full access} to all arms and receive no reward when pulling the same arm. Hence all players solve the same bandit problem with the goal of maximizing their cumulative reward. However, these settings neglect several important factors in many real-world applications, where players have \textit{limited access} to \textit{a dynamic local subset of arms} (i.e., an arm could sometimes be ``walking'' and not accessible to the player). To this end, this paper proposes a \textit{multi-player multi-armed walking bandits} model, aiming to address aforementioned modeling issues. The goal now is to maximize the reward, however, players can only pull arms from the local subset and only collect a full reward if no other players pull the same arm. We adopt Upper Confidence Bound (UCB) to deal with the exploration-exploitation tradeoff and employ distributed optimization techniques to properly handle collisions. By carefully integrating these two techniques, we propose a decentralized algorithm with near-optimal guarantee on the regret, and can be easily implemented to obtain competitive empirical performance.

Guojun Xiong, Gang Yan, Shiqiang Wang et al.

With the increasing demand for large-scale training of machine learning models, fully decentralized optimization methods have recently been advocated as alternatives to the popular parameter server framework. In this paradigm, each worker maintains a local estimate of the optimal parameter vector, and iteratively updates it by waiting and averaging all estimates obtained from its neighbors, and then corrects it on the basis of its local dataset. However, the synchronization phase is sensitive to stragglers. An efficient way to mitigate this effect is to consider asynchronous updates, where each worker computes stochastic gradients and communicates with other workers at its own pace. Unfortunately, fully asynchronous updates suffer from staleness of stragglers' parameters. To address these limitations, we propose a fully decentralized algorithm DSGD-AAU with adaptive asynchronous updates via adaptively determining the number of neighbor workers for each worker to communicate with. We show that DSGD-AAU achieves a linear speedup for convergence and demonstrate its effectiveness via extensive experiments.

Qianqian Xie, Weiguang Han, Zhengyu Chen et al.

LLMs have transformed NLP and shown promise in various fields, yet their potential in finance is underexplored due to a lack of comprehensive evaluation benchmarks, the rapid development of LLMs, and the complexity of financial tasks. In this paper, we introduce FinBen, the first extensive open-source evaluation benchmark, including 36 datasets spanning 24 financial tasks, covering seven critical aspects: information extraction (IE), textual analysis, question answering (QA), text generation, risk management, forecasting, and decision-making. FinBen offers several key innovations: a broader range of tasks and datasets, the first evaluation of stock trading, novel agent and Retrieval-Augmented Generation (RAG) evaluation, and three novel open-source evaluation datasets for text summarization, question answering, and stock trading. Our evaluation of 15 representative LLMs, including GPT-4, ChatGPT, and the latest Gemini, reveals several key findings: While LLMs excel in IE and textual analysis, they struggle with advanced reasoning and complex tasks like text generation and forecasting. GPT-4 excels in IE and stock trading, while Gemini is better at text generation and forecasting. Instruction-tuned LLMs improve textual analysis but offer limited benefits for complex tasks such as QA. FinBen has been used to host the first financial LLMs shared task at the FinNLP-AgentScen workshop during IJCAI-2024, attracting 12 teams. Their novel solutions outperformed GPT-4, showcasing FinBen's potential to drive innovation in financial LLMs. All datasets, results, and codes are released for the research community: https://github.com/The-FinAI/PIXIU.

Guojun Xiong, Jian Li

Whittle index policy is a heuristic to the intractable restless multi-armed bandits (RMAB) problem. Although it is provably asymptotically optimal, finding Whittle indices remains difficult. In this paper, we present Neural-Q-Whittle, a Whittle index based Q-learning algorithm for RMAB with neural network function approximation, which is an example of nonlinear two-timescale stochastic approximation with Q-function values updated on a faster timescale and Whittle indices on a slower timescale. Despite the empirical success of deep Q-learning, the non-asymptotic convergence rate of Neural-Q-Whittle, which couples neural networks with two-timescale Q-learning largely remains unclear. This paper provides a finite-time analysis of Neural-Q-Whittle, where data are generated from a Markov chain, and Q-function is approximated by a ReLU neural network. Our analysis leverages a Lyapunov drift approach to capture the evolution of two coupled parameters, and the nonlinearity in value function approximation further requires us to characterize the approximation error. Combing these provide Neural-Q-Whittle with $\mathcal{O}(1/k^{2/3})$ convergence rate, where $k$ is the number of iterations.

Xiaoyu Wang, Guojun Xiong, Houwei Cao et al.

Federated Learning (FL) trains a shared model using data and computation power on distributed agents coordinated by a central server. Decentralized FL (DFL) utilizes local model exchange and aggregation between agents to reduce the communication and computation overheads on the central server. However, when agents are mobile, the communication opportunity between agents can be sporadic, largely hindering the convergence and accuracy of DFL. In this paper, we propose Cached Decentralized Federated Learning (Cached-DFL) to investigate delay-tolerant model spreading and aggregation enabled by model caching on mobile agents. Each agent stores not only its own model, but also models of agents encountered in the recent past. When two agents meet, they exchange their own models as well as the cached models. Local model aggregation utilizes all models stored in the cache. We theoretically analyze the convergence of Cached-DFL, explicitly taking into account the model staleness introduced by caching. We design and compare different model caching algorithms for different DFL and mobility scenarios. We conduct detailed case studies in a vehicular network to systematically investigate the interplay between agent mobility, cache staleness, and model convergence. In our experiments, Cached-DFL converges quickly, and significantly outperforms DFL without caching.

Haohang Li, Yupeng Cao, Yangyang Yu et al. · utoronto

Recent advancements have underscored the potential of large language model (LLM)-based agents in financial decision-making. Despite this progress, the field currently encounters two main challenges: (1) the lack of a comprehensive LLM agent framework adaptable to a variety of financial tasks, and (2) the absence of standardized benchmarks and consistent datasets for assessing agent performance. To tackle these issues, we introduce \textsc{InvestorBench}, the first benchmark specifically designed for evaluating LLM-based agents in diverse financial decision-making contexts. InvestorBench enhances the versatility of LLM-enabled agents by providing a comprehensive suite of tasks applicable to different financial products, including single equities like stocks, cryptocurrencies and exchange-traded funds (ETFs). Additionally, we assess the reasoning and decision-making capabilities of our agent framework using thirteen different LLMs as backbone models, across various market environments and tasks. Furthermore, we have curated a diverse collection of open-source, multi-modal datasets and developed a comprehensive suite of environments for financial decision-making. This establishes a highly accessible platform for evaluating financial agents' performance across various scenarios.

Yohai Trabelsi, Guojun Xiong, Fentabil Getnet et al.

Ethiopia's Ministry of Health is upgrading health posts to improve access to essential services, particularly in rural areas. Limited resources, however, require careful prioritization of which facilities to upgrade to maximize population coverage while accounting for diverse expert and stakeholder preferences. In collaboration with the Ethiopian Public Health Institute and Ministry of Health, we propose a hybrid framework that systematically integrates expert knowledge with optimization techniques. Classical optimization methods provide theoretical guarantees but require explicit, quantitative objectives, whereas stakeholder criteria are often articulated in natural language and difficult to formalize. To bridge these domains, we develop the Large language model and Extended Greedy (LEG) framework. Our framework combines a provable approximation algorithm for population coverage optimization with LLM-driven iterative refinement that incorporates human-AI alignment to ensure solutions reflect expert qualitative guidance while preserving coverage guarantees. Experiments on real-world data from three Ethiopian regions demonstrate the framework's effectiveness and its potential to inform equitable, data-driven health system planning.

Yiran Song, Yikai Zhang, Shuang Zhou et al.

Multiple instance learning (MIL) has emerged as the dominant paradigm for whole slide image (WSI) analysis in computational pathology, achieving strong diagnostic performance through patch-level feature aggregation. However, existing MIL methods face critical limitations: (1) they rely on attention mechanisms that lack causal interpretability, and (2) they fail to integrate patient demographics (age, gender, race), leading to fairness concerns across diverse populations. These shortcomings hinder clinical translation, where algorithmic bias can exacerbate health disparities. We introduce \textbf{MeCaMIL}, a causality-aware MIL framework that explicitly models demographic confounders through structured causal graphs. Unlike prior approaches treating demographics as auxiliary features, MeCaMIL employs principled causal inference -- leveraging do-calculus and collider structures -- to disentangle disease-relevant signals from spurious demographic correlations. Extensive evaluation on three benchmarks demonstrates state-of-the-art performance across CAMELYON16 (ACC/AUC/F1: 0.939/0.983/0.946), TCGA-Lung (0.935/0.979/0.931), and TCGA-Multi (0.977/0.993/0.970, five cancer types). Critically, MeCaMIL achieves superior fairness -- demographic disparity variance drops by over 65% relative reduction on average across attributes, with notable improvements for underserved populations. The framework generalizes to survival prediction (mean C-index: 0.653, +0.017 over best baseline across five cancer types). Ablation studies confirm causal graph structure is essential -- alternative designs yield 0.048 lower accuracy and 4.2x times worse fairness. These results establish MeCaMIL as a principled framework for fair, interpretable, and clinically actionable AI in digital pathology. Code will be released upon acceptance.

Jimin Huang, Duanyu Feng, Nuo Chen et al.

Federated learning (FL) enables training large language models (LLMs) without sharing raw data, but adapting LLMs under strict data isolation and non-IID client distributions remains challenging in practice. Synthetic data offers a natural privacy-preserving surrogate for local training, yet existing federated pipelines typically treat synthetic generation as static or loosely coupled with downstream optimization, leading to rapidly diminishing utility under heterogeneous clients. We study federated adaptation of LLMs on tabular tasks where raw records and validation data cannot be shared, and local training must rely entirely on synthetic tables. We propose Concordia, a tri-level optimization framework that aligns synthetic data generation with federated validation utility despite these constraints. At the client level, models are adapted via parameter-efficient LoRA training on synthetic tables. Clients additionally learn lightweight utility scorers from private validation feedback to reweight synthetic samples during local training. At the outer level, each client refines its own synthetic table generator using group-relative policy optimization (GRPO), guided by an ensemble of heterogeneous scorers shared across clients, without aggregating generator parameters or exposing validation data. Experiments on privacy-sensitive tabular benchmarks from finance and healthcare demonstrate that Concordia consistently improves federated performance, cross-client stability, and robustness to distribution shift compared to static and decoupled synthetic-data baselines.

Yueru He, Xueqing Peng, Yupeng Cao et al.

We introduce FinCriticalED (Financial Critical Error Detection), a visual benchmark for evaluating OCR and vision language models on financial documents at the fact level. Financial documents contain visually dense and table heavy layouts where numerical and temporal information is tightly coupled with structure. In high stakes settings, small OCR mistakes such as sign inversion or shifted dates can lead to materially different interpretations, while traditional OCR metrics like ROUGE and edit distance capture only surface level text similarity. \ficriticaled provides 500 image-HTML pairs with expert annotated financial facts covering over seven hundred numerical and temporal facts. It introduces three key contributions. First, it establishes the first fact level evaluation benchmark for financial document understanding, shifting evaluation from lexical overlap to domain critical factual correctness. Second, all annotations are created and verified by financial experts with strict quality control over signs, magnitudes, and temporal expressions. Third, we develop an LLM-as-Judge evaluation pipeline that performs structured fact extraction and contextual verification for visually complex financial documents. We benchmark OCR systems, open source vision language models, and proprietary models on FinCriticalED. Results show that although the strongest proprietary models achieve the highest factual accuracy, substantial errors remain in visually intricate numerical and temporal contexts. Through quantitative evaluation and expert case studies, FinCriticalED provides a rigorous foundation for advancing visual factual precision in financial and other precision critical domains.

Polydoros Giannouris, Yuechen Jiang, Lingfei Qian et al.

Many sequential decision-making problems exhibit hierarchical structure, where high-level semantic choices constrain downstream actions and feedback is delayed and ambiguous. Learning in such settings is challenging due to credit assignment: performance degradation may arise from flawed abstractions, suboptimal execution, or their interaction. We study this challenge through pair trading, a domain that naturally combines long-horizon semantic reasoning for asset pair selection with short-horizon execution under partial observability. We formulate pair trading as a hierarchical reinforcement learning problem and propose a language-driven optimization framework in which both high-level and low-level policies are parameterized by large language models (LLMs) and optimized exclusively through prompt updates. Our approach leverages pretrained LLMs as hierarchical policies and uses trajectory- and episode-level textual feedback to adapt abstractions and execution without gradient-based fine-tuning. By explicitly separating abstraction selection from execution, the framework reduces non-stationarity across hierarchical levels and enables targeted adaptation under delayed feedback. Experiments on real-world market data show consistent improvements over traditional and LLM-based baselines, demonstrating the effectiveness of language-driven hierarchical reinforcement learning.

Guojun Xiong, Zhiyang Deng, Keyi Wang et al.

Large language models (LLMs) fine-tuned on multimodal financial data have demonstrated impressive reasoning capabilities in various financial tasks. However, they often struggle with multi-step, goal-oriented scenarios in interactive financial markets, such as trading, where complex agentic approaches are required to improve decision-making. To address this, we propose \textsc{FLAG-Trader}, a unified architecture integrating linguistic processing (via LLMs) with gradient-driven reinforcement learning (RL) policy optimization, in which a partially fine-tuned LLM acts as the policy network, leveraging pre-trained knowledge while adapting to the financial domain through parameter-efficient fine-tuning. Through policy gradient optimization driven by trading rewards, our framework not only enhances LLM performance in trading but also improves results on other financial-domain tasks. We present extensive empirical evidence to validate these enhancements.

Guojun Xiong, Gang Yan, Shiqiang Wang et al.

Decentralized learning has emerged as an alternative method to the popular parameter-server framework which suffers from high communication burden, single-point failure and scalability issues due to the need of a central server. However, most existing works focus on a single shared model for all workers regardless of the data heterogeneity problem, rendering the resulting model performing poorly on individual workers. In this work, we propose a novel personalized decentralized learning algorithm named DePRL via shared representations. Our algorithm relies on ideas from representation learning theory to learn a low-dimensional global representation collaboratively among all workers in a fully decentralized manner, and a user-specific low-dimensional local head leading to a personalized solution for each worker. We show that DePRL achieves, for the first time, a provable linear speedup for convergence with general non-linear representations (i.e., the convergence rate is improved linearly with respect to the number of workers). Experimental results support our theoretical findings showing the superiority of our method in data heterogeneous environments.

Shufan Wang, Guojun Xiong, Jian Li

Restless multi-armed bandits (RMAB) have been widely used to model sequential decision making problems with constraints. The decision maker (DM) aims to maximize the expected total reward over an infinite horizon under an "instantaneous activation constraint" that at most B arms can be activated at any decision epoch, where the state of each arm evolves stochastically according to a Markov decision process (MDP). However, this basic model fails to provide any fairness guarantee among arms. In this paper, we introduce RMAB-F, a new RMAB model with "long-term fairness constraints", where the objective now is to maximize the long term reward while a minimum long-term activation fraction for each arm must be satisfied. For the online RMAB-F setting (i.e., the underlying MDPs associated with each arm are unknown to the DM), we develop a novel reinforcement learning (RL) algorithm named Fair-UCRL. We prove that Fair-UCRL ensures probabilistic sublinear bounds on both the reward regret and the fairness violation regret. Compared with off-the-shelf RL methods, our Fair-UCRL is much more computationally efficient since it contains a novel exploitation that leverages a low-complexity index policy for making decisions. Experimental results further demonstrate the effectiveness of our Fair-UCRL.

Lingkai Kong, Haichuan Wang, Tonghan Wang et al.

Incorporating pre-collected offline data from a source environment can significantly improve the sample efficiency of reinforcement learning (RL), but this benefit is often challenged by discrepancies between the transition dynamics of the source and target environments. Existing methods typically address this issue by penalizing or filtering out source transitions in high dynamics-gap regions. However, their estimation of the dynamics gap often relies on KL divergence or mutual information, which can be ill-defined when the source and target dynamics have disjoint support. To overcome these limitations, we propose CompFlow, a method grounded in the theoretical connection between flow matching and optimal transport. Specifically, we model the target dynamics as a conditional flow built upon the output distribution of the source-domain flow, rather than learning it directly from a Gaussian prior. This composite structure offers two key advantages: (1) improved generalization for learning target dynamics, and (2) a principled estimation of the dynamics gap via the Wasserstein distance between source and target transitions. Leveraging our principled estimation of the dynamics gap, we further introduce an optimistic active data collection strategy that prioritizes exploration in regions of high dynamics gap, and theoretically prove that it reduces the performance disparity with the optimal policy. Empirically, CompFlow outperforms strong baselines across several RL benchmarks with shifted dynamics.

Mauricio Tec, Guojun Xiong, Haichuan Wang et al.

Deep Reinforcement Learning (RL) is remarkably effective in addressing sequential resource allocation problems in domains such as healthcare, public policy, and resource management. However, deep RL policies often lack transparency and adaptability, challenging their deployment alongside human decision-makers. In contrast, Language Agents, powered by large language models (LLMs), provide human-understandable reasoning but may struggle with effective decision making. To bridge this gap, we propose Rule-Bottleneck Reinforcement Learning (RBRL), a novel framework that jointly optimizes decision and explanations. At each step, RBRL generates candidate rules with an LLM, selects among them using an attention-based RL policy, and determines the environment action with an explanation via chain-of-thought reasoning. The RL rule selection is optimized using the environment rewards and an explainability metric judged by the LLM. Evaluations in real-world scenarios highlight RBRL's competitive performance with deep RL and efficiency gains over LLM fine-tuning. A survey further confirms the enhanced quality of its explanations.

Guojun Xiong, Haichuan Wang, Yuqi Pan et al.

Restless multi-armed bandits (RMABs) have been highly successful in optimizing sequential resource allocation across many domains. However, in many practical settings with highly scarce resources, where each agent can only receive at most one resource, such as healthcare intervention programs, the standard RMAB framework falls short. To tackle such scenarios, we introduce Finite-Horizon Single-Pull RMABs (SPRMABs), a novel variant in which each arm can only be pulled once. This single-pull constraint introduces additional complexity, rendering many existing RMAB solutions suboptimal or ineffective. %To address this, we propose using dummy states to duplicate the system, ensuring that once an arm is activated, it transitions exclusively within the dummy states. To address this shortcoming, we propose using \textit{dummy states} that expand the system and enforce the one-pull constraint. We then design a lightweight index policy for this expanded system. For the first time, we demonstrate that our index policy achieves a sub-linearly decaying average optimality gap of $\tilde{\mathcal{O}}\left(\frac{1}{ρ^{1/2}}\right)$ for a finite number of arms, where $ρ$ is the scaling factor for each arm cluster. Extensive simulations validate the proposed method, showing robust performance across various domains compared to existing benchmarks.

Guojun Xiong, Milind Tambe

In social impact optimization, AI decision systems often rely on solvers that optimize well-calibrated mathematical objectives. However, these solvers cannot directly accommodate evolving human preferences, typically expressed in natural language rather than formal constraints. Recent approaches address this by using large language models (LLMs) to generate new reward functions from preference descriptions. While flexible, they risk sacrificing the system's core utility guarantees. In this paper, we propose \texttt{VORTEX}, a language-guided reward shaping framework that preserves established optimization goals while adaptively incorporating human feedback. By formalizing the problem as multi-objective optimization, we use LLMs to iteratively generate shaping rewards based on verbal reinforcement and text-gradient prompt updates. This allows stakeholders to steer decision behavior via natural language without modifying solvers or specifying trade-off weights. We provide theoretical guarantees that \texttt{VORTEX} converges to Pareto-optimal trade-offs between utility and preference satisfaction. Empirical results in real-world allocation tasks demonstrate that \texttt{VORTEX} outperforms baselines in satisfying human-aligned coverage goals while maintaining high task performance. This work introduces a practical and theoretically grounded paradigm for human-AI collaborative optimization guided by natural language.

Guojun Xiong, Shufan Wang, Daniel Jiang et al.

Federated reinforcement learning (FedRL) enables multiple agents to collaboratively learn a policy without sharing their local trajectories collected during agent-environment interactions. However, in practice, the environments faced by different agents are often heterogeneous, leading to poor performance by the single policy learned by existing FedRL algorithms on individual agents. In this paper, we take a further step and introduce a \emph{personalized} FedRL framework (PFedRL) by taking advantage of possibly shared common structure among agents in heterogeneous environments. Specifically, we develop a class of PFedRL algorithms named PFedRL-Rep that learns (1) a shared feature representation collaboratively among all agents, and (2) an agent-specific weight vector personalized to its local environment. We analyze the convergence of PFedTD-Rep, a particular instance of the framework with temporal difference (TD) learning and linear representations. To the best of our knowledge, we are the first to prove a linear convergence speedup with respect to the number of agents in the PFedRL setting. To achieve this, we show that PFedTD-Rep is an example of the federated two-timescale stochastic approximation with Markovian noise. Experimental results demonstrate that PFedTD-Rep, along with an extension to the control setting based on deep Q-networks (DQN), not only improve learning in heterogeneous settings, but also provide better generalization to new environments.

Xueqing Peng, Lingfei Qian, Yan Wang et al.

Real-world financial analysis involves information across multiple languages and modalities, from reports and news to scanned filings and meeting recordings. Yet most existing evaluations of LLMs in finance remain text-only, monolingual, and largely saturated by current models. To bridge these gaps, we present MultiFinBen, the first expert-annotated multilingual (five languages) and multimodal (text, vision, audio) benchmark for evaluating LLMs in realistic financial contexts. MultiFinBen introduces two new task families: multilingual financial reasoning, which tests cross-lingual evidence integration from filings and news, and financial OCR, which extracts structured text from scanned documents containing tables and charts. Rather than aggregating all available datasets, we apply a structured, difficulty-aware selection based on advanced model performance, ensuring balanced challenge and removing redundant tasks. Evaluating 21 leading LLMs shows that even frontier multimodal models like GPT-4o achieve only 46.01% overall, stronger on vision and audio but dropping sharply in multilingual settings. These findings expose persistent limitations in multilingual, multimodal, and expert-level financial reasoning. All datasets, evaluation scripts, and leaderboards are publicly released.

Guojun Xiong, Jian Li

Restless multi-armed bandits (RMAB) play a central role in modeling sequential decision making problems under an instantaneous activation constraint that at most B arms can be activated at any decision epoch. Each restless arm is endowed with a state that evolves independently according to a Markov decision process regardless of being activated or not. In this paper, we consider the task of learning in episodic RMAB with unknown transition functions and adversarial rewards, which can change arbitrarily across episodes. Further, we consider a challenging but natural bandit feedback setting that only adversarial rewards of activated arms are revealed to the decision maker (DM). The goal of the DM is to maximize its total adversarial rewards during the learning process while the instantaneous activation constraint must be satisfied in each decision epoch. We develop a novel reinforcement learning algorithm with two key contributors: a novel biased adversarial reward estimator to deal with bandit feedback and unknown transitions, and a low-complexity index policy to satisfy the instantaneous activation constraint. We show $\tilde{\mathcal{O}}(H\sqrt{T})$ regret bound for our algorithm, where $T$ is the number of episodes and $H$ is the episode length. To our best knowledge, this is the first algorithm to ensure $\tilde{\mathcal{O}}(\sqrt{T})$ regret for adversarial RMAB in our considered challenging settings.

Lingfei Qian, Xueqing Peng, Yan Wang et al.

Although Large Language Model (LLM)-based agents are increasingly used in financial trading, it remains unclear whether they can reason and adapt in live markets, as most studies test models instead of agents, cover limited periods and assets, and rely on unverified data. To address these gaps, we introduce Agent Market Arena (AMA), the first lifelong, real-time benchmark for evaluating LLM-based trading agents across multiple markets. AMA integrates verified trading data, expert-checked news, and diverse agent architectures within a unified trading framework, enabling fair and continuous comparison under real conditions. It implements four agents, including InvestorAgent as a single-agent baseline, TradeAgent and HedgeFundAgent with different risk styles, and DeepFundAgent with memory-based reasoning, and evaluates them across GPT-4o, GPT-4.1, Claude-3.5-haiku, Claude-sonnet-4, and Gemini-2.0-flash. Live experiments on both cryptocurrency and stock markets demonstrate that agent frameworks display markedly distinct behavioral patterns, spanning from aggressive risk-taking to conservative decision-making, whereas model backbones contribute less to outcome variation. AMA thus establishes a foundation for rigorous, reproducible, and continuously evolving evaluation of financial reasoning and trading intelligence in LLM-based agents.

Yan Wang, Keyi Wang, Shanshan Yang et al.

The complexity of the Generally Accepted Accounting Principles (GAAP) and the hierarchical structure of eXtensible Business Reporting Language (XBRL) filings make financial auditing increasingly difficult to automate and verify. While large language models (LLMs) have demonstrated strong capabilities in unstructured text understanding, their ability to reason over structured, interdependent, and taxonomy-driven financial documents remains largely unexplored. To fill this gap, we introduce FinAuditing, the first taxonomy-aligned, structure-aware, multi-document benchmark for evaluating LLMs on financial auditing tasks. Built from real US-GAAP-compliant XBRL filings, FinAuditing defines three complementary subtasks, FinSM for semantic consistency, FinRE for relational consistency, and FinMR for numerical consistency, each targeting a distinct aspect of structured auditing reasoning. We further propose a unified evaluation framework integrating retrieval, classification, and reasoning metrics across these subtasks. Extensive zero-shot experiments on 13 state-of-the-art LLMs reveal that current models perform inconsistently across semantic, relational, and mathematical dimensions, with accuracy drops of up to 60-90% when reasoning over hierarchical multi-document structures. Our findings expose the systematic limitations of modern LLMs in taxonomy-grounded financial reasoning and establish FinAuditing as a foundation for developing trustworthy, structure-aware, and regulation-aligned financial intelligence systems. The benchmark dataset is available at Hugging Face.

Yan Wang, Yang Ren, Lingfei Qian et al.

Accurately understanding numbers from financial reports is fundamental to how markets, regulators, algorithms, and normal people read the economy and the world, yet even with XBRL (eXtensible Business Reporting Language) designed to tag every figure with standardized accounting concepts, mapping thousands of facts to over 10,000 U.S. GAAP concepts remains costly, inconsistent, and error-prone. Existing benchmarks define tagging as flat, single-step, extreme classification over small subsets of US-GAAP concepts, overlooking both the taxonomy's hierarchical semantics and the structured nature of real tagging, where each fact must be represented as a contextualized multi-field output. These simplifications prevent fair evaluation of large language models (LLMs) under realistic reporting conditions. To address these gaps, we introduce FinTagging, the first comprehensive benchmark for structure-aware and full-scope XBRL tagging, designed to evaluate LLMs' ability to extract and align financial facts through numerical reasoning and taxonomy alignment across text and tables. We define two subtasks: FinNI for numeric identification, which extracts numerical entities and their types from XBRL reports, and FinCL for concept linking, which maps each extracted entity to the corresponding concept in the full US-GAAP taxonomy. Together, these subtasks produce a structured representation of each financial fact. We evaluate diverse LLMs under zero-shot settings and analyze their performance across both subtasks and overall tagging accuracy. Results show that LLMs generalize well in numeric identification but struggle with fine-grained concept linking, revealing current limitations in structure-aware reasoning for accurate financial disclosure. All code and datasets are available on GitHub and Hugging Face.

Shufan Wang, Guojun Xiong, Shichen Zhang et al.

We study the data packet transmission problem (mmDPT) in dense cell-free millimeter wave (mmWave) networks, i.e., users sending data packet requests to access points (APs) via uplinks and APs transmitting requested data packets to users via downlinks. Our objective is to minimize the average delay in the system due to APs' limited service capacity and unreliable wireless channels between APs and users. This problem can be formulated as a restless multi-armed bandits problem with fairness constraint (RMAB-F). Since finding the optimal policy for RMAB-F is intractable, existing learning algorithms are computationally expensive and not suitable for practical dynamic dense mmWave networks. In this paper, we propose a structured reinforcement learning (RL) solution for mmDPT by exploiting the inherent structure encoded in RMAB-F. To achieve this, we first design a low-complexity and provably asymptotically optimal index policy for RMAB-F. Then, we leverage this structure information to develop a structured RL algorithm called mmDPT-TS, which provably achieves an \tilde{O}(\sqrt{T}) Bayesian regret. More importantly, mmDPT-TS is computation-efficient and thus amenable to practical implementation, as it fully exploits the structure of index policy for making decisions. Extensive emulation based on data collected in realistic mmWave networks demonstrate significant gains of mmDPT-TS over existing approaches.

Guojun Xiong, Shufan Wang, Jian Li et al.

We consider the problem of content caching at the wireless edge to serve a set of end users via unreliable wireless channels so as to minimize the average latency experienced by end users due to the constrained wireless edge cache capacity. We formulate this problem as a Markov decision process, or more specifically a restless multi-armed bandit problem, which is provably hard to solve. We begin by investigating a discounted counterpart, and prove that it admits an optimal policy of the threshold-type. We then show that this result also holds for average latency problem. Using this structural result, we establish the indexability of our problem, and employ the Whittle index policy to minimize average latency. Since system parameters such as content request rates and wireless channel conditions are often unknown and time-varying, we further develop a model-free reinforcement learning algorithm dubbed as Q^{+}-Whittle that relies on Whittle index policy. However, Q^{+}-Whittle requires to store the Q-function values for all state-action pairs, the number of which can be extremely large for wireless edge caching. To this end, we approximate the Q-function by a parameterized function class with a much smaller dimension, and further design a Q^{+}-Whittle algorithm with linear function approximation, which is called Q^{+}-Whittle-LFA. We provide a finite-time bound on the mean-square error of Q^{+}-Whittle-LFA. Simulation results using real traces demonstrate that Q^{+}-Whittle-LFA yields excellent empirical performance.

Guojun Xiong, Jian Li, Rahul Singh

We study a finite-horizon restless multi-armed bandit problem with multiple actions, dubbed R(MA)^2B. The state of each arm evolves according to a controlled Markov decision process (MDP), and the reward of pulling an arm depends on both the current state of the corresponding MDP and the action taken. The goal is to sequentially choose actions for arms so as to maximize the expected value of the cumulative rewards collected. Since finding the optimal policy is typically intractable, we propose a computationally appealing index policy which we call Occupancy-Measured-Reward Index Policy. Our policy is well-defined even if the underlying MDPs are not indexable. We prove that it is asymptotically optimal when the activation budget and number of arms are scaled up, while keeping their ratio as a constant. For the case when the system parameters are unknown, we develop a learning algorithm. Our learning algorithm uses the principle of optimism in the face of uncertainty and further uses a generative model in order to fully exploit the structure of Occupancy-Measured-Reward Index Policy. We call it the R(MA)^2B-UCB algorithm. As compared with the existing algorithms, R(MA)^2B-UCB performs close to an offline optimum policy, and also achieves a sub-linear regret with a low computational complexity. Experimental results show that R(MA)^2B-UCB outperforms the existing algorithms in both regret and run time.

Guojun Xiong, Gang Yan, Rahul Singh et al.

With the increasing demand for large-scale training of machine learning models, consensus-based distributed optimization methods have recently been advocated as alternatives to the popular parameter server framework. In this paradigm, each worker maintains a local estimate of the optimal parameter vector, and iteratively updates it by waiting and averaging all estimates obtained from its neighbors, and then corrects it on the basis of its local dataset. However, the synchronization phase can be time consuming due to the need to wait for \textit{stragglers}, i.e., slower workers. An efficient way to mitigate this effect is to let each worker wait only for updates from the fastest neighbors before updating its local parameter. The remaining neighbors are called \textit{backup workers.} To minimize the globally training time over the network, we propose a fully distributed algorithm to dynamically determine the number of backup workers for each worker. We show that our algorithm achieves a linear speedup for convergence (i.e., convergence performance increases linearly with respect to the number of workers). We conduct extensive experiments on MNIST and CIFAR-10 to verify our theoretical results.

Guojun Xiong, Rahul Singh, Jian Li

We consider the problem of service placement at the network edge, in which a decision maker has to choose between $N$ services to host at the edge to satisfy the demands of customers. Our goal is to design adaptive algorithms to minimize the average service delivery latency for customers. We pose the problem as a Markov decision process (MDP) in which the system state is given by describing, for each service, the number of customers that are currently waiting at the edge to obtain the service. However, solving this $N$-services MDP is computationally expensive due to the curse of dimensionality. To overcome this challenge, we show that the optimal policy for a single-service MDP has an appealing threshold structure, and derive explicitly the Whittle indices for each service as a function of the number of requests from customers based on the theory of Whittle index policy. Since request arrival and service delivery rates are usually unknown and possibly time-varying, we then develop efficient learning augmented algorithms that fully utilize the structure of optimal policies with a low learning regret. The first of these is UCB-Whittle, and relies upon the principle of optimism in the face of uncertainty. The second algorithm, Q-learning-Whittle, utilizes Q-learning iterations for each service by using a two time scale stochastic approximation. We characterize the non-asymptotic performance of UCB-Whittle by analyzing its learning regret, and also analyze the convergence properties of Q-learning-Whittle. Simulation results show that the proposed policies yield excellent empirical performance.