arXiv subjects

Manxi Wu

Publications and source records attributed to Manxi Wu.

At least 19 recordsLinked to original sources

arXiv2026

OPENPATH: A Supervisor--Specialist Agent System for Personalized, Accessible, and Multi-stop Urban Trip Planning

Urban trip-planning systems are commonly optimized for travel time and cost, but they offer limited support for the heterogeneous needs that real travelers bring, such as personalized preferences, multi-stop itinerary construction, and end-to-end wheelchair accessibility. We present openpaths, a supervisor-specialist multi-agent system that handles all of these tasks within a single architecture. openpaths adopts a deliberate division of labor: LLM agents parse natural-language input, classify request intent, and orchestrate execution, while classical algorithms perform route optimization over curated mobility and accessibility data. This design ensures that the resulting trip honors heterogeneous user preferences and enforces strict accessibility requirements when requested. Beyond per-user planning, openpaths doubles as a measurement instrument for city-scale accessibility analysis: applied to NYC, the system reveals substantial ADA infrastructure gaps and quantifies their effect on job accessibility for wheelchair users. Overall, this study shows how a supervisor-specialist LLM agentic framework can support heterogeneous trip planning and transparent, equitable transportation analysis in real urban environments.

eess.SY↗

arXiv2026

Budget-Efficient Automatic Algorithm Design via Code Graph

Large language models (LLMs) have emerged as powerful tools for automatic algorithm design (AAD). However, existing pipelines remain inefficient. They operate at the granularity of full algorithms, redundantly rewriting recurring substructures and discarding low-fitness candidates that may contain valuable algorithmic features. We formalize budget-efficient automatic algorithm design, wherein the search policy maximizes realized fitness subject to limited computational cost. We propose a directed acyclic graph representation of algorithms and build a search framework that fully exploits the LLM's output. Instead of querying the LLM for full algorithms, we use it to obtain corrections: compact operators that add, replace, or remove code blocks. Each correction augments the graph, yielding new algorithms that compose with prior corrections. This graph structure decomposes algorithms into sets of corrections, enabling correction-level credit assignment that informs subsequent queries. We complement this framework with theoretical insights into the ideal balance between search depth and breadth at different budget levels. We validate our method empirically on three combinatorial optimization problems, demonstrating consistent superiority of our graph-based search over full-algorithm search at equal token budget. Finally, our experiments suggest that rich contexts help only when the LLM's prior knowledge is shallow, and can hinder performance otherwise.

cs.AI↗

arXiv2026

Learning to Recommend in Unknown Games

We study preference learning through recommendations in multi-agent game settings, where a moderator repeatedly interacts with agents whose utility functions are unknown. In each round, the moderator issues action recommendations and observes whether agents follow or deviate from them. We consider two canonical behavioral feedback models-best response and quantal response-and study how the information revealed by each model affects the learnability of agents' utilities. We show that under quantal-response feedback the game is learnable, up to a positive affine equivalence class, with logarithmic sample complexity in the desired precision, whereas best-response feedback can only identify a larger set of agents' utilities. We give a complete geometric characterization of this set. Moreover, we introduce a regret notion based on agents' incentives to deviate from recommendations and design an online algorithm with low regret under both feedback models, with bounds scaling linearly in the game dimension and logarithmically in time. Our results lay a theoretical foundation for AI recommendation systems in strategic multi-agent environments, where recommendation compliances are shaped by strategic interaction.

cs.GT↗

arXiv2026

Average Unfairness in Routing Games

We propose average unfairness as a new measure of fairness in routing games, defined as the ratio between the average latency and the minimum latency experienced by users. This measure is a natural complement to two existing unfairness notions: loaded unfairness, which compares maximum and minimum latencies of routes with positive flow, and user equilibrium (UE) unfairness, which compares maximum latency with the latency of a Nash equilibrium. We show that the worst-case values of all three unfairness measures coincide and are characterized by a steepness parameter intrinsic to the latency function class. We show that average unfairness is always no greater than loaded unfairness, and the two measures are equal only when the flow is fully fair. Besides that, we offer a complete comparison of the three unfairness measures, which, to the best of our knowledge, is the first theoretical analysis in this direction. Finally, we study the constrained system optimum (CSO) problem, where one seeks to minimize total latency subject to an upper bound on unfairness. We prove that, for the same tolerance level, the optimal flow under an average unfairness constraint achieves lower total latency than any flow satisfying a loaded unfairness constraint. We show that such improvement is always strict in parallel-link networks and establish sufficient conditions for general networks. We further illustrate the latter with numerical examples. Our results provide theoretical guarantees and valuable insights for evaluating fairness-efficiency tradeoffs in network routing.

cs.MA↗

arXiv2026

Game-to-Real Gap: Quantifying the Effect of Model Misspecification in Network Games

Game-theoretic models and solution concepts provide rigorous tools for predicting collective behavior in multi-agent systems. In practice, however, different agents may rely on different game-theoretic models to design their strategies. As a result, when these heterogeneous models interact, the realized outcome can deviate substantially from the outcome each agent expects based on its own local model. In this work, we introduce the game-to-real gap, a new metric that quantifies the impact of such model misspecification in multi-agent environments. The game-to-real gap is defined as the difference between the utility an agent actually obtains in the multi-agent environment (where other agents may have misspecified models) and the utility it expects under its own game model. Focusing on quadratic network games, we show that misspecifications in either (i) the external shock or (ii) the player interaction network can lead to arbitrarily large game-to-real gaps. We further develop novel network centrality measures that allow exact evaluation of this gap in quadratic network games. Our analysis reveals that standard network centrality measures fail to capture the effects of model misspecification, underscoring the need for new structural metrics that account for this limitation. Finally, through illustrative numerical experiments, we show that existing centrality measures in network games may provide a counterintuitive understanding of the impact of model misspecification.

cs.GT↗

arXiv2025

Optimal Batched Scheduling of Stochastic Processing Networks Using Atomic Action Decomposition

Stochastic processing networks (SPNs) have broad applications in healthcare, transportation, and communication networks. The control of SPN is to dynamically assign servers in batches under uncertainty to optimize long-run performance. This problem is challenging as the policy dimension grows exponentially with the number of servers, making standard reinforcement learning and policy optimization methods intractable at scale. We propose an atomic action decomposition framework that addresses this scalability challenge by breaking joint assignments into sequential single-server assignments. This yields policies with constant dimension, independent of the number of servers. We study two classes of atomic policies, the step-dependent and step-independent atomic policies, and prove that both achieve the same optimal long-run average reward as the original joint policies. These results establish that computing the optimal SPN control can be made scalable without loss of optimality using the atomic framework. Our results offer theoretical justification for the strong empirical success of the atomic framework in large-scale applications reported in previous articles.

eess.SY↗

arXiv2025

Learning with Episodic Hypothesis Testing in General Games: A Framework for Equilibrium Selection

We introduce a new hypothesis testing-based learning dynamics in which players update their strategies by combining hypothesis testing with utility-driven exploration. In this dynamics, each player forms beliefs about opponents' strategies and episodically tests these beliefs using empirical observations. Beliefs are resampled either when the hypothesis test is rejected or through exploration, where the probability of exploration decreases with the player's (transformed) utility. In general finite normal-form games, we show that the learning process converges to a set of approximate Nash equilibria and, more importantly, to a refinement that selects equilibria maximizing the minimum (transformed) utility across all players. Our result establishes convergence to equilibrium in general finite games and reveals a novel mechanism for equilibrium selection induced by the structure of the learning dynamics.

cs.GT↗

arXiv2025

Atomic Proximal Policy Optimization for Electric Robo-Taxi Dispatch and Charger Allocation

Pioneering companies such as Waymo have deployed robo-taxi services in several U.S. cities. These robo-taxis are electric vehicles, and their operations require the joint optimization of ride matching, vehicle repositioning, and charging scheduling in a stochastic environment. We model the operations of the ride-hailing system with robo-taxis as a discrete-time, average-reward Markov Decision Process with an infinite horizon. As the fleet size grows, dispatching becomes challenging, as both the system state space and the fleet dispatching action space grow exponentially with the number of vehicles. To address this, we introduce a scalable deep reinforcement learning algorithm, called Atomic Proximal Policy Optimization (Atomic-PPO), that reduces the action space using atomic action decomposition. We evaluate our algorithm using real-world NYC for-hire vehicle trip records and measure its performance by the long-run average reward achieved by the dispatching policy, relative to a fluid-based upper bound. Our experiments demonstrate the superior performance of Atomic-PPO compared to benchmark methods. Furthermore, we conduct extensive numerical experiments to analyze the efficient allocation of charging facilities and assess the impact of vehicle range and charger speed on system performance.

cs.AI↗

arXiv2024

Congestion Pricing for Efficiency and Equity: Theory and Applications to the San Francisco Bay Area

Congestion pricing, while adopted by many cities to alleviate traffic congestion, raises concerns about widening socioeconomic disparities due to its disproportionate impact on low-income travelers. We address this concern by proposing a new class of congestion pricing schemes that not only minimize total travel time, but also incorporate an equity objective, reducing disparities in the relative change in travel costs across populations with different incomes, following the implementation of tolls. Our analysis builds on a congestion game model with heterogeneous traveler populations. We present four pricing schemes that account for practical considerations, such as the ability to charge differentiated tolls to various traveler populations and the option to toll all or only a subset of edges in the network. We evaluate our pricing schemes in the calibrated freeway network of the San Francisco Bay Area. We demonstrate that the proposed congestion pricing schemes improve both the total travel time and the equity objective compared to the current pricing scheme. Our results further show that pricing schemes charging differentiated prices to traveler populations with varying value-of-time lead to a more equitable distribution of travel costs compared to those that charge a homogeneous price to all.

cs.GT↗

arXiv2024

Convergence of Decentralized Actor-Critic Algorithm in General-sum Markov Games

Markov games provide a powerful framework for modeling strategic multi-agent interactions in dynamic environments. Traditionally, convergence properties of decentralized learning algorithms in these settings have been established only for special cases, such as Markov zero-sum and potential games, which do not fully capture real-world interactions. In this paper, we address this gap by studying the asymptotic properties of learning algorithms in general-sum Markov games. In particular, we focus on a decentralized algorithm where each agent adopts an actor-critic learning dynamic with asynchronous step sizes. This decentralized approach enables agents to operate independently, without requiring knowledge of others' strategies or payoffs. We introduce the concept of a Markov Near-Potential Function (MNPF) and demonstrate that it serves as an approximate Lyapunov function for the policy updates in the decentralized learning dynamics, which allows us to characterize the convergent set of strategies. We further strengthen our result under specific regularity conditions and with finite Nash equilibria.

cs.MA↗

arXiv2024

Bounding the Price-of-Fair-Sharing using Knapsack-Cover Constraints to guide Near-Optimal Cost-Recovery Algorithms

We consider the problem of fairly allocating the cost of providing a service among a set of users, where the service cost is formulated by an NP-hard {\it covering integer program (CIP)}. The central issue is to determine a cost allocation to each user that, in total, recovers as much as possible of the actual cost while satisfying a stabilizing condition known as the {\it core property}. The ratio between the total service cost and the cost recovered from users has been studied previously, with seminal papers of Deng, Ibaraki, \& Nagomochi and Goemans \& Skutella linking this {\it price-of-fair-sharing} to the integrality gap of an associated LP relaxation. Motivated by an application of cost allocation for network design for LPWANs, an emerging IoT technology, we investigate a general class of CIPs and give the first non-trivial price-of-fair-sharing bounds by using the natural LP relaxation strengthened with knapsack-cover inequalities. Furthermore, we demonstrate that these LP-based methods outperform previously known methods on an LPWAN-derived CIP data set. We also obtain analogous results for a more general setting in which the service provider also gets to select the subset of users, and the mechanism to elicit users' private utilities should be group-strategyproof. The key to obtaining this result is a simplified and improved analysis for a cross-monotone cost-allocation mechanism.

cs.GT↗

arXiv2024

Designing High-Occupancy Toll Lanes: A Game-Theoretic Analysis

In this article, we study the optimal design of High Occupancy Toll (HOT) lanes. The traffic authority determines the road capacity allocation between HOT lanes and ordinary lanes, as well as the toll price charged for travelers using HOT lanes who do not meet the high-occupancy eligibility criteria. We develop a game-theoretic model to analyze the decisions of travelers with heterogeneous preference parameters in values of time and carpool disutilities. These travelers choose between paying or forming carpools to use the HOT lanes, or taking the ordinary lanes. Travelers' welfare depends on the congestion cost of the lane they use, the toll payment, and the carpool disutilities. For highways with a single entrance and exit node, we provide a complete characterization of equilibrium strategies and a comparative statics analysis of how the equilibrium vehicle flow and travel time change with HOT capacity and toll price. We then extend the single segment model to highways with multiple entrance and exit nodes. We extend the equilibrium concept and propose various design objectives considering traffic congestion, toll revenue, and social welfare. Using the data collected from the HOT lane of the California Interstate Highway 880 (I-880), we formulate a convex program to estimate the travel demand and approximate the distribution of travelers' preference parameters. We then compute the optimal toll design of five segments for I-880 for achieve each one of the four objectives, and compare the optimal solution with the current toll pricing.

cs.GT↗

arXiv2024

Adaptive Incentive Design with Learning Agents

We propose an adaptive incentive mechanism that learns the optimal incentives in environments where players continuously update their strategies. Our mechanism updates incentives based on each player's externality, defined as the difference between the player's marginal cost and the operator's marginal cost at each time step. The proposed mechanism updates the incentives on a slower timescale compared to the players' learning dynamics, resulting in a two-timescale coupled dynamical system. Notably, this mechanism is agnostic to the specific learning dynamics used by players to update their strategies. We show that any fixed point of this adaptive incentive mechanism corresponds to the optimal incentive mechanism, ensuring that the Nash equilibrium coincides with the socially optimal strategy. Additionally, we provide sufficient conditions under which the adaptive mechanism converges to a fixed point. Our results apply to both atomic and non-atomic games. To demonstrate the effectiveness of our proposed mechanism, we verify the convergence conditions in two practically relevant classes of games: atomic aggregative games and non-atomic routing games.

cs.GT↗

arXiv2023

Network Flow Problems with Electric Vehicles

Electric vehicle (EV) adoption in long-distance logistics faces challenges such as range anxiety and uneven distribution of charging stations. Two pivotal questions emerge: How can EVs be efficiently routed in a charging network considering range limits, charging speeds and prices? And, can the existing charging infrastructure sustain the increasing demand for EVs in long-distance logistics? This paper addresses these questions by introducing a novel theoretical and computational framework to study the EV network flow problems. We present an EV network flow model that incorporates range constraints and nonlinear charging rates, and identify conditions under which polynomial-time solutions can be obtained for optimal single EV routing, maximum flow, and minimum-cost flow problems. Our findings provide insights for optimizing EV routing in logistics, ensuring an efficient and sustainable future.

cs.DS↗

arXiv2023

Convergence and Stability of Coupled Belief--Strategy Learning Dynamics in Continuous Games

We propose a learning dynamics to model how strategic agents repeatedly play a continuous game while relying on an information platform to learn an unknown payoff-relevant parameter. In each time step, the platform updates a belief estimate of the parameter based on players' strategies and realized payoffs using Bayes's rule. Then, players adopt a generic learning rule to adjust their strategies based on the updated belief. We present results on the convergence of beliefs and strategies and the properties of convergent fixed points of the dynamics. We obtain sufficient and necessary conditions for the existence of globally stable fixed points. We also provide sufficient conditions for the local stability of fixed points. These results provide an approach to analyzing the long-term outcomes that arise from the interplay between Bayesian belief learning and strategy learning in games, and enable us to characterize conditions under which learning leads to a complete information equilibrium.

cs.MA↗

arXiv2023

Information Design for Spatial Resource Allocation

In this paper, we study platforms where resources and jobs are spatially distributed, and resources have the flexibility to strategically move to different locations for better payoffs. The price of the service at each location depends on the number of resources present and the market size, which is modeled as a random state. Our focus is on how the platform can utilize information about the underlying state to influence resource repositioning decisions and ultimately increase commission revenues. We establish that in many practically relevant settings a simple monotone partitional information disclosure policy is optimal. This policy reveals state realizations below a threshold and above a second (higher) threshold, and pools all states in between and maps them to a unique signal realization. We also provide algorithmic approaches for obtaining (near-)optimal information structures that are monotone partitional in general settings.

cs.GT↗

arXiv2023

Market Design for Capacity Sharing in Networks

We study a market mechanism that sets edge prices to incentivize strategic agents to efficiently share limited network capacity. In this market, agents form coalitions, with each coalition sharing a unit capacity of a selected route and making payments to cover edge prices. Our focus is on the existence and computation of market equilibrium, where challenges arise from the interdependence between coalition formation among strategic agents with heterogeneous preferences and route selection that induces a network flow under integral capacity constraints. To address this interplay between coalition formation and network capacity utilization, we introduce a novel approach based on combinatorial auction theory and network flow theory. We establish sufficient conditions on the network topology and agents' preferences that guarantee both the existence and polynomial-time computation of a market equilibrium. Additionally, we identify a particular market equilibrium that maximizes utilities for all agents and the outcome is equivalent to the classical Vickrey-Clarke-Groves mechanism. Furthermore, we extend our results to multi-period settings and general networks, showing that when the sufficient conditions are not met, an equilibrium may still exist but requires more complex, path-based pricing mechanisms that set differentiated prices based on agents' preference parameters.

cs.GT↗

arXiv2023

Markov $\alpha$-Potential Games

We propose a new framework of Markov $\alpha$-potential games to study Markov games. We show that any Markov game with finite-state and finite-action is a Markov $\alpha$-potential game, and establish the existence of an associated $\alpha$-potential function. Any optimizer of an $\alpha$-potential function is shown to be an $\alpha$-stationary Nash equilibrium. We study two important classes of practically significant Markov games, Markov congestion games and the perturbed Markov team games, via the framework of Markov $\alpha$-potential games, with explicit characterization of an upper bound for $\alpha$ and its relation to game parameters. Additionally, we provide a semi-infinite linear programming based formulation to obtain an upper bound for $\alpha$ for any Markov game. Furthermore, we study two equilibrium approximation algorithms, namely the projected gradient-ascent algorithm and the sequential maximum improvement algorithm, along with their Nash regret analysis, and corroborate the results with numerical experiments.

cs.GT↗