Agricultural regions in rural areas face damage from climate-related risks, including droughts, heavy rainfall, and shifting weather patterns. Prior research calls for adaptive risk-management solutions and decision-making strategies. To this end, artificial intelligence (AI), particularly agentic AI, offers a promising path forward. Agentic AI systems consist of autonomous, specialized agents capable of solving complex, dynamic tasks. While past systems have relied on single-agent models or have used multi-agent frameworks only for static functions, there is a growing need for architectures that support dynamic collaborative reasoning and context-aware outputs. To bridge this gap, we present AgroAskAI, a multi-agent reasoning system for climate adaptation decision support in agriculture, with a focus on vulnerable rural communities. AgroAskAI features a modular, role-specialized architecture that uses a chain-of-responsibility approach to coordinate autonomous agents, integrating real-time tools and datasets. The system has built-in governance mechanisms that mitigate hallucination and enable internal feedback for coherent, locally relevant strategies. The system also supports multilingual interactions, making it accessible to non-English-speaking farmers. Experiments on common agricultural queries related to climate adaptation show that, with additional tools and prompt refinement, AgroAskAI delivers more actionable, grounded, and inclusive outputs. Our experimental results highlight the potential of agentic AI for sustainable and accountable decision support in climate adaptation for agriculture.

In 2020, maternal mortality in India was estimated to be as high as 130 deaths per 100K live births, nearly twice the UN's target. To improve health outcomes, the non-profit ARMMAN sends automated voice messages to expecting and new mothers across India. However, 38% of mothers stop listening to these calls, missing critical preventative care information. To improve engagement, ARMMAN employs health workers to intervene by making service calls, but workers can only call a fraction of the 100K enrolled mothers. Partnering with ARMMAN, we model the problem of allocating limited interventions across mothers as a restless multi-armed bandit (RMAB), where the realities of large scale and model uncertainty present key new technical challenges. We address these with GROUPS, a double oracle–based algorithm for robust planning in RMABs with scalable grouped arms. Robustness over grouped arms requires several methodological advances. First, to adversarially select stochastic group dynamics, we develop a new method to optimize Whittle indices over transition probability intervals. Second, to learn group-level RMAB policy best responses to these adversarial environments, we introduce a weighted index heuristic. Third, we prove a key theoretical result that planning over grouped arms achieves the same minimax regret--optimal strategy as planning over individual arms, under a technical condition. Finally, using real-world data from ARMMAN, we show that GROUPS produces robust policies that reduce minimax regret by up to 50%, halving the number of preventable missed voice messages to connect more mothers with life-saving maternal health information.

Improving health equity is an urgent task for our society. The advent of mobile clinics plays an important role in enhancing health equity, as they can provide easier access to preventive healthcare for patients from disadvantaged populations. For effective functioning of mobile clinics, accurate prediction of demand (expected number of individuals visiting mobile clinic) is the key to their daily operations and staff/resource allocation. Despite its importance, there have been very limited studies on predicting demand of mobile clinics. To the best of our knowledge, we are among the first to explore this area, using AI-based techniques. A crucial challenge in this task is that there are no known existing data sources from which we can extract useful information to account for the exogenous factors that may affect the demand, while considering protection of client privacy. We propose a novel methodology that completely uses public data sources to extract the features, with several new components that are designed to improve the prediction. Empirical evaluation on a real-world dataset from the mobile clinic The Family Van shows that, by leveraging publicly available data (which introduces no extra monetary cost to the mobile clinics), our AI-based method achieves 26.4% - 51.8% lower Root Mean Squared Error (RMSE) than the historical average-based estimation (which is presently employed by mobile clinics like The Family Van). Our algorithm makes it possible for mobile clinics to plan proactively, rather than reactively, as what has been doing.

Preventing poaching through ranger patrols protects endangered wildlife, directly contributing to the UN Sustainable Development Goal 15 of life on land. Combinatorial bandits have been used to allocate limited patrol resources, but existing approaches overlook the fact that each location is home to multiple species in varying proportions, so a patrol benefits each species to differing degrees. When some species are more vulnerable, we ought to offer more protection to these animals; unfortunately, existing combinatorial bandit approaches do not offer a way to prioritize important species. To bridge this gap, (1) We propose a novel combinatorial bandit objective that trades off between reward maximization and also accounts for prioritization over species, which we call ranked prioritization. We show this objective can be expressed as a weighted linear sum of Lipschitz-continuous reward functions. (2) We provide RankedCUCB, an algorithm to select combinatorial actions that optimize our prioritization-based objective, and prove that it achieves asymptotic no-regret. (3) We demonstrate empirically that RankedCUCB leads to up to 38% improvement in outcomes for endangered species using real-world wildlife conservation data. Along with adapting to other challenges such as preventing illegal logging and overfishing, our no-regret algorithm addresses the general combinatorial bandit problem with a weighted linear objective.

We introduce robustness in \textit{restless multi-armed bandits} (RMABs), a popular model for constrained resource allocation among independent stochastic processes (arms). Nearly all RMAB techniques assume stochastic dynamics are precisely known. However, in many real-world settings, dynamics are estimated with significant uncertainty, e.g., via historical data, which can lead to bad outcomes if ignored. To address this, we develop an algorithm to compute minimax regret–robust policies for RMABs. Our approach uses a double oracle framework (oracles for \textit{agent} and \textit{nature}), which is often used for single-process robust planning but requires significant new techniques to accommodate the combinatorial nature of RMABs. Specifically, we design a deep reinforcement learning (RL) algorithm, DDLPO, which tackles the combinatorial challenge by learning an auxiliary “$\lambda$-network” in tandem with policy networks per arm, greatly reducing sample complexity, with guarantees on convergence. DDLPO, of general interest, implements our reward-maximizing agent oracle. We then tackle the challenging regret-maximizing nature oracle, a non-stationary RL challenge, by formulating it as a multi-agent RL problem between a policy optimizer and adversarial nature. This formulation is of general interest—we solve it for RMABs by creating a multi-agent extension of DDLPO with a shared critic. We show our approaches work well in three experimental domains.

Many online platforms today (such as Amazon, Netflix, Spotify, LinkedIn, and AirBnB) can be thought of as two-sided markets with producers and customers of goods and services. Traditionally, recommendation services in these platforms have focused on maximizing customer satisfaction by tailoring the results according to the personalized preferences of individual customers. However, our investigation reinforces the fact that such customer-centric design of these services may lead to unfair distribution of exposure to the producers, which may adversely impact their well-being. However, a pure producer-centric design might become unfair to the customers. As more and more people are depending on such platforms to earn a living, it is important to ensure fairness to both producers and customers. In this work, by mapping a fair personalized recommendation problem to a constrained version of the problem of fairly allocating indivisible goods, we propose to provide fairness guarantees for both sides. Formally, our proposed FairRec algorithm guarantees Maxi-Min Share of exposure for the producers, and Envy-Free up to One Item fairness for the customers. Extensive evaluations over multiple real-world datasets show the effectiveness of FairRec in ensuring two-sided fairness while incurring a marginal loss in overall recommendation quality. Finally, we present a modification of FairRec (named as FairRecPlus ) that at the cost of additional computation time, improves the recommendation performance for the customers, while maintaining the same fairness guarantees.

Prior probability shift is a phenomenon where the training and test datasets differ structurally within population subgroups. This phenomenon can be observed in the yearly records of several real-world datasets, for example, recidivism records and medical expenditure surveys. If unaccounted for, such shifts can cause the predictions of a classifier to become unfair towards specific population subgroups. While the fairness notion called Proportional Equality (PE) accounts for such shifts, a procedure to ensure PE-fairness was unknown. In this work, we design an algorithm, called CAPE, that ensures fair classification under such shifts. We introduce a metric, called prevalence difference, which CAPE attempts to minimize in order to achieve fairness under prior probability shifts. We theoretically establish that this metric exhibits several properties that are desirable for a fair classifier. We evaluate the efficacy of CAPE via a thorough empirical evaluation on synthetic datasets. We also compare the performance of CAPE with several state-of-the-art fair classifiers on real-world datasets like COMPAS (criminal risk assessment) and MEPS (medical expenditure panel survey). The results indicate that CAPE ensures a high degree of PE-fairness in its predictions, while performing well on other important metrics.

In many public health settings, it is important for patients to adhere to health programs, such as taking medications and periodic health checks. Unfortunately, beneficiaries may gradually disengage from such programs, which is detrimental to their health. A concrete example of gradual disengagement has been observed by an organization that carries out a free automated call-based program for spreading preventive care information among pregnant women. Many women stop picking up calls after being enrolled for a few months. To avoid such disengagements, it is important to provide timely interventions. Such interventions are often expensive and can be provided to only a small fraction of the beneficiaries. We model this scenario as a restless multi-armed bandit (RMAB) problem, where each beneficiary is assumed to transition from one state to another depending on the intervention. Moreover, since the transition probabilities are unknown a priori, we propose a Whittle index based Q-Learning mechanism and show that it converges to the optimal solution. Our method improves over existing learning-based methods for RMABs on multiple benchmarks from literature and also on the maternal healthcare dataset.

Multi-action restless multi-armed bandits (RMABs) are a powerful framework for constrained resource allocation in which N independent processes are managed. However, previous work only study the offline setting where problem dynamics are known. We address this restrictive assumption, designing the first algorithms for learning good policies for Multi-action RMABs online using combinations of Lagrangian relaxation and Q-learning. Our first approach, MAIQL, extends a method for Q-learning the Whittle index in binary-action RMABs to the multi-action setting. We derive a generalized update rule and convergence proof and establish that, under standard assumptions, MAIQL converges to the asymptotically optimal multi-action RMAB policy as t → ∞. However, MAIQL relies on learning Q-functions and indexes on two timescales which leads to slow convergence and requires problem structure to perform well. Thus, we design a second algorithm, LPQL, which learns the well-performing and more general Lagrange policy for multi-action RMABs by learning to minimize the Lagrange bound through a variant of Q-learning. To ensure fast convergence, we take an approximation strategy that enables learning on a single timescale, then give a guarantee relating the approximation's precision to an upper bound of LPQL's return as t → ∞. Finally, we show that our approaches always outperform baselines across multiple settings, including one derived from real-world medication adherence data.

Fairness and bias in automated decision-making gain importance as the prevalence of algorithms increases in different areas of social life. This paper contributes to the discussion of algorithmic fairness with a crowdsourced vignette survey on recidivism risk assessment, which we compare to previous studies on this topic and to predictions of an automated recidivism risk tool. We use the case of the Correctional Offender Management Profiling for Alternative Sanctions (COMPAS) and the Broward County dataset of pre-trial defendants as a data source and for purposes of comparability with the earlier analysis. In our survey, each respondent assessed recidivism risk for a set of vignettes describing real defendants, where each set was balanced with regard to the defendants' race and re-offender status. The survey ensured a 50: 50 ratio of black and white respondents. We found that predictions in our survey---while less accurate---were considerably more fair in terms of equalized odds than previous surveys. We attribute it to the differences in survey design: using the balanced set of vignettes and not providing feedback after responding to each vignette. We also analyzed the performance and fairness of predictions by race of respondent and defendant. We found that both white and black respondents tend to favor defendants of their own race, but the magnitude of the effect is relatively small. In addition to the survey, we train two statistical models, one trained with balanced data and other with unbalanced data. We observe that the model trained on balanced data is substantially more fair and possess less in-group bias.

We investigate the problem of fair recommendation in the context of two-sided online platforms, comprising customers on one side and producers on the other. Traditionally, recommendation services in these platforms have focused on maximizing customer satisfaction by tailoring the results according to the personalized preferences of individual customers. However, our investigation reveals that such customer-centric design may lead to unfair distribution of exposure among the producers, which may adversely impact their well-being. On the other hand, a producer-centric design might become unfair to the customers. Thus, we consider fairness issues that span both customers and producers. Our approach involves a novel mapping of the fair recommendation problem to a constrained version of the problem of fairly allocating indivisible goods. Our proposed FairRec algorithm guarantees at least Maximin Share (MMS) of exposure for most of the producers and Envy-Free up to One Good (EF1) fairness for every customer. Extensive evaluations over multiple real-world datasets show the effectiveness of FairRec in ensuring two-sided fairness while incurring a marginal loss in the overall recommendation quality.

Concurrency bugs are notoriously hard to detect and reproduce. Controlled concurrency testing (CCT) techniques aim to offer a solution, where a scheduler explores the space of possible interleavings of a concurrent program looking for bugs. Since the set of possible interleavings is typically very large, these schedulers employ heuristics that prioritize the search to “interesting” subspaces. However, current heuristics are typically tuned to specific bug patterns, which limits their effectiveness in practice. In this paper, we present QL, a learning-based CCT framework where the likelihood of an action being selected by the scheduler is influenced by earlier explorations. We leverage the classical Q-learning algorithm to explore the space of possible interleavings, allowing the exploration to adapt to the program under test, unlike previous techniques. We have implemented and evaluated QL on a set of microbenchmarks, complex protocols, as well as production cloud services. In our experiments, we found QL to consistently outperform the state-of-the-art in CCT.

We consider the problem of allocating a set of indivisible goods among a group of homogeneous agents under matroid constraints and additive valuations, in a fair manner. We propose a novel algorithm that computes a fair allocation for instances with additive and identical valuations, even under matroid constraints. Our result provides a computational anchor to the existential result of the fairness notion, called EF1 (envy-free up to one good) by Biswas and Barman in this setting. We further provide examples to show that the fairness notions stronger than EF1 does not always exist in this setting.

We study the problem of allocating indivisible goods among n agents in a fair manner. For this problem, maximin share (MMS) is a well-studied solution concept which provides a fairness threshold. Specifically, maximin share is defined as the minimum utility that an agent can guarantee for herself when asked to partition the set of goods into n bundles such that the remaining (n-1) agents pick their bundles adversarially. An allocation is deemed to be fair if every agent gets a bundle whose valuation is at least her maximin share. Even though maximin shares provide a natural benchmark for fairness, it has its own drawbacks and, in particular, it is not sufficient to rule out unsatisfactory allocations. Motivated by these considerations, in this work we define a stronger notion of fairness, called groupwise maximin share guarantee (GMMS). In GMMS, we require that the maximin share guarantee is achieved not just with respect to the grand bundle, but also among all the subgroups of agents. Hence, this solution concept strengthens MMS and provides an ex-post fairness guarantee. We show that in specific settings, GMMS allocations always exist. We also establish the existence of approximate GMMS allocations under additive valuations, and develop a polynomial-time algorithm to find such allocations. Moreover, we establish a scale of fairness wherein we show that GMMS implies approximate envy freeness. Finally, we empirically demonstrate the existence of GMMS allocations in a large set of randomly generated instances. For the same set of instances, we additionally show that our algorithm achieves an approximation factor better than the established, worst-case bound.

We consider the problem of fairly allocating indivisible goods, among agents, under cardinality constraints and additive valuations. In this setting, we are given a partition of the entire set of goods---i.e., the goods are categorized---and a limit is specified on the number of goods that can be allocated from each category to any agent. The objective here is to find a fair allocation in which the subset of goods assigned to any agent satisfies the given cardinality constraints. This problem naturally captures a number of resource-allocation applications, and is a generalization of the well-studied unconstrained fair division problem. The two central notions of fairness, in the context of fair division of indivisible goods, are envy freeness up to one good (EF1) and the (approximate) maximin share guarantee (MMS). We show that the existence and algorithmic guarantees established for these solution concepts in the unconstrained setting can essentially be achieved under cardinality constraints. Furthermore, focusing on the case wherein all the agents have the same additive valuation, we establish that EF1 allocations exist even under matroid constraints.

A key challenge in participatory sensing systems has been the design of incentive mechanisms that motivate individuals to contribute data to consuming applications. Emerging trends in urban development and smart city planning indicate the use of citizen reports to gather insights and identify areas for transformation. Consumers of these reports (e.g. city agencies) typically associate non-uniform utility (or values) to different reports based on the spatio-temporal context of the reports. For example, a report indicating traffic congestion near an airport, in early morning hours, would tend to have much higher utility than a similar report from a sparse residential area. In such cases, the design of an incentive mechanism must motivate participants, via appropriate rewards (or payments), to provide higher utility reports when compared to less valued ones. The main challenge in designing such an incentive scheme is two-fold: (i) lack of prior knowledge of participants in terms of their availability (i.e. who are in the vicinity) and reporting behaviour (i.e. what are the rewards expected); and (ii) minimizing payments to the reporters while ensuring that the desired number of reports are collected. In this paper, we propose STOC-PISCES, an algorithm that guarantees a stochastic optimal solution in the generalized setting of an unknown set of participants, with non-deterministic availabilities and stochastically rational reporting behaviour. The superior performance of STOC-PISCES in experimental settings, based on real-world data, endorses its adoption as an incentive strategy in participatory sensing applications like smart city management.