arXiv subjects

Milind Tambe

Publications and source records attributed to Milind Tambe.

At least 19 recordsLinked to original sources

arXiv2026

Reaching Hidden Populations: Generative Frontier Planning for Peer-Referral Recruitment

Peer-referral programs help connect populations at high risk for HIV and other infectious diseases with testing and prevention services when conventional outreach is ineffective. However, referral vouchers and incentives are limited, and standard operational guidelines give each participant the same fixed number of vouchers, ignoring differences in referral capacity. Motivated by our collaboration with public health practitioners, we study how to allocate a fixed voucher budget adaptively across participants and rounds to maximize total recruitment. Prior work assumes future recruits are i.i.d. from a population-level distribution and summarizes the recruitment frontier only by its size, ignoring covariate-dependent recruitment potential. We propose Generative Frontier Planning (GFP), which learns referral capacity with a censored count model and referrer-conditioned recruit covariates with a conditional diffusion model. Its structured value function yields a deterministic Bellman backup shared by fitted value iteration and planning, while inducing diminishing returns that give intra-round greedy allocation a (1-1/e)-approximation guarantee for each fixed round budget. Cross-round selection then determines how much budget to spend. We evaluate GFP on two data-calibrated recruitment environments constructed from de-identified recruiter-recruit records: a public ICPSR respondent-driven sampling dataset and a dataset provided by FHI 360, an international global health nonprofit. GFP recruits up to 21.5% more individuals than the strongest baseline under the same budget, showing its potential for resource-limited peer-referral programs.

cs.LG↗

arXiv2026

Continual Reinforcement Learning Is an Integration Problem

This paper presents an opinionated set of ten desiderata intended to inform the design and evaluation of reinforcement-learning agents that learn continually throughout a continuing lifetime. We use these desiderata to examine a representative selection of existing approaches. Progress on individual desiderata is valuable, but the longer-term aim should be to integrate all ten within a single agent. To our knowledge, no published evaluation has yet provided evidence for such an integration. Likewise, the representative benchmarks we review probe different parts of this target, but separate evaluations do not establish that the corresponding properties coexist within one agent throughout a continuing lifetime. As a secondary contribution, we therefore present a compact persistent-world scenario as a playable companion to the desiderata and outline a proposed benchmark that examines a broad range of associated behavioral capabilities together within one such lifetime.

cs.LG↗

arXiv2026

Coral Discovery: The Division of Cognitive Labor in Autonomous Research

A research community is only as strong as the way it divides its cognitive labour. The philosopher Philip Kitcher argued that researchers should not all pursue the most promising approach. Credit rules, not a central plan, keep some of them on other lines. We bring this question to autonomous research, where Large Language Model agents improve programs against a deterministic grader. Agents that share only a score follow the leader and converge onto one approach. Coral Discovery gives the community a direction board. A verifier labels every attempt with a direction, the mechanism earning the score, and a method, one change within it. Per direction, the board tracks how much each eval improves the score, adds an exploration bonus for little-tried directions, prices the option of opening a new direction, and suggests how many agents each direction deserves. Credit is earned against a direction's own best, so a lagging direction keeps its agents. Agents finish their lines, then treat the board as advice. We test on nine tasks with the same model and budget, without grader access except for Kernel. Coral Discovery beats the strongest open autonomous multi-agent system on 6 tasks, ties on 1, and loses on 2. Against published numbers, it is best or tied on 4. It improves the reported Kernel result from 1103 to 1095 cycles and passes 1103 at eval 275, under half of the 596 used before. It sets a new Polyominoes state of the art, 91.78 against 87.0. Direction labels show that the leading scores rest on directions a score-only community never entered. Code will be released shortly.

cs.MA↗

arXiv2026

AI-driven Prices for Externalities and Sustainability in Production Markets

Traditional competitive markets do not account for negative externalities; indirect costs that some participants impose on others, such as the cost of over-appropriating a common-pool resource (which diminishes future stock, and thus harvest, for everyone). Quantifying appropriate interventions to market prices has proven to be quite challenging. We propose a practical approach to computing market prices and allocations via a deep reinforcement learning policymaker agent, operating in an environment of other learning agents. Our policymaker allows us to tune the prices with regard to diverse objectives such as sustainability and resource wastefulness, fairness, buyers' and sellers' welfare, etc. As a highlight of our findings, our policymaker is significantly more successful in maintaining resource sustainability, compared to the market equilibrium outcome, in scarce resource environments.

cs.MA↗

arXiv2026

DiffNash: Finding Nash Equilibrium in High-Dimensional Continuous Action Spaces with Diffusion Policies

Computing equilibria in high-dimensional continuous games requires learning and representing rich, multi-modal strategy distributions, something conventional neural policies struggle to achieve. Diffusion models offer a natural solution, but standard diffusion training requires direct samples from a fixed target distribution, which are generally unavailable under iterative game-solving updates. We propose a diffusion-based framework for equilibrium computation that enables diffusion-based variants of Online Mirror Descent (OMD) and Fictitious Play (FP). Our approach derives a reweighted score-matching objective that trains diffusion policies without requiring direct samples from each updated policy. Our main method, DiffNash, combines the fast convergence of OMD with the sample efficiency of FP by reusing past actions through a replay buffer. To correct the resulting distribution shift from sample reuse, we derive an unbiased estimator of the difference between current and past policies' Evidence Lower Bounds, whose exponential provides a tractable proxy for the corresponding importance weight without evaluating diffusion likelihoods. We evaluate our approach on forest protection games and continuous Colonel Blotto games, reducing the Nash gap over the strongest baseline by 35.6% and 24.7%, respectively, with minimal hyperparameter tuning.

cs.LG↗

arXiv2026

Large Language Model Orchestration under Heterogeneous Preferences via Explicit Persona Inference

LLM orchestration investigates how an orchestrator coordinates a group of autonomous agents to achieve common goals or maximize collective welfare. The agents are typically heterogeneous, each holding a private preference that it pursues but does not reveal. Inferring such hidden preferences from behavior has been a subject of long-standing research in game theory and multi-agent systems. The core challenge lies in maintaining a belief over every agent's preference and updating it from the agents' observed actions. Existing LLM orchestrators carry that belief as prompt text with no explicit update rule. This lets early errors persist and propagate rather than be corrected. We therefore propose \textbf{HARP} (Heterogeneous-preference Agent oRchestration via Preference inference), a novel framework that moves the belief out of the prompt. Specifically, HARP maintains one numeric posterior per agent over a finite set of candidate preferences and updates it in closed form by Bayes' rule. The language model supplies only actions and per-candidate likelihoods, so estimation is decoupled from its reasoning. We prove that HARP attains the same $\tilde O(\sqrt K)$ Bayesian regret as explicit joint inference when the factorization is exact. Furthermore, HARP\textsuperscript{+} augments planning with a bonus for actions that distinguish the candidates, so inference continues even when the optimal action is uninformative. Empirical results on three substrates, ranging from payoffs the preferences fully determine, through payoffs that depend on more than them, to scales where explicit joint inference is infeasible, demonstrate that HARP\textsuperscript{+} is the strongest non-oracle method across the class our theory identifies.

cs.CL↗

arXiv2026

Many Preferences, Few Policies: Compact Portfolios for Multi-Objective LLM Alignment

Aligning large language models (LLMs) requires balancing competing objectives such as helpfulness, harmlessness, and conciseness. The appropriate balance varies across users and applications, yet training, evaluating, and deploying many policies across different reward weights is costly. We study how to identify a small portfolio of LLMs that preserves near-optimal performance across all reward weightings. We propose PALM (Portfolio of Aligned LLMs), an algorithm that combines a structured grid of weight vectors, a lazy search that optimizes policies only where needed, and pruning. Given target approximation tolerances, PALM returns a portfolio that provably contains a near-optimal policy for every weight vector, with an explicit upper bound on portfolio size. Such portfolios can support scalable personalization, reward-weight exploration during model development, and compact decoding-time configurations. Experiments show that PALM generally achieves smaller approximation gaps than same-size portfolios built from uniformly spaced or randomly sampled weights. We further demonstrate that PALM scales effectively to higher-dimensional reward spaces through efficient search and sparse preference structure.

cs.CL↗

arXiv2026

Tight Efficiency Guarantees for Strategyproof Linear Regression

We study the trade-off between squared-error accuracy and incentive compatibility in linear regression. Agents report private labels associated with publicly known features and prefer predictions close to their true labels. Ordinary least squares (OLS) need not elicit truthful reports. For regression with $d$ parameters, we design a deterministic group-strategyproof mechanism achieving a $(d+1)$-approximation to the least-squares optimum and prove optimality even among universally strategyproof randomized mechanisms, answering an open question of Chen et al. (EC 2018). Relaxing universal strategyproofness to strategyproofness in expectation reveals a sharp separation: squared individual loss retains the factor $d+1$, while absolute individual loss admits the tight ratio $2-1/(\lceil d/2\rceil+1)$.

cs.GT↗

arXiv2026

Contrasting Cost-Agnostic and Cost-Sensitive Losses under Limited Model Capacity via $\mathcal H$-consistency

There is a prevalent debate in machine learning about whether practitioners should train models to optimize a task-agnostic objective (e.g., cross entropy) or incorporate the downstream decision task into the optimization objective (e.g., weighted cross entropy). In ideal settings, like those with infinite data and infinite model capacity, the two approaches are statistically equivalent for the downstream decision task. In practice, however, incorporating the decision task into model training has been shown to empirically improve task-specific performance in certain real-world scenarios. The cause of these benefits has not been theoretically studied to date. Focusing on the setting with limited model capacity through the model class $\mathcal H$, we establish a strict performance gap between post-processing a model learned with a cost-agnostic objective (e.g., thresholding a risk score prediction) and models learned by optimizing a cost-sensitive model without a threshold search. In particular, we establish this gap when there is a hypothesis recovering the optimal decision boundary for the discrete task, but it does not align with the optimal cost-agnostic hypothesis, and give a simple example demonstrating the plausibility of this setting. With assumptions that are hard to verify in practice, we demonstrate that this gap generally exists on classification datasets from the UCI repository, particularly with very simple models.

cs.LG↗

arXiv2026

Adaptive Multi-Round Allocation with Stochastic Arrivals

We study a sequential resource allocation problem motivated by adaptive network recruitment, in which a limited budget of identical resources must be allocated over multiple rounds to individuals with stochastic referral capacity. Successful referrals endogenously generate future decision opportunities while allocating additional resources to an individual exhibits diminishing returns. We first show that the single-round allocation problem admits an exact greedy solution based on marginal survival probabilities. In the multi-round setting, the resulting Bellman recursion is intractable due to the stochastic, high-dimensional evolution of the frontier. To address this, we introduce a population-level surrogate value function that depends only on the remaining budget and frontier size. This surrogate enables an exact dynamic program via truncated probability generating functions, yielding a planning algorithm with polynomial complexity in the total budget. We further analyze robustness under model misspecification, proving a multi-round error bound that decomposes into a tight single-round frontier error and a population-level transition error. Finally, we evaluate our method on real-world inspired recruitment scenarios.

cs.AI↗

arXiv2026

Policy-Embedded Graph Expansion: Networked HIV Testing with Diffusion-Driven Network Samples

HIV is a retrovirus that attacks the human immune system and can lead to death without proper treatment. In collaboration with the WHO and the University of Witwatersrand, we study how to improve the efficiency of HIV testing with the goal of eventual deployment, directly supporting progress toward UN Sustainable Development Goal 3.3. While prior work has demonstrated the promise of intelligent algorithms for sequential, network-based HIV testing, existing approaches rely on assumptions that are impractical in our real-world implementations. Here, we study sequential testing on incrementally revealed disease networks and introduce Policy-Embedded Graph Expansion (PEGE), a novel framework that directly embeds a generative distribution over graph expansions into the decision-making policy rather than attempting explicit topological reconstruction. We further propose Dynamics-Driven Branching (DDB), a diffusion-based graph expansion model that supports decision making in PEGE and is designed for data-limited settings where forest structures arise naturally, as in our real-world referral process. Experiments on real HIV transmission networks show that the combined approach (PEGE + DDB) consistently outperforms baselines (e.g., 17.3% improvement in discounted reward and 15.4% more HIV detections with 25% of the population tested) and explore key tradeoffs that drive solution quality.

cs.SI↗

arXiv2026

Optimizing Health Coverage in Ethiopia: A Learning-augmented Approach and Persistent Proportionality Under an Online Budget

As part of nationwide efforts aligned with the United Nations' Sustainable Development Goal 3 on Universal Health Coverage, Ethiopia's Ministry of Health is strengthening health posts to expand access to essential healthcare services. However, only a fraction of this health system strengthening effort can be implemented each year due to limited budgets and other competing priorities, thus the need for an optimization framework to guide prioritization across the regions of Ethiopia. In this paper, we develop a tool, Health Access Resource Planner (HARP), based on a principled decision-support optimization framework for sequential facility planning that aims to maximize population coverage under budget uncertainty while satisfying region-specific proportionality targets at every time step. We then propose two algorithms: (i) a learning-augmented approach that improves upon expert recommendations at any single-step; and (ii) a greedy algorithm for multi-step planning, both with strong worst-case approximation estimation. In collaboration with the Ethiopian Public Health Institute and Ministry of Health, we demonstrated the empirical efficacy of our method on three regions across various planning scenarios.

cs.AI↗

arXiv2026

Reward Shaping for (Inference-Time) Alignment: A Stackelberg Game Perspective

Existing alignment methods directly use the reward model learned from user preference data to optimize an LLM policy, subject to KL regularization with respect to the base policy. This practice is suboptimal for maximizing user's utility because the KL regularization may cause the LLM to inherit the bias in the base policy that conflicts with user preferences. While amplifying rewards for preferred outputs can mitigate this bias, it also increases the risk of reward hacking. This tradeoff motivates the problem of optimally designing reward models under KL regularization. We formalize this reward model optimization problem as a Stackelberg game, and show that a simple reward shaping scheme can effectively approximate the optimal reward model. We empirically evaluate our method in inference-time alignment settings and demonstrate that it integrates seamlessly into existing alignment methods with minimal overhead. Our method consistently improves average reward and achieves win-tie rates exceeding 66% against all baselines, averaged across evaluation settings.

cs.LG↗

arXiv2026

Latent Spherical Flow Policy for Reinforcement Learning with Combinatorial Actions

Reinforcement learning (RL) with combinatorial action spaces remains challenging because feasible action sets are exponentially large and governed by complex feasibility constraints, making direct policy parameterization impractical. Existing approaches embed task-specific value functions into constrained optimization programs or learn deterministic structured policies, sacrificing generality and policy expressiveness. We propose a solver-induced \emph{latent spherical flow policy} that brings the expressiveness of modern generative policies to combinatorial RL while guaranteeing feasibility by design. Our method, LSFlow, learns a \emph{stochastic} policy in a compact continuous latent space via spherical flow matching, and delegates feasibility to a combinatorial optimization solver that maps each latent sample to a valid structured action. To improve efficiency, we train the value network directly in the latent space, avoiding repeated solver calls during policy optimization. To address the piecewise-constant and discontinuous value landscape induced by solver-based action selection, we introduce a smoothed Bellman operator that yields stable, well-defined learning targets. Empirically, our approach outperforms state-of-the-art baselines by an average of 20.6\% across a range of challenging combinatorial RL tasks.

cs.LG↗

arXiv2026

Generating Robust Portfolios of Optimization Models using Large Language Models

Mathematical optimization is a powerful tool for structured decision-making across domains such as resource allocation and planning. Formulating optimization models faithful to reality, though, remains a significant bottleneck as it typically demands both domain expertise and optimization knowledge that are often scarce. Recent advances in large language models (LLMs) promise to bridge this gap, enabling the generation of candidate optimization models from natural language descriptions. However, there is no guarantee that any single LLM-generated model is reliable, and existing approaches that output only one model are therefore risky. In this work, we propose a novel algorithm that generates a portfolio of optimization models, designed to be robust to the limitations of LLMs. Our method exploits the observation that a single LLM can play two distinct roles $\unicode{x2014}$ as a stochastic generator and as a reasoning evaluator $\unicode{x2014}$ and proposes a unified framework that leverages both capabilities in a complementary manner. We provide theoretical guarantees showing that, as long as either the generator or the evaluator is well-aligned with human preferences, the portfolio is guaranteed to contain high-quality candidates, enabling a principled human-in-the-loop process in which a decision-maker can review multiple candidates before committing to one. We further validate our approach empirically, demonstrating strong performance across a range of optimization modeling tasks.

cs.AI↗

arXiv2026

Bilevel Optimization of Synthetic Trajectories for Multi-Turn LLM Fine-Tuning

While LLMs excel at single-turn generation, they struggle with long-horizon, multi-turn interactions. Offline reinforcement learning (RL) offers a scalable approach, yet its performance hinges on the availability and quality of multi-turn trajectory data. A common remedy is to augment training with synthetic trajectories generated by LLMs or simulators, but synthetic data is highly heterogeneous in quality, and naively treating all trajectories as equally informative can degrade performance. We propose BOOST, a bilevel optimization framework where the inner level trains the LLM on reweighted data and the outer level trains a lightweight reweighting head on held-out real validation tasks, assigning continuous trajectory-level weights without requiring an external judge. To ground this approach, we derive a PAC-Bayesian bound revealing a three-way trade-off: synthetic data increases diversity but risks task-shift, while concentrating weight on high-quality trajectories improves empirical performance at the cost of effective sample size. Empirically, our method consistently outperforms multiple baselines. Analysis reveals it upweights synthetic trajectories that align with the real data distribution and exhibit higher qualitative merit.

cs.LG↗

arXiv2026

Beyond Majority Voting: LLM Aggregation by Leveraging Higher-Order Information

With the rapid progress of multi-agent large language model (LLM) reasoning, how to effectively aggregate answers from multiple LLMs has emerged as a fundamental challenge. Standard majority voting treats all answers equally, failing to consider latent heterogeneity and correlation across models. In this work, we design two new aggregation algorithms called Optimal Weight (OW) and Inverse Surprising Popularity (ISP), leveraging both first-order and second-order information. Our theoretical analysis shows these methods provably mitigate inherent limitations of majority voting under mild assumptions, leading to more reliable collective decisions. We empirically validate our algorithms on synthetic datasets, popular LLM fine-tuning benchmarks such as UltraFeedback and MMLU, and a real-world healthcare setting ARMMAN. Our algorithms consistently outperform standard baselines, establishing a robust, training-free framework for effective multi-agent LLM aggregation.

cs.LG↗

arXiv2026

Learning to Persuade a Biased Receiver

We study a repeated information design setting in which the receiver, who is also the decision-maker, updates beliefs in a systematically biased way. More specifically, a distorted posterior in our model can be written as a convex combination of the prior and the Bayesian posterior, governed by a fixed but unknown parameter. Over repeated interactions, the sender chooses persuasive signaling schemes, observes only the receiver's realized actions, and seeks to minimize regret relative to a full-information oracle that knows the receiver's biased updating rule. We propose a safe exploration algorithm for learning the receiver's bias while maintaining high persuasion value. The algorithm exploits the asymmetric cost of probing: conservative probes incur only local loss, whereas overly aggressive probes may lose the persuasive opportunity entirely. For general finite state and action spaces and arbitrary bounded utilities, our method achieves $O(\log\log T)$ regret. A matching $Ω(\log\log T)$ lower bound shows that this rate is optimal. We further discuss the influence on receiver welfare, as well as extensions to jointly unknown prior and bias, and contextual settings with time-varying priors and utilities.

cs.GT↗