This annotated reading list surveys emerging works at the intersection of information design and large language models (LLMs). While classical information design theory studies signaling in abstract mathematical models, real-world communication often occurs in natural language. We highlight papers that use LLMs to elicit and communicate information through natural-language messages, cover techniques used in "information design + LLM" research such as language-space optimization and LLM proxies, and discuss papers on LLM persuasion. We aim to illustrate the potential of LLMs to bridge the gap between the theory and practice of information design.

Modern prediction markets face two limitations that restrict their applicability in a range of settings: (i) they reveal what the crowd believes but not the evidence or reasoning behind those beliefs, and (ii) they require an event with an external ground truth that resolves at a known future date. We address these twin challenges by introducing evidence markets, a generalization of prediction markets that incentivizes the submission of evidence alongside beliefs and can be endogenously resolved using the crowd-sourced evidence if external resolution is not possible. At its core, the market uses a logarithmic market scoring rule whose liquidity parameter changes dynamically with the accumulated evidence quality. We prove that platform loss is bounded, evidence is rewarded proportional to the current market uncertainty, and can be equivalently implemented through an automated market maker. In the case where the marker resolves endogenously based on submitted evidence, we characterize how withholding evidence shifts a trader's belief about resolution and use it to prove truthful belief and evidence reporting is a always an ε-dominant strategy incentive compatible (DSIC) strategy. To address operational considerations, we propose evidence verification via an LLM-as-a-Judge framework with staking and give an asynchronous execution algorithm that is not bottle-necked by verification. Throughout the work, we use LLM evaluations – determining which model is best for a given task – as a salient and representative running example for our proposed market.

Coincident Peak (CP) pricing is widely used in U.S. electricity markets to allocate capacity and transmission costs. This paper develops a behavioral game-theoretic framework for CP-driven load shifting that couples a nonlinear cost-allocation model with day-ahead (one-shot) and real-time (sequential-learning) decision processes. We examine two update rules, namely best-response dynamics (BRD) and fictitious-play dynamics (FPD), across continuous and finite action spaces to quantify how flexibility, action resolution, and participation influence peak outcomes. Using ERCOT peak-day data, we find that FPD reliably reduces system peaks, whereas BRD is more variable and can increase peaks under tight-capacity conditions. Finer action resolution improves peak shaving, while the number of participants is largely neutral when aggregate flexibility is fixed. Meanwhile, information-provider signals can induce herding, whereas response-aware or diverse signals improve peak shaving. These results highlight both the potential and limits of CP pricing: smoothing information and enabling granular control are as important as the amount of available flexibility. The framework offers practical guidance for system operators and consumers: For ISOs, broadcasting smoothed CP signals and setting minimum controllable-capacity thresholds enhance coordination. For consumers, greater flexibility and finer control resolution improve both cost savings and peak-shaving performance.

We study the problem of learning the utility functions of no-regret learning agents in a repeated normal-form game. Differing from most prior literature, we introduce a principal with the power to observe the agents playing the game, send agents signals, and give agents *payments* as a function of their actions. We show that the principal can, using a number of rounds polynomial in the size of the game, learn the utility functions of all agents to any desired precision $\varepsilon > 0$, for any no-regret learning algorithms of the agents. Our main technique is to formulate a zero-sum game between the principal and the agents, where the principal's strategy space is the set of all payment functions. Finally, we discuss implications for the problem of *steering* agents to a desired equilibrium: in particular, we introduce, using our utility-learning algorithm as a subroutine, the first algorithm for steering arbitrary no-regret learning agents without prior knowledge of their utilities.

This paper studies the design of optimal proper scoring rules when the principal has partial knowledge of an agent's signal distribution. Recent work characterizes the proper scoring rules that maximize the increase of an agent's payoff when the agent chooses to access a costly signal to refine a posterior belief from her prior prediction, under the assumption that the agent's signal distribution is fully known to the principal. In our setting, the principal only knows about a set of distributions where the agent's signal distribution belongs. We formulate the scoring rule design problem as a max-min optimization that maximizes the worst-case increase in payoff across the set of distributions. We propose an efficient algorithm to compute an optimal scoring rule when the set of distributions is finite, and devise a fully polynomial-time approximation scheme that accommodates various infinite sets of distributions. We further remark that widely used scoring rules, such as the quadratic and log rules, as well as previously identified optimal scoring rules under full knowledge, can be far from optimal in our partial knowledge settings.

Mechanisms for continued self-improvement of language models without external supervision remain an open challenge. We propose Peer-Predictive Self-Training (PST), a label-free fine-tuning framework in which multiple language models improve collaboratively by leveraging a cross-model aggregated response as an internal training signal. Given a prompt question, the models generate responses sequentially; the final aggregated answer, often more reliable than individual responses in practice, serves as an internal target for learning. We measure how informative each intermediate response is about the aggregate using pointwise mutual information (PMI), and use this signal to scale self-training updates. Responses already aligned with the aggregate are updated less, while less informative or misaligned responses are updated more. On mathematical reasoning benchmarks (SimulEq, Math500, and MultiArith), PST improves exact-match accuracy by 2.2 to 4.3 percentage points across Gemma-2-2B, LLaMA-3.2-1B, and Qwen-2.5-1.5B, and reduces the average generator-verifier gap (GV-Gap) by 26 to 40 percent, while requiring no external supervision or teacher-student hierarchy and relying solely on cross-model interactions. These results suggest that cross-model generations and peer-predictive feedback can serve as an effective approach for self-supervised training.

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(loglog T) regret. A matching Ω(loglog 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.

We study repeated contextual procurement auctions in which the platform must learn context-dependent product values from bandit feedback. We give an exactly truthful explore-then-commit mechanism with O((ng)^1/3T^2/3) regret. We also give a frozen-payment UCB mechanism with a regret-incentive tradeoff: the near-UCB tuning attains O(√(ngT)) welfare regret, while for fixed n,g its total incentive error is O(T^3/4); the balanced tuning gives O(T^2/3) on both scales. Regret is measured as welfare loss relative to the full-information efficient allocation. We prove a matching lower bound for the frozen-payment regret-incentive tradeoff.

This paper reports two approaches to forecasting replicability for a corpus of 3000 published social science papers, using large-scale human assessments. Replication Markets used incentivized surveys and prediction markets where participants traded assets linked to replication outcomes and market prices were interpreted as replication predictions. The repliCATS project used a structured group deliberation protocol, including interactive discussion, and mathematically aggregated forecasts to generate replication predictions. Accuracy for both approaches was validated against a subset of (n=37) independent, high-power replication studies. The predictive accuracy (median [range]) achieved for AUC by Replication Markets was 0.76 [0.72-0.82], and 0.76 [0.68-0.81] by repliCATS. Replication Markets achieved a classification accuracy of 73% [68-76%] and repliCATS achieved 68% [59-78%]. These results place the performance of both teams within the accuracy range achieved in prior replication forecasting studies. We conclude that informative forecasts can be elicited by both methods, but there are trade-offs between scale and accuracy.

Automated methods for the assessment of replicability of scientific claims offer a scalable complement to replication studies and traditional peer review. Drawing on a large dataset of claims, human judgments, and a limited set of replication outcomes, we developed and evaluated three distinct artificial intelligence systems designed to predict human expert assessments of replicability using diverse methodologies—including synthetic prediction markets, interpretable feature-based modeling, knowledge graph reasoning, and semantic parsing with argument structures. While these systems achieved modest calibration to human judgment distributions, they failed to discriminate between replicable and non-replicable claims. Our findings suggest that while machine assessments of research replicability may complement human reasoning, their current performance limitations and opportunities for bias demand careful evaluation before real-world application.

In this paper, we study a generalization of Markov games and pseudo-games that we call Markov pseudo-games, which, like the former, captures time and uncertainty, and like the latter, allows for the players' actions to determine the set of actions available to the other players. In the same vein as Arrow and Debreu, we intend for this model to be rich enough to encapsulate a broad mathematical framework for modeling economies. We then prove the existence of a game-theoretic equilibrium in our model, which in turn implies the existence of a general equilibrium in the corresponding economies. Finally, going beyond Arrow and Debreu, we introduce a solution method for Markov pseudo-games and prove its polynomial-time convergence. We then provide an application of Markov pseudo-games to infinite-horizon Markov exchange economies, a stochastic economic model that extends Radner's stochastic exchange economy and Magill and Quinzii's infinite-horizon incomplete markets model. We show that under suitable assumptions, the solutions of any infinite-horizon Markov exchange economy (i.e., recursive Radner equilibria -- RRE) can be formulated as the solution to a concave Markov pseudo-game, thus establishing the existence of RRE and providing first-order methods for approximating RRE. Finally, we demonstrate the effectiveness of our approach in practice by building the corresponding generative adversarial policy neural network and using it to compute RRE in a variety of infinite-horizon Markov exchange economies.

We propose a new variant of the strategic classification problem: a principal reveals a classifier, and $n$ agents report their (possibly manipulated) features to be classified. Motivated by real-world applications, our model crucially allows the manipulation of one agent to affect another; that is, it explicitly captures inter-agent externalities. The principal-agent interactions are formally modeled as a Stackelberg game, with the resulting agent manipulation dynamics captured as a simultaneous game. We show that under certain assumptions, the pure Nash Equilibrium of this agent manipulation game is unique and can be efficiently computed. Leveraging this result, PAC learning guarantees are established for the learner: informally, we show that it is possible to learn classifiers that minimize loss on the distribution, even when a random number of agents are manipulating their way to a pure Nash Equilibrium. We also comment on the optimization of such classifiers through gradient-based approaches. This work sets the theoretical foundations for a more realistic analysis of classifiers that are robust against multiple strategic actors interacting in a common environment.

We examine hypothesis testing within a principal-agent framework, where a strategic agent, holding private beliefs about the effectiveness of a product, submits data to a principal who decides on approval. The principal employs a hypothesis testing rule, aiming to pick a p-value threshold that balances false positives and false negatives while anticipating the agent's incentive to maximize expected profitability. Building on prior work, we develop a game-theoretic model that captures how the agent's participation and reporting behavior respond to the principal's statistical decision rule. Despite the complexity of the interaction, we show that the principal's errors exhibit clear monotonic behavior when segmented by an efficiently computable critical p-value threshold, leading to an interpretable characterization of their optimal p-value threshold. We empirically validate our model and these insights using publicly available data on drug approvals. Overall, our work offers a comprehensive perspective on strategic interactions within the hypothesis testing framework, providing technical and regulatory insights.

Common sense suggests that when individuals explain why they believe something, we can arrive at more accurate conclusions than when they simply state what they believe. Yet, there is no known mechanism that provides incentives to elicit explanations for beliefs from agents. This likely stems from the fact that standard Bayesian models make assumptions (like conditional independence of signals) that preempt the need for explanations, in order to show efficient information aggregation. A natural justification for the value of explanations is that agents' beliefs tend to be drawn from overlapping sources of information, so agents' belief reports do not reveal all that needs to be known. Indeed, this work argues that rationales-explanations of an agent's private information-lead to more efficient aggregation by allowing agents to efficiently identify what information they share and what information is new. Building on this model of rationales, we present a novel 'deliberation mechanism' to elicit rationales from agents in which truthful reporting of beliefs and rationales is a perfect Bayesian equilibrium.

Competitions are widely used to identify top performers in judgmental forecasting and machine learning, and the standard competition design ranks competitors based on their cumulative scores against a set of realized outcomes or held-out labels. However, this standard design is neither incentive-compatible nor very statistically efficient. The main culprit is noise in outcomes/labels that experts are scored against; it allows weaker competitors to often win by chance, and the winner-take-all nature incentivizes misreporting that improves win probability even if it decreases expected score. Attempts to achieve incentive-compatibility rely on randomized mechanisms that add even more noise in winner selection, but come at the cost of determinism and practical adoption. To tackle these issues, we introduce a novel deterministic mechanism: WOMAC (Wisdom of the Most Accurate Crowd). Instead of scoring experts against noisy outcomes, as is standard, WOMAC scores experts against the best ex-post aggregate of peer experts' predictions given the noisy outcomes. WOMAC is also more efficient than the standard competition design in typical settings. While the increased complexity of WOMAC makes it challenging to analyze incentives directly, we provide a clear theoretical foundation to justify the mechanism. We also provide an efficient vectorized implementation and demonstrate empirically on real-world forecasting datasets that WOMAC is a more reliable predictor of experts' out-of-sample performance relative to the standard mechanism. WOMAC is useful in any competition where there is substantial noise in the outcomes/labels.

How can we assess the reliability of a dataset without access to ground truth? We introduce the problem of reliability scoring for datasets collected from potentially strategic sources. The true data are unobserved, but we see outcomes of an unknown statistical experiment that depends on them. To benchmark reliability, we define ground-truth-based orderings that capture how much reported data deviate from the truth. We then propose the Gram determinant score, which measures the volume spanned by vectors describing the empirical distribution of the observed data and experiment outcomes. We show that this score preserves several ground-truth based reliability orderings and, uniquely up to scaling, yields the same reliability ranking of datasets regardless of the experiment -- a property we term experiment agnosticism. Experiments on synthetic noise models, CIFAR-10 embeddings, and real employment data demonstrate that the Gram determinant score effectively captures data quality across diverse observation processes.

Analyses of voting algorithms often overlook informational externalities shaping individual votes. For example, pre-polling information often skews voters towards candidates who may not be their top choice, but who they believe would be a worthwhile recipient of their vote. In this work, we aim to understand the role of external information in voting outcomes. We study this by analyzing (1) the probability that voting outcomes align with external information, and (2) the effect of external information on the total utility across voters, or social welfare. In practice, voting mechanisms elicit coarse information about voter utilities, such as ordinal preferences, which initially prevents us from directly analyzing the effect of informational externalities with standard voting mechanisms. To overcome this, we present an intermediary mechanism for learning how preferences change with external information which does not require eliciting full cardinal preferences. With this tool in hand, we find that voting mechanisms are generally more likely to select the alternative most favored by the external information, and when external information reflects the population's true preferences, social welfare increases in expectation.

Generalized principal-agent problems, including Stackelberg games, contract design, and Bayesian persuasion, are a class of economic problems where an agent best responds to a principal's committed strategy. We study repeated generalized principal-agent problems under the assumption that the principal does not have commitment power and the agent uses algorithms to learn to respond to the principal. We reduce this problem to a one-shot generalized principal-agent problem where the agent approximately best responds. Using this reduction, we show that: (1) if the agent uses contextual no-regret learning algorithms with regret $\mathrm{Reg}(T)$, then the principal can guarantee utility at least $U^* - \Theta\big(\sqrt{\tfrac{\mathrm{Reg}(T)}{T}}\big)$, where $U^*$ is the principal's optimal utility in the classic model with a best-responding agent.(2) If the agent uses contextual no-swap-regret learning algorithms with swap-regret $\mathrm{SReg}(T)$, then the principal cannot obtain utility more than $U^* + O(\frac{\mathrm{SReg(T)}}{T})$. But (3) if the agent uses mean-based learning algorithms (which can be no-regret but not no-swap-regret), then the principal can sometimes do significantly better than $U^*$.These results not only refine previous results in Stackelberg games and contract design, but also lead to new results for Bayesian persuasion with a learning agent and all generalized principal-agent problems where the agent does not have private information.

Prediction markets elicit and aggregate beliefs by paying agents based on how close their predictions are to a verifiable future outcome. However, outcomes of many important questions are difficult to verify or unverifiable, in that the ground truth may be hard or impossible to access. Examples include questions about causal effects where it is infeasible or unethical to run randomized trials; crowdsourcing and content moderation tasks where it is prohibitively expensive to verify ground truth; and questions asked over long time horizons, where the delay until the realization of the outcome skews agents' incentives to report their true beliefs. We present a novel and unintuitive result showing that it is possible to run an $\varepsilon-$incentive compatible prediction market to elicit and efficiently aggregate information from a pool of agents without observing the outcome by paying agents the negative cross-entropy between their prediction and that of a carefully chosen reference agent. Our key insight is that a reference agent with access to more information can serve as a reasonable proxy for the ground truth. We use this insight to propose self-resolving prediction markets that terminate with some probability after every report and pay all but a few agents based on the final prediction. We show that it is an $\varepsilon-$Perfect Bayesian Equilibrium for all agents to report truthfully in our mechanism and to believe that all other agents report truthfully. Although primarily of interest for unverifiable outcomes, this design is also applicable for verifiable outcomes.

The optimal signaling schemes in information design (Bayesian persuasion) problems often involve non-explainable randomization or disconnected partitions of state space, which are too intricate to be audited or communicated. We propose explainable information design in the context of information design with a continuous state space, restricting the information designer to use K-partitional signaling schemes defined by deterministic and monotone partitions of the state space, where a unique signal is sent for all states in each part. We first prove that the price of explainability (PoE) – the ratio between the performances of the optimal explainable signaling scheme and unrestricted signaling scheme – is exactly 1/2 in the worst case, meaning that partitional signaling schemes are never worse than arbitrary signaling schemes by a factor of 2. We then study the complexity of computing optimal explainable signaling schemes. We show that the exact optimization problem is NP-hard in general. But for Lipschitz utility functions, an ε-approximately optimal explainable signaling scheme can be computed in polynomial time. And for piecewise constant utility functions, we provide an efficient algorithm to find an explainable signaling scheme that provides a 1/2 approximation to the optimal unrestricted signaling scheme, which matches the worst-case PoE bound. A technical tool we develop is a conversion from any optimal signaling scheme (which satisfies a bi-pooling property) to a partitional signaling scheme that achieves 1/2 fraction of the expected utility of the former. We use this tool in the proofs of both our PoE result and algorithmic result.