Sequential Decision Making

Discrete choice model specification is a time-consuming task in which modellers often specify and estimate multiple models while balancing goodness-of-fit, parsimony, and behavioural plausibility. We present Delphos, a multitask reinforcement learning framework that learns transferable specification strategies across transport choice datasets. Delphos frames model specification as a sequential decision-making problem in which it applies a sequence of modelling actions and receives feedback from an estimation environment based on model performance and convergence. To transfer modelling decisions across datasets with different sets of variables, Delphos represents utility specifications as sets of modelling terms using a DeepSet-Q architecture, allowing a shared specification policy to learn across multiple datasets. Trained on nine transport choice datasets, Delphos consistently outperforms independently trained single-task agents, indicating that sharing modelling experience improves learning efficiency and helps identify promising sequences of modelling decisions with fewer unsuccessful estimation attempts. When applied without further training to the unseen Swissmetro and Decisions datasets, the same agent identifies competitive specifications in less than 20 minutes on a standard CPU. It achieves a higher log-likelihood per observation than the VNS metaheuristic on Swissmetro and performance comparable to a published MNL specification developed by expert modellers on Decisions. These findings show that accumulating and reusing modelling experience enables Delphos to function as an intelligent assistant for discrete choice model specification. It reduces manual trial-and-error while allowing modellers to retain control over model diagnosis, refinement, and final selection.

Decentralized bandit systems often contain heterogeneous agents: rewards can change at individual agents even when the best action for the network stays the same. These local changes may cancel when rewards are averaged across agents, so the number of local changes $\Stloc$ can be much larger than the number of changes in the best common arm $\Stdec$. We introduce Decision-Relevant Fresh Comparison (DRFC), which uses new, balanced samples from all agents to compare arms at the network level and switches only when fresh global evidence indicates that the common best arm has changed. We prove a high-probability dynamic regret bound with no adaptation term depending on $\Stloc$, and show that every algorithm must still pay for identifying genuine decision switches and propagating them through the communication graph. Under a distinct time-average benchmark, an anytime-valid sliding-window extension handles gradual drift; experiments on synthetic, semi-real, and MovieLens-1M replays show that DRFC ignores decision-irrelevant local changes while the extension avoids false switches.

Sequential deliberation is a mechanism for collective decision making: at each round, a uniformly randomly selected pair is asked to revise a collective outcome, which then becomes the reference point for the next round. Existing theory by Fain et al.~\cite{fain2017sequential} treats the current outcome solely as the disagreement alternative in bargaining. Yet an existing draft, policy, or proposal might carry social influence and anchor participants' expressed positions toward the status quo. We introduce anchored sequential deliberation on a one-dimensional decision space. In each round, two participants with bliss points $U$ and $V$ shift their positions toward the previous outcome $O_{t-1}$ with anchoring strength $λ$, then Nash-bargain using $O_{t-1}$ as the disagreement alternative. The update simplifies to $O_t=(1-λ)\mathsf{Median}\{U,V,O_{t-1}\}+λO_{t-1}$. We establish a convergence--stability trade-off. For every population distribution and $λ<1$, the process has a unique stationary distribution. A monotone coupling yields a $1$-Wasserstein contraction factor of at most $\frac{1+λ}{2}$ and at least $λ$; thus, stronger anchoring slows mixing. On the other hand, stationary social cost weakly decreases with $λ$, although the worst-case distortion remains $\frac{1+\sqrt{2}}{2}$. We also identify a unique \emph{deliberative fixed point}, where the expected unanchored movement is zero, and prove that the stationary distribution concentrates around it as $λ\to 1$. For the uniform population, stationary distortion lies between $1+\frac{1-λ}{9+7λ}$ and $1+\frac{1-λ}{6(1+λ)}$, with both bounds approaching $1$ as $λ\to1$. Simulations for uniform and Beta populations show that stronger anchoring slows mixing, concentrates the stationary distribution, and lowers stationary distortion in these instances.

LLM agents for sequential decision tasks are often post-trained with trajectory-level outcome labels, but such labels provide little supervision for preserving multiple successful branches from the same decision state. We study this problem as successful strategy coverage: how broadly a model realizes distinct successful strategies under a fixed rollout budget. We present Direct Diversity Optimization (DDO), an offline post-training method that combines Divergence-Tree Collection (DTC) with the Reference-Relative Target-Odds Objective (RTO). DTC constructs state-aligned branch sets rooted at shared decision states, and RTO trains the model to match reference-relative targets over successful alternatives. DDO achieves the strongest task success and successful strategy coverage among the compared post-training methods across BabyAI, BabaIsAI, and WebShop. It also achieves the highest recovery rate after local action replacement and higher task success and coverage than successful-only imitation and decoding-time diversification controls.

AI agents increasingly gather evidence, invoke tools, apply constraints, and produce decisions that people or software may commit to action. A final output alone cannot show which evidence, tool state, rule, authorization, or action path produced it. We present DNative-Twin, a graph-native digital twin that records a committed agentic decision as a typed trajectory and re-executes its decision mechanism under declared conditions. The graph links the state observed by the agent, the path it followed, and the authority behind the resulting action. The twin synchronizes this information, replays the mechanism in isolation, and compares it under controlled changes. We instantiate the framework in enterprise decision processes using three public process logs and controlled replay suites. The experiments identify a specific failure: graph structure localizes represented changes but cannot determine the consequence of an unobserved tool state. In a three-condition controlled experiment with 300 injected instances, unresolved-divergence recall increased from 0 to 0.667 when replay-contract state was added and to 1.0 when verification results were also available; the held-out set contained no critical-class instance. Across 500--5,000 BPI 2020 cases, median end-to-end time increased from 0.794 to 8.889 seconds on the reported platform. These results separate the roles of graph structure, replay context, and verification evidence in reviewing a decision mechanism.

Large language model agents can plan, invoke tools, and modify external states, yet most systems still take an explicit user instruction as a fixed starting point. Proactive service moves the decision upstream: an agent must infer service opportunities from incomplete environmental and user signals, choose among remaining silent, asking, assisting, and acting, and account for interruption, misunderstanding, overreach, and privacy costs. This survey gives an operational definition centered on initiative and formulates the problem as a partially observable sequential decision process constrained by authorization and risk. The formulation represents timing, content, and delivery within one structured action, while making explicit the option value of waiting, the decision value of questions, and feedback-induced state changes. On this basis, we organize existing methods along one decision pipeline (state and need estimation, intervention gating, action construction, and feedback adaptation) and describe prescribed, predictive, model based, and return optimizing mechanisms as nonexclusive policy-construction components. We further normalize decision units and three-axis evidence descriptors across streaming dialogue, screen, video, software-engineering, and human-agent collaboration resources, and formalize metrics for triggering, timing, calibration, user burden, safety, and policy value. The synthesis shows why offline classification performance alone does not predict deployment benefit and why long-term memory is not a defining condition of proactivity. Reliable proactive service instead requires calibrated incremental intervention value, verifiable authorization, recoverable execution, and counterfactual evidence.

No single optimization method is uniformly best for all problems, and the most suitable optimizer choice can change during a run. Existing approaches that change optimizer during execution typically predetermine part of the strategy: the portfolio is restricted to one algorithm class, the switch occurs once at a fixed time, or the frequency of decisions is treated as a hyperparameter rather than a learned one. We introduce "Reinforcement Learning to Choose Optimizers", which formulates the optimization algorithm choice as a sequential decision-making problem. At each decision, a recurrent policy reads the current run state and decides both which optimizer should be used next and for how long. The portfolio includes both gradient-based and derivative-free optimizers, and each switch passes on the current best solution and a representative step size. A context proxy conditions a gating network over expert heads, and training employs a decoupled actor-critic whose return is expressed in the same empirical runtime distribution metric used at evaluation. Training tasks and portfolio are designed jointly so that no optimizer dominates. On unseen problems, the learned policy outperforms every portfolio optimizer at all but the smallest budgets, and it remains robust under distribution shift.

Bilevel optimization provides a natural modeling language for hierarchical decision problems. However, applying existing numerical solvers usually requires substantial manual analysis and reformulation. In this paper, we introduce disciplined bilevel programming (DBLP), a symbolic framework that allows users to specify and solve optimistic bilevel problems in a high-level, human-readable way that is close to the mathematical formulation. For problems with a disciplined nonlinear upper problem and a convex lower problem satisfying the disciplined parameterized programming rules, DBLP automatically canonicalizes the lower problem into conic form and constructs an equivalent single-level reformulation using the conic Karush-Kuhn-Tucker conditions. We relax the resulting complementarity constraint and use a gap continuation procedure to approximately solve a sequence of smooth nonlinear problems. We implement DBLP in the open-source Python package BLVPY, an extension of CVXPY for bilevel programming. We demonstrate the modeling and solution capabilities of BLVPY on a range of bilevel optimization problems from several application domains. The proposed framework and implementation allow users to specify and solve bilevel optimization problems within a few lines of code, without prior expertise in bilevel modeling and numerical optimization.

We consider the problem of sequential prediction of an $m$-ary sequence, where at each epoch, (i) the environment selects an outcome from an $m$-ary alphabet, (ii) the learner selects a probability distribution over the same alphabet (unaware of the outcome generated by the environment), and finally, (iii) the learner incurs a cost that depends on the probability assigned to the outcome. The cost function we consider captures the complexity of predicting the outcome generated by the environment, in a scenario where the aforementioned prediction is performed via comparative queries to a lying oracle. We consider both stochastic and adversarial environments, propose algorithms for both settings, and establish logarithmic upper bounds on their regret.

Many operational decisions are sequences of interventions under a cumulative resource limit, such as a maintenance schedule within a crew-hour budget. Choosing among them calls for the outcome and the cumulative cost each would produce, counterfactual quantities identified from observational data. Two strategies with the same expected cost can exceed the budget at very different rates, so constraining the mean does not bound how often an overrun occurs. Prior two-step architectures, recently extended to continuous doses, constrain the mean cost rather than its tail and allocate at a single decision point. Methods that do bound a cost tail take its distribution from a specified model rather than identifying it from data. We present a predict-then-optimize framework. In the prediction step, any estimator returning an outcome value and a cost distribution supplies what the decision rule consumes, so the predictor is interchangeable. In the optimization step, a chance-constrained selection over a finite candidate set bounds the probability that the cumulative cost exceeds the budget. That tail does not decompose across stages, so each strategy is scored whole. Sweeping the tolerated violation probability traces a safety-utility frontier, and distribution-free finite-sample bounds cover violation and outcome shortfall. Four of five environments, spanning clinical treatment and equipment maintenance, supply exact counterfactual ground truth; the fifth carries real outcomes from a digital-health micro-randomized trial. Across them, the rule holds the budget where a point-estimate rule overruns it, at an outcome cost the frontier makes explicit. All code is available at https://github.com/mfriendly/counterfactual-chance-selection

This paper proposes a novel learning-based approach to approximately solve instances of mixed-integer optimization problems. These problems are computationally challenging, as they require jointly determining discrete and continuous decisions while satisfying complex combinatorial constraints. The proposed method relies on a graph-based generative diffusion model that learns the discrete component of mixed-integer optimization problems while integrating a training-free feasibility projection operator directly into the reverse diffusion process to steer intermediate samples toward the feasible set throughout generation. Once the discrete decisions are generated, the remaining optimization reduces to a continuous problem that can be solved efficiently (relative to the original problem) using existing numerical methods. The resulting framework named Constrained Graph Diffusion (CGD), is problem-agnostic and can accommodate a broad class of mixed-integer optimization problems through suitable projection operators. We evaluate CGD on optimal transmission switching for ACOPF and discrete portfolio optimization, demonstrating substantial improvements in feasibility and solution quality over learning-based baselines while achieving speedups of up to $425\times$ over state-of-the-art numerical solvers for MINLPs.

In sequential decision making, an agent typically observes its environment and acts at every timestep. However, such active participation may not always be necessary; tasks such as brewing coffee include periods that are served equally well by letting the environment evolve without constant monitoring and control. During such periods, the agent could simply wait to conserve its resources, or redirect its attention to another task. We capitalize on these opportunities by training a "waiting policy" that decides where and how long to wait. This involves forgoing sensing to commit to a wait action, representing a deliberate pause for a set number of timesteps. We formalize "learning to wait" as minimizing the frequency of sensing and decision making without sacrificing task performance (e.g., the total amount of time to complete a task). To train a waiting policy, we propose an approach that employs reinforcement learning with lexicographically ordered objectives. In experiments across 4 discrete-state household tasks and 3 continuous-state environments, we show that our approach successfully learns waiting behaviors, and can adapt pre-trained policies to wait where appropriate. While different tasks permit different amounts of waiting without sacrificing task performance, our approach consistently finds solutions with significant waiting, sometimes waiting for over 50 percent of the task duration.

Reliability qualification of advanced semiconductor devices requires sequential stress decisions that balance characterization objectives against multiple competing failure mechanisms. Current practice relies on static test plans derived from population-level acceleration models, which cannot adapt to per-unit variability or real-time degradation observations. This paper presents a closed-loop adaptive test planning framework that formulates reliability qualification as a partially observable sequential decision problem and solves it using Monte Carlo tree search for seed-action simulators (MCTS-SA) coupled with extended Kalman filter (EKF) belief-state estimation. The framework models stochastic, per-device variability in bias temperature instability (BTI), electromigration (EM), and time-dependent dielectric breakdown (TDDB), and treats stress selection as a constrained sequential optimization, i.e., to maximize the probability of successful degradation characterization while respecting catastrophic failure constraints. Under the experimental assumptions used here (discrete stress actions, proxy damage observability, and cumulative degradation without recovery), we believe this to be a novel application of tree-search-based adaptive test planning to multi-mechanism reliability qualification. Across 5,000 planning iterations, the characterization yield (CY) improves from 20% in the first 500 iterations to over 54% in the final 500, with 39% cumulative success, while the best successful test sequence terminates with EM and TDDB damage fractions DEM=0.564 and DTDDB=0.537, well within safety margins. These results demonstrate that sequential Bayesian planning can synthesize damage-aware test policies that significantly outperform non-adaptive strategies for reliability qualification under competing failure modes.

This note aims to serve as an entry point to the literature on learning in games, a topic with significant theoretical appeal and a wide range of applications -- from machine learning and data science to economics and beyond. Our presentation is structured around two complementary viewpoints: We first consider a single agent -- the learner -- engaged in a sequential decision process in an unknown, non-stationary, and possibly adversarial environment. We then examine what happens when the environment is shaped by the decisions of several interacting agents, not necessarily aware of each other's actions or goals, and all seeking to improve their individual rewards. In this general context, we examine a family of regularized learning policies based on best-responding to the past history of play, up to a regularization penalty intended to encourage exploration and prevent over-commitment to suboptimal choices. In the single-agent setting, we present some basic regret bounds for regularized learning in adversarial multi-armed bandits; in the multi-agent setting, we describe an ergodic equilibrium convergence result for zero-sum games in the spirit of classical results on fictitious play, as well as a "folk theorem" linking strategic and dynamic notions of stability -- Nash equilibria and attracting points of regularized learning, respectively. We pay special attention to the information available to the players and, through a unified analysis framework, we study both oracle- and payoff-based (bandit) methods. Our goal is to provide a coherent and comprehensible -- albeit, by necessity, not comprehensive -- account of some recent ideas in the field, and to discuss their implications for the study of rationality.

This paper proposes the Bayesian Expected Uncertainty Reduction (B-EUR) model, which formalizes the value of trying a candidate design action as its expected reduction of epistemic uncertainty about action--outcome relations. The model addresses one part of the Uncertainty Driven Action (UDA) model's open question concerning how changes in uncertainty perception determine action selection. We examine two environmental properties: generalizability, or how far knowledge from one trial extends to neighboring candidates, and outcome discriminability, or how clearly differences among outcomes can be distinguished. We tested the model through simulations and human experiments using a graph-shape guessing task that isolates learning about action--outcome relations under a limited trial budget. Epistemic value followed an inverted-U-shaped relationship with generalizability and increased with outcome discriminability in the simulations. In the human experiments, the subjective value of trying and enjoyment followed inverted-U-shaped relationships with generalizability, while choice behavior reflected both properties. The B-EUR model provides a computational account of candidate-action evaluation within uncertainty-driven design activity and offers implications for constructing prototype sets, framing design problems, and organizing feedback to support informative exploration.

When a student must learn concepts connected by prerequisite dependencies, when does the order of instruction matter, and what does it cost to find the best one? We study instructional sequencing as a stochastic shortest-path problem in which attempting a concept succeeds with a state-dependent probability and failure leaves the learner state unchanged. We first prove that this stochasticity can be eliminated exactly: the problem collapses to a deterministic shortest-path problem on the lattice of prerequisite order ideals, preserving optimal values and actions. The collapse removes stochastic complexity but not combinatorial complexity: optimal sequencing remains NP-hard -- via reduction from feedback arc set in tournaments -- even with no prerequisite edges, unit costs, uniform binary nonnegative transfer, and success probabilities at least $1/2$. Hardness is not uniform: when realizable transfer preferences remain jointly acyclic with the prerequisites, any topological order of the residual joint graph is optimal, and fixed prerequisite width yields polynomial-time exact dynamic programming. A computable diagnostic, $mΔ$, bounds the value of sequencing before optimization. On 70,893 interactions from an introductory CS course, the diagnostic certifies a doubly easy regime -- little value to optimize and little space to search -- while constructed transfer instances realize the challenging regime, where myopic sequencing suffers large regret yet exact A* with a consistent heuristic expands only linearly many states on that family.

Large Language Models (LLMs) have recently shown strong capabilities in reasoning, planning, and tool-use, enabling new forms of autonomous agents. However, LLM-based agents struggle with long-horizon sequential decision tasks that require precise action optimization and environment interaction. Reinforcement Learning (RL), while effective for sequential control, often lacks the high-level abstraction and task decomposition abilities needed for complex scenarios. This paper introduces an LLM-Augmented Reinforcement Learning Agent that integrates LLM-driven planning with RL-based action optimization. The proposed architecture leverages the LLM to generate subgoals, structured plans, and contextual guidance, while the RL agent refines low-level actions through interaction with the environment. Experiments on sequential decision tasks demonstrate improved sample efficiency, higher success rates, and more coherent action trajectories compared to RL-only and LLM-only baselines. This hybrid paradigm highlights a promising direction for building more capable autonomous systems.

Large language models have improved substantially on single-shot reasoning tasks, but their performance in sequential decision-making is less well understood. We study this on fully-observable two-player zero-sum games, which provide ground-truth evaluation: outcomes are determined by the rules, and optimality of individual moves can be computed or approximated, without relying on a judge model. Across model tiers, LLMs play suboptimally in simple games such as tic-tac-toe or Connect Four, and lose to MCTS opponents. Obfuscations that preserve the game tree but rewrite its surface form leave performance largely unchanged, indicating the gap is not fully explained by recall of memorized strategies. Motivated by this performance gap, we introduce an agentic framework enhanced with an experience memory designed for the sequential setting and addressing common challenges of sequential decision-making such as credit assignment. We show that post-game reflection and rule extraction yield measurable improvements on tic-tac-toe without modifying the model weights.

Sequential decision-making in real-world applications often involves uncertainty about the environment's model. Uncertain Markov decision processes (UMDPs) represent the possible environments as a set of MDPs with shared states and actions but potentially different transition probabilities and rewards. Optimizing a single policy across all possible MDPs may sacrifice performance, while preparing an individually optimized policy for every MDP may violate operational, regulatory, or interpretability constraints on the number of policies that can be prepared and deployed. We consider settings in which model uncertainty is resolved shortly before execution, allowing the most suitable policy to be selected from a limited set prepared in advance. We introduce $k$-adaptable policy synthesis, which optimizes such a set of $k$ policies under a minimax-regret objective. We prove that the problem is NP-hard and develop KAPS, an exact nested branch-and-bound algorithm with problem-specific bounds and heuristics. KAPS jointly optimizes which MDPs share a policy and the policies themselves. Experiments across various UMDP benchmarks show that the largest reduction in regret consistently occurs when increasing from one to two policies. In the single-policy setting, KAPS is competitive with existing methods in solution quality and proves optimality substantially more often.

LLM now pass medical licensing examinations and, in curated cases, can rival physicians at diagnostic reasoning. These developments have accelerated the use of LLMs for symptom assessment and clinical decision support in diagnostic and treatment guidance, administrative documentation, and rules-based alert enhancement. This Perspective concerns the most consequential of these applications: the autonomous triage of self-presenting, undifferentiated patients, with little or no clinician in the loop. For that task, the evidence of safety does not yet exist. The gap is not in medical knowledge but in the fidelity of clinical evaluation: a model optimized to continue the most probable text is not optimized to act safely when the safe answer is the improbable must-not-miss diagnosis. Safe triage is not the selection of the most likely diagnosis; it is a sequential decision under asymmetric cost, in which the single catastrophic miss outweighs many false alarms, and the decisive signal may be one the patient has not volunteered - and that the model has not been trained to seek. The core deficit is therefore one of information gathering under uncertainty. Under incomplete histories, LLM systems may fail to show the behaviors safe triage requires: broadening the differential; seeking the missing red flag; lowering the threshold for escalation; deferring judgement until sufficient information is obtained; and escalating concern where high-harm diagnoses remain unexcluded. These modes of failure for LLMs can be difficult to detect considering that evaluations to date often use complete, well-curated, confidence-gated simulations. The application of LLMs under these conditions may be amplified by assistant-like behaviors and positive bias, including credulity, agreeableness, and miscalibration - when these are not constrained by clinical triage logic.

As humans, we face many decisions that require us to choose between sticking to something and giving up. This thesis uses algorithmic tools to derive insights about such decision-making problems in theoretical models, studying both near-optimal methods and outcomes of social and behavioral influences. Along the way, this thesis sheds light on what we gain and what we lose as we move from a messy and complex real world setting to a very general abstract model by studying various points along this spectrum. In Part I, we study algorithms for sequential decision-making in the improving multi-armed bandits problem. We provide nearly matching upper and lower bounds in the general case. Then, we then ask what is possible if we have access to similar instances to the one we wish to deploy our algorithm on. To that end, we provide guarantees in the data-driven algorithm design framework, showing that a polynomial number of samples is sufficient for learning good algorithms from a class of algorithms. In Part II, we study algorithmic approaches for problems in social epistemology. We start by analyzing what role theoretical models can play in the study of social problems. We then study social and behavioral influences in decision-making requiring investment. First, we provide mathematical formalism in which to study the formation of pessimism traps, a phenomenon identified by philosophers in which agents are influenced by their predecessors to engage in less-ambitious goals. We develop financial interventions to sustainably shift communities out of these traps. The second problem we study is the influence of grit as a behavioral trait in ambitious decision-making. Overall, these works seek to theoretically model phenomena in social epistemology and provide a framework for intervening algorithmically.

We study finite-horizon MDP planning under \emph{root-based} (resolute) risk objectives that apply a rank-dependent functional to the distribution of total returns. Such objectives are non-linear in the return distribution and generally break Bellman optimality, so direct optimization by scenario-tree enumeration is intractable. We propose \textbf{ERQDP}, an enumeration-free and sampling-free method that solves a rank--quantile surrogate via exact DP (Dynamic Programming), evaluates candidate policies exactly by DP over return Probability Mass Functions (PMFs) on a discretized return grid (with an explicit rounding bound), and refines the surrogate in an anytime loop that reports an explicit upper--lower gap (certificate) for the target objective up to discretization budgets. Across tested benchmarks, ERQDP returns certified solutions or explicit residual gaps, enables fast risk-parameter sweeps with substantial runtime gains, and supports both risk-averse and risk-seeking behaviors.

Sequential decision making in non-stationary and partially observable environments requires rapid adaptation to latent regime changes. However, existing Transformer decision models face a structural bottleneck in the retrieval mechanism: even when reward is used for training or exposed as an input token, attention retrieval remains primarily driven by observation-derived similarity. We formalize this limitation as feedback-blind retrieval, and formally show that, on feedback-informative tasks, observation-equivalent histories with different action-reward outcomes cannot be distinguished by any observation-only attention, resulting in suboptimal choice. To address this mismatch, we propose the Utility-Augmented Transformer (UAT), a new feedback-conditioned retrieval attention architecture in which a compact utility state modulates the query, key, and value projections, allowing action-reward history to directly alter context retrieval during the forward pass. UAT also enjoys an exact zero-gate degradation property that recovers the Vanilla Transformer when feedback is uninformative. Under finite-horizon compactness and Lipschitz assumptions, we prove that UAT strictly enlarges the observation-only Transformer class and can uniformly approximate feedback-dependent decision maps. Across four non-stationary benchmarks: synthetic navigation with hidden goal shifts, non-stationary sepsis treatment, cross-market portfolio allocation, and delayed-feedback recommendation, UAT consistently improves performance over observation-only, test-time adaptation, and input-level feedback baselines, with particularly large gains in noisier regimes that require stronger adaptation.

What gives the Bellman equation its form? We show that the recursive properties of optimal value functions follow from three conditions: that the dynamics decomposes through sufficient statistics, that the return decomposes recursively, and that the aggregation of uncertainty is compatible with both. When all three conditions hold on a common state, the Bellman equation arises from their mutual consistency; when one fails, tractability can often be recovered by augmenting the state or by deforming return or dynamics. The same conditions are shown to give rise to three dualities: one between probability and return, one between return and aggregation, and one between aggregation and probability. Our framework reveals these dualities as arising from a single construction, unifying methods developed separately across reinforcement learning, control, and decision theory.

We model cryptographic auditing of off-chain data as a Constrained MDP (CMDP) under partial observability: the storage node's hidden type and corruption state make the problem a POMDP, while a miss-rate ceiling rho imposes an explicit security constraint. We propose DRQN-CMDP, a Deep Recurrent Q-Network whose GRU layer maintains a belief over the latent node type, paired with Lagrangian dual ascent that adapts the miss-rate penalty lambda automatically. A pairing-free homomorphic-MAC primitive supplies O(1) on-chain verification cost. Across 13 methods--four DQN variants, PPO, A2C, PPO-Lagrangian, a stateful Bayesian heuristic, three fixed-rule baselines, and an oracle-informed heuristic--DRQN-CMDP achieves a favourable balance: 83% lower gas than fixed high-frequency auditing, single-digit miss rate (7.5%), and moderate detection latency--a combination no other method matches across all three objectives simultaneously.

As Large Language Models (LLMs) are increasingly deployed as autonomous agents in high-stakes domains, understanding contextual factors that may modulate their decision-making becomes critical. While LLMs are trained to perceive and resonate with users' emotions, it remains unclear whether induced emotion can influence their sequential decision-making. We investigate this question using the Iowa Gambling Task (IGT), a classic psychological paradigm for studying decision-making under uncertainty, combined with an imagination-based emotion induction procedure. We first validate the feasibility of this paradigm by confirming that LLMs can sense strong, distinguishable emotions from context and that LLM agents can learn from sequential interactions in a human-like pace. With the validated setup, we find that, different from humans, induced emotion does not significantly bias the decision dynamics of LLM agents on average. However, the effects of anger are conditioned: inducing anger makes LLM agents less sensitive to penalties for bad decisions, and in early stages of the game, anger can lower exploration, locking decisions into a few choices early. These findings reveal the subtle yet distinct effects of induced emotion on LLM decision-making compared to human behavior, and provide a tool for future research on affective modulation of LLM agents.

Black-box conditional quantile forecasts are widely used for sequential decisions under asymmetric costs, such as inventory planning in supply chain management. Once deployed, such forecasters must be monitored continuously as data streams drift and regimes change; this invalidates standard, fixed-horizon backtests for calibration. Further, existing backtests do not take into account that the notion of calibration is, in fact, information-dependent: forecasts can look calibrated to an auditor with coarse information while being miscalibrated to an auditor with richer information. We develop a distribution-free and game-theoretic testing framework for continuously auditing black-box conditional quantile forecasters with non-i.i.d. losses, such that the resulting evidence process is powerful against predictably chosen alternatives specified by the features available to the auditor. We first formalize notions of conditional quantile calibration when different sets of features are available to the auditor, establishing that the coarseness of the auditor's information set determines the hardness of the testing problem. We then identify the sets of alternatives for which the auditor can achieve power, and focusing on contextual bets linear in the features, we derive finite-time detection guarantees for such alternatives, all without an i.i.d. assumption. The resulting evidence processes are interpretable at the feature level, as they quantify fine-grained, "feature-aware" evidence for miscalibration. We empirically validate these methods on simulated and real data, finding that a popular time series forecaster (Chronos-2) is highly miscalibrated w.r.t. multiple relevant features.

Search APIs expose ranked snippets, URLs, and metadata on which agents decide whether to answer, search again, or fetch pages. We evaluate these interfaces as decision surfaces on a fixed sample of 100 questions from the 254-question SealQA-Hard subset, using one frozen GPT-5.4 agent, a fixed orchestration harness, and a shared page-fetch backend across Brave, Tavily, and Firecrawl. A Kimi-K2.6 oracle labels visible URL-level evidence; a separate answer audit yields 25, 25, and 26 correct answers out of 100. These counts indicate similar observed accuracy but do not establish equivalence. Under the tested configurations, Brave exposes more pre-fetch support alongside a larger snippet surface; Tavily has a larger rank-1 share among trajectory-pooled supporting observations; and Firecrawl is associated with broader exploration. First-search query-level metrics distinguish support availability from ranking, while contradiction exposure complements contradiction-to-gold ratios. A retrospective oracle union covers 44/100 questions, versus 26/100 for the best individual provider: 18 percentage points of headroom. The observed evidence and action differences motivate evaluating search APIs jointly with agent policy and retrieval budget.

A central premise of autonomous scientific imaging is that smarter navigation, whether Bayesian, RL-based, or otherwise adaptive, is the principal lever for sample-efficient acquisition. We present evidence to the contrary in scanning transmission electron microscopy (STEM), an atomic-resolution imaging modality whose every measurement deposits damaging electron dose. We introduce STEMGym, an open-source Gymnasium benchmark of 15 physics-simulated STEM worlds spanning five materials, three difficulty levels, and four characterisation tasks, scored by the Dose-Efficiency Curve area (DEC-AUC), a single scalar capturing the information-vs-dose Pareto frontier. Across 33 agent configurations under realistic dose budgets, the dominant determinant of dose efficiency is the analyst (perception) pipeline, not the navigator: pairing a trained CNN analyst with naïve raster scanning raises DEC-AUC by 5.5x over a CNN-free raster baseline (0.287 vs.\ 0.052), while substituting Bayesian or adaptive finite-state-machine navigation for raster yields no statistically significant further gain. Production-tier vision-language models further underperform task-specific CNNs by {\sim}13x on crystallographic defect analysis. By decoupling perception, navigation, and planning under a unified dose budget, STEMGym reframes where ML effort should be invested in autonomous electron microscopy and provides the measurement infrastructure to test it.

One goal in reinforcement learning (RL) research is to understand general-purpose sequential decision-making, using benchmark simulators as a proxy for learning in deployment settings. When running experiments, however, the goal of achieving high performance in the simulator can mutate into focusing exclusively on solving the simulator. To achieve high scores, researchers may adopt solutions exclusively meant for solving simulators, rather than learning while the agent is deployed outside a simulator. Solving simulators is also worthy of investigation, but it is a fundamentally different RL research question. In this paper, we argue that RL researchers need to distinguish between two use cases of simulators: solving simulators and using simulators as a proxy for learning in deployment. We first discuss how these two use-cases are importantly different, in terms of constraints on how the agent can use the simulator, which algorithms are appropriate, and which evaluation metrics are appropriate. We then highlight several issues and misleading conclusions that can occur by not making the distinction between these two settings clear, supported with examples and simple experiments. This work is a call to the community to begin clearly distinguishing how they are using simulators in their work, hopefully sparking further discussion on which empirical practices work best in each setting.

The global minimum-variance portfolio (GMVP) is the canonical decision built from an estimated covariance matrix, yet covariance estimators are universally evaluated by matrix-norm loss, which is not the object the decision depends on. We characterise exactly how covariance-estimation error maps into GMVP suboptimality. We prove an exact regret identity and a non-asymptotic bound showing decision regret depends on the estimation error only through its action on the portfolio weights, scaled by portfolio concentration and the conditioning of the true covariance. From this we derive the decision geometry: GMVP regret is invariant to a (p-1)-dimensional projection of the p^2-dimensional error matrix, with invariance to the covariance-scale direction as an exact special case. We then apply the framework to heavy-tailed returns (tail index kappa in (2,4)), establishing the regret convergence rate implied by the centred operator-norm rate, and confirm the theory on a skew-t/t-copula simulation design with pre-registered analysis. The decision-focused advantage is a sharper constant and a concentration discount rather than a faster rate; we report an honest high-conditioning boundary of the rate prediction. The results complement recent decision-focused learning approaches by supplying the exact estimation geometry and consistency theory they lack.

Recent studies on world modeling for Large Language Model (LLM) agents typically formulate the learning objective as next-observation prediction. However, this objective ties supervision to what a transition happens to reveal, which may omit the dynamics most relevant to the agent's current decision. To bridge this gap, we propose Agent-Authored World Modeling (AAWM), a training procedure that constructs supervision from the policy's own decision needs. Specifically, at each state, the agent identifies what it needs to understand about the environment before acting. These needs drive the retrieval of relevant transition evidence across trajectories, which is then synthesized into training targets that capture decision-oriented dynamics instead of reconstructing the next observation. This aligns the training objective with the dynamics the policy needs before acting, not with the contents of the next observation. Experimental results validate the effectiveness of AAWM across multiple environments and training settings. These results show that decision-aware world-model targets provide a more effective learning signal than next-observation prediction.

Sequential contextual stochastic programs model real-time decision systems in which each time epoch commits to an action under uncertainty whose consequences propagate into future decisions. In many practical contexts, these programs require obtaining solutions rapidly as new information becomes available. These problems can be represented through scenario approximations to be solved by off-the-shelf optimization solvers, which achieve high decision quality offline but typically run in seconds to minutes per instance, falling short of the sub-second responses that peak periods of planning require. This paper develops a learning-based optimization proxy: a scenario-embedded neural network trained offline on solver-generated labels, paired online with a decoder that enforces feasibility, replacing the per-epoch solve with a single forward pass. The framework is specialized to omnichannel order fulfillment, where each arriving order requires a sub-second assignment of products to distribution centers and carrier services under stochastic delivery times and future demand. A two-stage contextual stochastic program is introduced to formulate this problem, and its contextual sample average approximation (C-SAA) supplies the offline labels, while a composite training loss combines label imitation, a constraint-violation penalty, and self-supervised cost alignment. In a calibrated simulator built from JD.com transactional records, a detailed computational study is provided. The proxy reduces decision latency by roughly 2800x relative to the online finite-sample C-SAA reference and improves over it by 3.3% in realized fulfillment cost. Relative to established fulfillment policies, the proxy lowers total realized cost by at least 10.7% and roughly halves the late-delivery rate.

Online time-series forecasters receive labels only after horizon-dependent delays, while every adaptation step spends limited compute. We study when an online learner should update, not how to adapt at every opportunity, and introduce ADOWIP: a residual-adapter framework with sealed delay queues, exact budget accounting, and auditable update telemetry. Its main scheduler is an observed decision-loss priority gate that updates only after feedback is revealed, when downstream loss, optionally penalized by prediction MSE, exceeds a calibrated empirical quantile and budget remains. We prove hard-budget feasibility, projected-OGD regret for a convex linear accepted-update subproblem, and stability plus conditional finite-sample gate-selection statements. On public ETT capacity-planning tasks, a frozen calibration/evaluation split selects a gate that lowers held-out decision loss against always, fixed-period, and drift-triggered exact-update baselines under matched compute. Secondary threshold/load-index ETT suites are mixed: 33 of 41 selected contrasts clear the stricter cross-artifact Holm family, and the 8 nonpassing rows are explicitly excluded from primary claims. The same protocol improves an external UCI Bike capacity proxy with 20/0 held-out wins, and a fixed gate passes three full-year Capital Bikeshare station-rebalancing contrasts. Probe-based and finance experiments remain negative, delimiting the current scope of decision-prioritized adaptation.

Selective ensemble for modern machine learning systems requires choosing promising model candidates under limited evaluation budgets, while downstream tasks often specify only partial preferences over capabilities such as accuracy, robustness, and reasoning. This setting naturally gives rise to a sequential decision problem under partially specified linear preferences. We formalize it as preference-directed multi-objective bandits (PDMOB), where admissible trade-offs are represented by a polyhedral preference cone. Based on this formulation, we introduce Pareto $C$-optimality, which recovers standard Pareto optimality and single-weight scalarization as special cases. We then propose the preference-directed upper confidence bound (PrefUCB) algorithm, which maintains directional confidence intervals to guide exploration. We analyze both indicator-based and gap-weighted regret, and establish instance-dependent logarithmic bounds for both criteria, recovering the optimal logarithmic dependence on the horizon $T$ in classical special cases. Experiments on large pre-trained model selective ensemble tasks and online asset allocation under institutional mandates validate the efficacy of our method.

Plugging predictions of unknown parameters into downstream optimization problems, often referred to as the ``predict-then-optimize'' paradigm, has long been a standard approach in decision-making under uncertainty. However, improved predictive accuracy does not, in general, translate into improved decision quality. This disconnect has motivated growing interest in decision-focused learning (DFL) within the operations research community. This tutorial reviews recent developments in DFL and highlights key methodological insights, with a particular focus on stochastic linear programming as the downstream decision-making problem. We discuss why several widely used tools in traditional statistical learning are not directly suited to decision-focused settings and must be rethought, including (i) data collection strategies driven purely by predictive uncertainty and (ii) distributional distance measures such as the Wasserstein distance. We summarize properties of DFL that distinguish it from conventional predictive modeling and provide insights into the development of new decision-focused tools.

We introduce Bellman-sufficient information complexity for minimax analysis of sequential decision problems. A Bellman-sufficient state retains enough of the history to close the controlled recursion, while an index $Y=χ(Ω)$ specifies the decision-relevant information being charged. The upper bound is a log-penalized Bellman program; the lower bound is a Bellman--Fano comparison along an algorithm-dependent reference trajectory. If the two values match at a common localization scale and the stated admissibility, calibration, and growth conditions hold, they form an information-risk sandwich. UCB, E2D, and AMS/EBO control or relax the upper Bellman bracket in different ways. For the main application, we give a negative answer to a widely studied form of the GP--UCB minimax-optimality question. For every $0<α<1/4$, we construct one bounded continuous kernel whose minimax regret is $Θ(T^{1-α})$ along an infinite sequence of horizons, while two globally calibrated GP--UCB rules incur linear regret under one fixed truth. An epochwise finite-marginal action-index AIR Bellman policy, implemented through robust AIR/AMS/EBO control, attains the minimax order. The construction separates realized information from the cost of uniform optimism: many low-value directions inflate the exploration multiplier and change the trajectory. Through the canonical RKHS feature map, it also yields a finite-horizon polynomial minimax separation for the specified maximal-information-calibrated LinUCB rule. A reproducible experiment illustrates the mechanism.

Social Learning is a decentralized decision-making paradigm in which spatially dispersed agents collect streaming observations regulated by one of a finite number of models (the hypotheses). The agents are interested in assigning probability scores (the beliefs) to the possible hypotheses. To this end, the agents exchange their beliefs according to a certain communication graph. It has been shown that, under reasonable conditions on the identifiability of the decision model and the network connectivity, each agent ultimately places all the belief mass on the true hypothesis governing the data. However, several questions remain unanswered regarding the evaluation of the social learning performance. One recently adopted performance metric is the rejection rate, i.e., the rate at which the beliefs about the erroneous hypotheses vanish. One contribution of this work is to establish that the rejection rate leads to several paradoxes, which make it unsuitable as a valid performance measure. We then focus on studying the error probability measure. For a binary Gaussian problem, we derive an analytical formula characterizing the ratio between the individual agents' probabilities and the optimal Bayesian probability. The formula shows that this ratio is expressed by the product of two terms quantifying the effect of the network connectivity and the role of the prior information. As a result, an irreducible gap emerges between the decentralized and the centralized error probabilities, which is agent-dependent and does not disappear asymptotically.

As neural networks are increasingly deployed in safety-critical domains, testing is essential to evaluate and improve their reliability. Existing testing methods, whether black-box or white-box, primarily use global mutation or coverage-guided strategies, both of which struggle to efficiently uncover diverse model failures while remaining proximate to the original data distribution and semantics. We propose BayesWarp, a testing framework that addresses this limitation by mutating decision-critical input regions identified via interpretable saliency techniques and adaptively guiding the testing process using an uncertainty-aware Bayesian Optimization strategy, enabling the discovery of diverse failures while preserving distributional and semantic proximity to the original data. Evaluation on MNIST, CIFAR-10, and ImageNet across six neural network models shows that BayesWarp improves failure discovery, failure diversity, test case quality, and critical neuron coverage under a fixed mutation budget. These results demonstrate that BayesWarp improves testing effectiveness. Moreover, fine-tuning with the generated failure cases leads to improvements in model performance.

We tackle the Metro Network Expansion Problem (MNEP), a subset of the Transport Network Design Problem (TNDP), which focuses on expanding metro systems to satisfy travel demand. Traditional methods rely on exact and heuristic approaches that require expert-defined constraints to reduce the search space. Recently, deep reinforcement learning (Deep RL) has emerged due to its effectiveness in complex sequential decision-making processes-it remains, however, computationally expensive, environmentally costly, and requires additional engineering to interpret. We show that MNEP problems are small enough to not require Deep RL methods. Reformulating the MNEP as a Non-Markovian Rewards Decision Process (NMRDP), we use tabular RL to achieve similar performance with significantly fewer training episodes, additionally offering greater interpretability. Additionally, we incorporate social equity criteria into the reward functions, focusing on efficiency and fairness, highlighting the versatility of our method. Evaluated in real-world settings-Xi'an and Amsterdam-our method reduces total episodes by a factor of 18 and total carbon emissions by a factor of 12 on average, while remaining competitive with Deep RL. This approach offers a replicable, modular, interpretable, and resource-efficient solution with potential applications to other combinatorial optimization problems.

Reinforcement learning problems typically define the goal as maximizing the expected value of a scalar reward function. But, pairwise preferences are often easier to specify than scalar rewards, and they express certain goals that scalar rewards cannot. Methods for reinforcement learning with pairwise preferences have thus received growing interest. Unfortunately, these methods are inefficient in problems with long time horizons, and they lack guarantees on the performance of Markov policies relative to history-dependent policies, which bridge the theory and practice of reinforcement learning. We therefore propose the \textit{Markov decision contest} as a new problem model for reinforcement learning with pairwise preferences. We prove that stationary Markov policies are optimal among all history-dependent policies, that solving a Markov decision contest exactly is in P, and that a simple iterative algorithm converges to an optimal policy at a sublinear rate. Lastly, in a set of high-dimensional decision problems with long time horizons, we show that our approximate algorithm is significantly more learning-efficient than prior work.

Agent benchmarks increasingly record rich interaction trajectories, yet evaluation often reduces each rollout to a pass rate or reward score. We introduce TraceGraph, a graph-based framework that turns released multi-model agent trajectories into shared decision landscapes. For each task, TraceGraph builds a graph over observable action-observation states from pooled rollouts before model identity is introduced. It then overlays outcome-informed productive cores and trap regions, and summarizes each rollout with three events: Access, Trap exposure, and Repair. Across trajectories spanning five benchmark splits, TraceGraph profiles reveal navigation differences hidden by aggregate scores and show that splits differ in whether they reward avoiding traps or recovering from them. The same TraceGraph landscape also motivates a trap-aware recovery pipeline for SWE-bench: aruntime detector fires on states matching historical trap regions, then lightweight continuation policies are evaluated from the same prefix. On fired states, the best pooled single-factor policy raises official resolved rate from 40.4% to 43.5% on the per-provider fired subset and from 41.0% to 44.8% on common-fired instances, with provider-specific active components. Overall, TraceGraph provides a process vocabulary for asking what agent benchmarks test, where models diverge on a shared landscape, and how failure regions can guide downstream improvement.

Sequential filtering pipelines are a common design pattern in large-scale systems, where a large population of items is progressively reduced by a sequence of stages that each incur cost. Despite their prevalence in ranking systems, cascaded machine learning inference, and fraud detection, filter ordering is often determined by heuristics without formal guarantees. We formalize sequential filtering under an expected-cost objective and prove that, under an independence model, ordering filters by increasing ratio of cost to rejection probability minimizes expected total cost. Extensive Monte Carlo simulations show that the optimal ordering strictly dominates common heuristics across all runs, both in expectation and across the full distribution of outcomes.

Mechanistic interpretability seeks to explain a model's behaviour by finding its circuit: the sparse subgraph of the model's computation that is causally responsible for it. Automated methods have made this search systematic, but each one starts afresh for every behaviour, and the effort spent finding one circuit does nothing for the next. Circuit discovery has thus been automated, but not amortised. We ask whether circuit discovery can itself be learned. We frame it as a sequential decision problem over the computation graph of GPT-2 small, in which a policy removes edges until it reaches a compact subgraph that preserves the behaviour, guided by a faithfulness reward defined through causal intervention. A single policy trained across twelve behaviours recovers a faithful circuit for each, and once frozen it transfers to behaviours it never saw during training, recovering their known circuits without further search. A short warm-start improves these transferred circuits, returning far smaller ones than training from scratch. While the learned policy does not match a per-behaviour search on circuit size or cost, it shows that circuit discovery is a learnable, transferable procedure rather than a search repeated for every behaviour.

Bayesian optimal experimental design (BOED) selects experiments to maximize information gain about model parameters. However, in decision-critical settings, reducing parameter uncertainty does not necessarily improve downstream decisions, as only specific parameter directions relevant to the objective truly matter. We propose GoBOED, a goal-driven BOED framework that directly optimizes experimental designs for a specified decision-making objective. GoBOED combines an amortized variational posterior surrogate with a differentiable convex decision layer, enabling gradient-based design optimization that is fully decision-focused. We theoretically show that GoBOED gradients are insensitive to parameter directions irrelevant to the decision objective, providing a formal justification for why goal-driven design achieves equivalent decision quality over a wider set of experimental designs than information-gain maximization. Empirically, across source localization, epidemic management, and pharmacokinetic control, GoBOED identifies designs that better align with downstream decision objectives and reveals that near-optimal design windows are substantially wider than those predicted by goal-agnostic BOED approaches.

Existing LLM routing frameworks treat queries as independent events, neglecting the sequential nature of real-world user sessions constrained by global computational budgets. This mismatch inevitably leads to budget bankruptcy: myopic routing policies exhaust resources on early interactions, forcing subsequent and often more complex queries onto inadequate models. We introduce SeqRoute, a framework that formulates multi-turn routing as a finite-horizon Markov Decision Process and solves it via offline reinforcement learning. By incorporating the remaining budget into the state space and training with Conservative Q-Learning (CQL), SeqRoute learns delayed gratification to strategically preserve resources for high-stakes turns later in the session. To overcome data starvation, we propose Hindsight Budget Relabeling (HBR). This technique retrospectively simulates historical trajectories under diverse hypothetical budgets, expanding 10,000 raw sessions into 2.38 million transitions enriched with critical bankruptcy signals. At deployment, a dynamic $λ$-sweep mechanism enables zero-shot navigation of the cost-quality Pareto frontier without retraining. Extensive evaluations demonstrate that SeqRoute reduces operational costs by 6.0-73.5% while maintaining or improving quality, and suppresses bankruptcy rates to under 1%, strictly dominating behavior cloning, budget-aware heuristics, and static baselines across the entire Pareto frontier.

Human decision-making is sequential and uncertainty-aware, yet standard neural networks often rely on static, dense forward computation with limited visibility into evidence acquisition, uncertainty evolution, or when computation should stop. We introduce \textbf{Neural Bayesian Sequential Routing (NBSR)}, a framework that models neural inference as active evidence accumulation over a hierarchical Directed Acyclic Graph (DAG). Within a Dirichlet--Categorical conjugate framework, neural experts query a persistent global knowledge oracle to extract positive evidence vectors, which act as pseudo-counts and update a Dirichlet belief state by exact conjugate addition. Coupled with a Gumbel-Softmax Straight-Through estimator, this update enables hard, path-dependent routing while preserving surrogate gradients for end-to-end training. The resulting Dirichlet precision and entropy provide mechanisms for uncertainty quantification, entropy-based early exiting, OOD abstention, and cost-aware evidence acquisition. We prove that, under strictly positive evidence extraction, total Dirichlet precision increases monotonically along any valid trajectory and marginal predictive variance is bounded, formalizing sequential ``hypothesis sharpening''; under idealized capacity and optimization assumptions, the terminal Dirichlet expectation recovers the Bayes-optimal conditional distribution. Empirical evaluations across visual categorization, structured medical diagnosis, language modeling, partially observable control, and cost-aware Bayesian experimental design show that NBSR achieves competitive predictive performance while providing transparent routing traces, path-dependent evidence attribution, uncertainty-aware decision control, and resource-rational inference. Overall, NBSR offers a mathematically grounded framework for interpretable, modular, and resource-rational agentic AI.

In learning-augmented online algorithms, predictions are usually valued for what they say: a value estimate, a solution, or an algorithmic recommendation. This paper shows that predictions can also be valuable solely due to their arrival time. We study the fundamental secretary problem augmented with a stochastic precursor: a content-free signal that is guaranteed to arrive no later than the best item, but is otherwise stochastically timed. The signal does not carry any additional information; nevertheless, its timing alone changes the structure of optimal stopping. We characterize optimal policies in the random-order and adversarial-order models. In random order, a single uniformly timed precursor already gives success probability at least $\frac12$, improving on the classic $\frac1e$ benchmark. With increasingly late precursors, the success probability approaches $1$. In adversarial order, for which traditional models do not admit strong guarantees, sufficiently concentrated precursors recover constant success guarantees. Our results show that such novel forms of asynchronous temporal information are a distinct and powerful form of advice in online decision making and may also be effective for other problems.

Suppose a planner has a pre-trained simulator of a sequential decision problem and the option to run real experiments in the field. The simulator is cheap to query but inherits confounding and drift from its calibration data. Experimentation is unbiased but consumes one real unit per trial. We study when, and how, the planner should supplement the simulator with experiments. We give three results. First, an extended simulation lemma decomposes the simulator's value error into a calibration--deployment shift that randomization can identify and a parametric residual that no further interaction can reduce. Second, the value gap between the simulator-optimal policy and the optimum splits into a local component, on states the deployed policy already visits, and a reachability component, on states it does not. The reachability component stays bounded away from zero at any horizon under purely passive learning. Third, we propose Fisher-SEP, a simulation-aided experimental policy (SEP) that minimizes the posterior predictive variance of a target policy's value, with reward-only and transition-only specializations. Two case studies illustrate the regimes. In a vending-machine supply chain, front-loaded experimentation overtakes posterior updating once the horizon is long enough to amortize the pilot. In an HIV mobile-testing example with a corridor that separates a well-surveilled region from a poorly-surveilled one, only designed exploration reaches the poorly-surveilled region.

Ride-hailing platforms like DiDi Chuxing operate in highly dynamic environments where balancing driver supply and passenger demand is critical. Although driver-side subsidies serve as a primary lever to align these forces and improve key KPIs like completed rides (\texttt{Rides}) and gross merchandise value (\texttt{GMV}), optimizing them in production requires simultaneously meeting three constraints: (i) responsiveness to stochastic shocks, (ii) strict subsidy-rate caps, and (iii) low-latency execution at city scale. These requirements rule out expensive per-order optimization, calling for a forward-looking, constraint-aware city-level controller for online sequential decision making. To meet these requirements, we introduce D$^3$-Subsidy (Dynamic Driver-side Diffusion-based Subsidy), a hierarchical diffusion-based framework for deployable city-wide subsidy control. To bridge the train-inference gap, D$^3$-Subsidy employs a prefix-conditioned diffusion model that samples plausible future trajectories from immutable historical observations, ensuring the training protocol aligns with the fixed-history nature of online deployment. These generated plans are then decoded by a context-conditioned inverse module into low-dimensional city-level control signals. For scalable execution, we bridge the gap between city-level planning and fine-grained dispatch via a Lagrangian-dual-derived mapping, which embeds subsidy-rate caps directly into order-driver incentives without iterative optimization. Additionally, a multi-city pretraining strategy with parameter-efficient fine-tuning enables robust transfer across heterogeneous cities. Extensive offline evaluations demonstrate that D$^3$-Subsidy improves \texttt{Rides} and \texttt{GMV} while enhancing cap compliance, and a real-world A/B test confirms significant uplift while keeping budget-related violation metrics within operational thresholds.

Individualized treatment selection with continuous actions requires accurate causal response estimation in decision-relevant regions, rather than uniformly over the entire action space. Estimating a global causal response surface and then choosing the treatment that maximizes it can therefore be suboptimal, since standard estimation objectives allocate modeling effort according to the observed treatment distribution rather than the regions that determine the optimal decision. While decision-aware approaches have been studied in unconfounded settings, this problem remains underexplored in proximal causal inference, where proxy variables and bridge functions enable identification under suitable assumptions even in the presence of hidden confounding. Despite recent progress, proximal methods have primarily focused on treatment-effect and potential-outcome estimation rather than treatment selection and optimal decision-making. To bridge this gap, we introduce a policy-targeted weighted bridge loss that emphasizes decision-relevant treatment regions while retaining global stabilization. We prove a regret bound showing that the proposed weighted bridge loss controls treatment-selection regret through a weighted ill-posedness constant. We instantiate the framework in decision-aware variants of several proximal bridge solvers, yielding practical algorithms that alternate between weighted bridge estimation, response-surface projection, policy update, and weight refinement. Empirically, we find that decision-aware weighting reduces regret across several bridge solvers, suggesting improved treatment selection in proximal settings.

Probabilistic search algorithms, such as Monte Carlo Tree Search (MCTS), have proven very effective in solving sequential decision-making tasks under uncertainty. However, interpreting asymmetric search trees that incorporate bandit-based tree traversal and simulation-based value estimation is difficult for end users based solely on raw tree statistics. While prior work requires hand-crafted formal logic constraints that must be updated when the problem changes, we present a framework that enables large language models (LLMs) to generate evidence-grounded explanations of MCTS decisions from recorded search traces in an end-to-end manner. Our framework maps natural-language questions to a structured set of intent categories, determines whether the existing tree contains sufficient evidence, triggers targeted expansion when needed, and generates explanations using tree statistics such as visit counts, value estimates, and risk information. Experimental results provide the first evidence that LLMs can serve as end-to-end explainers for probabilistic search, without requiring intermediate formal representations.

Strategic mine production scheduling under geological uncertainty is conventionally formulated as a stochastic optimization problem in which a fixed extraction sequence and routing decisions are computed ex ante. This plan-driven paradigm treats uncertainty as passive: decisions are hedged across geological scenarios, but planning does not anticipate how future observations will inform future decisions. We propose a different perspective by formulating mine scheduling as a Partially Observable Markov Decision Process (POMDP), in which extraction and routing decisions are made sequentially with planning explicitly integrating the expectation of future belief updates. To achieve computational tractability, we introduce a hybrid SA-POMDP architecture that combines simulated annealing-based (SA) value approximation with ensemble-based belief updating via ensemble smoother with multiple data assimilation (ES-MDA). At each decision epoch, candidate actions are evaluated through their expected long-term value under the current belief, and the belief is updated as mining observations are assimilated. This yields an adaptive policy rather than a fixed plan. We evaluate the framework on a copper-gold open-pit mining complex with multiple processing destinations. Under a statistically consistent prior, the SA-POMDP reduces the expectation-reality gap from 22.3% to 4.6%, improving realized NPV by USD8.4M relative to one-shot stochastic optimization. Under systematic prior misspecification of 10%, the adaptive framework outperforms static planning by up to USD44.6M (36.9%), demonstrating structural robustness beyond scenario hedging. These results show that sequential belief updating transforms geological uncertainty from a passive constraint into an active component of value creation.

Many online decision problems over combinatorial actions are addressed via convex relaxations, leading to online convex optimization with piecewise linear objectives and induced polyhedral structure. We show that regret in such problems is governed by \emph{polyhedral instability}: the number of changes of the active region. Under full information feedback and fixed partition assumptions, if $\mathrm{RS}_T$ denotes the number of region switches and $V_{\max}$ the maximum number of vertices per region, we prove $\Regret_T= Θ(\sqrt{(1+\mathrm{RS}_T)\,T\,\log V_{\max}})$ interpolating between experts-like and dimension-dependent OCO rates. For online submodular--concave games under Lovász convexification, this reduces to the permutation-switch count $\mathrm{SC}_T$, yielding the matching rate $\Regret_T= Θ(\sqrt{(1+\mathrm{SC}_T)\,T\,\log n})$. Experiments on synthetic and real combinatorial problems (shortest path, influence maximization) validate the predicted scaling and indicate that low-instability regimes can arise in practice without explicit enumeration of actions.

Contextual bandits (CB) are online sequential decision-making problems under partial feedback that underpin many adaptive services. There is a growing demand to deploy CB agents directly on-device, under strict constraints on memory, compute, and energy. However, standard linear CB algorithms are often impractical for resource-constrained devices with their unfavorable scaling in computational and memory costs. Recently, HD-CB, a CB approach based on hyperdimensional computing principles, has been proposed to model and solve CB problems by moving into high-dimensional spaces. HD-CB offers faster convergence, favorable scalability, and improves memory efficiency compared to linear CB algorithms. However, its learning rule is accumulation-based: the values of action vectors grow over time, requiring high precision. While periodic binarization can prevent overflow in low-precision components, it may discard important information about magnitudes and degrade decision quality. This paper introduces probabilistic HD-CB, a low-precision variant that replaces deterministic accumulation with a probabilistic update rule. At each step, only a random subset of vector components is updated, with a time-decaying update probability, and component values are constrained to a predefined range [-k,+k]. This approach enables low-precision components, prevents overflow without periodic binarization, and reduces the expected update cost in proportion to the fraction of updated components. Off-policy evaluation on standardized synthetic CB benchmarks using the Open Bandit Pipeline shows that probabilistic HD-CB consistently outperforms binarized HD-CB at equal precision, while approaching the performance of HD-CB with as few as 3 bits per component.

Information-theoretic generalization bounds based on the supersample construction are a central tool for algorithm-dependent generalization analysis in the batch i.i.d.~setting. However, existing supersample conditional mutual information (CMI) bounds do not directly apply to sequential decision-making problems such as online learning, streaming active learning, and bandits, where data are revealed adaptively and the learner evolves along a causal trajectory. To address this limitation, we develop a sequential supersample framework that separates the learner filtration from a proof-side enlargement used for ghost-coordinate comparisons. Under a row-wise exchangeability assumption, the sequential generalization gap is controlled by sequential CMI, a sum of roundwise selector--loss information terms. We also establish a Bernstein-type refinement that yields faster rates under suitable variance conditions. The selector-SCMI proof strategy applies to online learning, streaming active learning with importance weighting, and stochastic multi-armed bandits.

Hybrid mechanistic models, physical priors with learned residuals, promise to reduce the data required for good decisions, but have no computable criterion to test this. We characterize the value of mechanistic priors in sequential decision-making within both asymptotic and burn-in regimes. To formalize this, we introduce the mechanistic information of a model -- the mutual information between the model's recommended policy $\hatπ$ and the true optimal policy $π^*$ -- quantified via an occupancy-weighted bias $B_μ$. In the asymptotic regime (large $N$), matched bounds reveal that Bayesian regret scales with the residual entropy $H_{\mathrm{mech}}$, delivering a theoretical sample complexity reduction of $H(μ)/H_{\mathrm{mech}}$ compared to an uninformed baseline. Furthermore, we provide a model certificate to determine empirical sample efficiency. Complementarily, in the clinically relevant burn-in regime (small $N$), we establish a lower bound on the penalty incurred by confidently wrong priors. We demonstrate both the asymptotic and burn-in bounds across 5-fluorouracil (5-FU) dosing simulations motivated by published FOLFOX pharmacokinetic data, where a hybrid prior yields large sample-efficiency gains in the burn-in regime. Finally, we contrast these grounded models with LLM priors, demonstrating that LLMs can suffer severe losses in mechanistic information, thereby motivating the exclusive use of physically-grounded priors for safety-critical applications.

Large language models (LLMs) have shown remarkable in-context learning (ICL) capabilities, yet their potential for sequential decision-making remains underexplored. In this paper, we study the ICL capabilities of LLMs in sequential decision-making settings, including Markov Decision Processes (MDPs), Partially Observable MDPs (POMDPs), and Ambiguous POMDPs (APOMDPs). We fine-tune pretrained LLMs to perform few-shot decision-making directly from offline, oracle-labeled trajectories. Our framework enables flexible imitation of policies through supervised fine-tuning (SFT). Theoretically, we focus on linear MDPs and interpret a fine-tuned attention layer as implicitly estimating optimal Q-functions from in-context data. Building on this interpretation, we derive an end-to-end suboptimality bound for the induced policy that separates the in-context estimation error from the training-length bias. Empirically, across synthetic MDP, POMDP, and APOMDP settings, we find that fine-tuned LLMs achieve substantially smaller optimality gaps than in-context-only and random baselines, with especially large gains in longer-horizon, partially observed, and model-ambiguous environments. Together, these results show that supervised fine-tuning provides an effective route to endowing pretrained LLMs with sequential decision-making capabilities from offline data, which is an important advantage in domains such as healthcare where offline data are abundant.

Layer pruning efficiently reduces Large Language Model (LLM) computational costs but often triggers sudden performance collapse. Existing representation-based analyses struggle to explain this mechanism. We propose studying pruning through decision representation. Focusing on multiple-choice tasks, we introduce two metrics, Decision Margin and Option Frequency, and an Iterative Pruning method to analyze layer-wise decision dynamics. Our findings reveal a sharp decision transition that partitions the network into two stages: a Silent Phase, where the model cannot yet predict the correct answer, and a Decisive Phase, where the correct prediction emerges. We also find that pruning the Decisive Phase has minimal impact, whereas pruning the Silent Phase triggers immediate performance collapse, highlighting its extreme sensitivity to structural changes. Therefore, we conclude that pruning-induced collapse stems from disrupting the Silent Phase, which prevents the critical decision transition from occurring.

AI agent research spans a wide spectrum: from RL agents that learn from scratch to foundation model agents that leverage pre-trained knowledge, yet no unified benchmark enables fair comparison across these approaches. We present Agentick, a benchmark for sequential decision-making agents designed to evaluate RL, LLM, VLM, hybrid, and human agents on common ground and to power research on the fundamental challenges of sequential decision-making. Agentick provides 37 procedurally generated tasks across six capability categories, four difficulty levels, and five observation modalities, all exposed through a single Gymnasium-compatible interface. The benchmark ships with a Coding API, oracle reference policies for all tasks, pre-built SFT datasets, a composable agent harness, and a live leaderboard. An evaluation spanning 27 configurations and over 90,000 episodes reveals that no single approach dominates: GPT-5 mini leads overall at 0.309 oracle-normalized score while PPO dominates planning and multi-agent tasks; the reasoning harness multiplies LLM performance by 3-10x; and ASCII observations consistently outperform natural language. These findings highlight the substantial room for improvement that remains across all agent paradigms. Agentick's capability-decomposed, multi-modal design provides the empirical infrastructure needed to drive progress toward general autonomous agents, both as an evaluation framework and as a training ground for RL post-training of foundation models in truly sequential environments.