Decisions

Scientific experiments are often designed to maximize information gain, yet in many applications the primary objective is to support reliable downstream decision-making. Existing decision-aware experimental design and active learning methods typically assume well-specified outcome models and implicitly rely on the stability of the optimal decision under real-world perturbations. In practice, however, experimental outcomes are frequently influenced by hidden or weakly modeled effects, which can substantially alter decision optimality and lead to misleading conclusions. We study sequential adversarially robust decision-aware experimental design, where data acquisition has to take into account information gain against plausible worst-case unexpected effects, modeled here as variation in adversarial variables. Building on Bayesian decision theory, we formalize an adversarially robust optimal decision under this setting and derive a principled Bayesian experimental design criterion. The criterion explicitly targets decision stability rather than nominal optimality. Experiments on synthetic and real-world scientific datasets show that conventional decision-aware design can converge rapidly to high confidence yet fragile decisions, while our robustness-aware approach yields decisions that are significantly more stable and reliable under adversarial variation.

Evaluating decisions made under uncertainty is hard when labeled outcomes are scarce, costly, or confounded with luck. We treat subjective expected utility (SEU) maximization as a stated standard and define a graded measure -- SEU sensitivity -- of an agent's conformity to it. The vehicle is a softmax choice model with a sensitivity parameter $α$ on SEU-valued alternatives; the contribution is a sequence of identifiability results for $α$ and for belief and utility parameters $(β, δ)$, validated in Stan via prior predictive checks, parameter recovery, and simulation-based calibration (SBC), with finite-sample caveats intact. In the uncertain-choice-only model $m_0$, $α$ is identifiable given the expected-utility vector $η$ and sharply recovered, while $(β, δ)$ are only weakly informed: the posterior barely contracts and concentrates on a $β$-$δ$ trade-off. In the extended model $m_1$, $δ$ becomes identifiable in principle via a $β$-free risky block, but its practical recovery gain at realistic sample sizes is negligible (matched-count CI-width reduction under 1%), and that block yields no detected $α$-precision gain at matched choice count. These are two distinct phenomena: for $δ$, identifiability does not imply precise estimability at realistic $n$; for $α$, identifiability is silent about what governs finite-$n$ precision. Marginal SBC passes for both models even where the joint posterior is weakly informed -- a demarcation we make precise. A two-by-two application (GPT-4o and Claude 3.5 Sonnet, each on insurance-claims triage and Ellsberg-style urns, with sampling temperature as the lever) runs end-to-end on real LLM choice data, detecting a structured comparative $α$ effect in two of four cells.

Deliberation plays a crucial role in collaboration; when humans work together, they naturally engage in communication to align information and reach an agreement. In this paper, we investigate deliberative large language model (LLM) agents under partially observable joint decision-making tasks. We formalize deliberative collaboration as a cooperative joint decision problem with partial and asymmetric observations, and introduce a scalable benchmark that instantiates this problem across multiple task settings and domains in which agents must exchange information through deliberation to reach a joint decision with a shared reward. We then instantiate a reference scaffold and evaluation protocol for deliberative agents and conduct a systematic evaluation of a range of representative LLMs. The results reveal that complex deliberative collaboration tasks continue to challenge state-of-the-art language models. Even with the aid of external mathematical tools, language models may fail in either the deliberation process for aligning information or the complex reasoning process for making the decision. On the other hand, diagnostic analysis reveals that the deliberation process may also provide opportunities for reflection and error correction, sometimes improving performance over centralized baselines. Altogether, our work establishes a foundation for evaluating and improving LLM agents in deliberative collaboration and provides insights into the strengths, limitations, and properties of current LLM-based multi-agent systems.

We present LLM4SDM, the first study of open-source smaller language models (OS-sLLMs) for automated assessment of shared decision making (SDM) using the Observer OPTION12 framework. Unlike previous work that relies on large commercial models and the shorter OPTION5 instrument, our study focuses on privacy-preserving locally deployable models and Dutch melanoma consultation transcripts. Using expert-annotated clinical consultations, we evaluate three general-domain and two medical-domain OS-sLLMs during a development-phase pilot study. Results show that general-domain models outperform medical-domain models, which exhibit substantial hallucination and instruction-following failures. Gemma3:12b achieves the strongest agreement with human annotations (Pearson r=0.51, Spearman \r{ho}=0.59). Item-level and qualitative analyses reveal systematic challenges related to temporal discourse reasoning, conversational role attribution, and evidence grounding. We further introduce a Judge-LLM consensus framework designed to support disagreement resolution among multiple models. Our findings suggest that while current OS-sLLMs cannot replace human annotators, they offer a promising foundation for privacy-preserving human-in-the-loop SDM assessment.

Automated experimentation is moving from closed-loop optimization toward open decision-making, where human or AI planners must forecast the consequences of candidate actions before executing them. Such forecasts require a model of both sides of the experiment: how the sample is likely to respond and what the instrument is likely to detect. We therefore introduce a coupled digital-twin framework that separates these roles and then links them. In this framework, the sample twin encodes material state inferred from prior knowledge and measurements till the moment. The instrument twin captures signal formation, feedback dynamics, and operating constraints based on prior knowledge. When coupled, the two twins estimate expected outcomes, uncertainty, and risk for candidate microscope operations. For amplitude-modulation scanning probe microscopy, we realize this framework with a physics-informed encoder of force-distance curves, a deterministic scanner model of cantilever and feedback dynamics, and sparse learned residual corrections. The encoder first recovers scanner-driving descriptors with sub-nanometer accuracy. The calibrated scanner then reproduces typical traces within a few nanometers and identifies operating-point noise amplification as the main source of mismatch. Supplementary phase analysis localizes residual error to the phase channel, which clarifies where added physics is needed. Together, these results establish coupled sample and instrument twins as a practical foundation for predictive microscope operation and autonomous experimental planning.

This paper introduces a quantum-inspired computational framework for harmonic decision-making in music. The proposed approach formulates harmonization as an optimization problem within a structured combinatorial space, where multiple candidate chord sequences are evaluated under interacting musical constraints. The model combines an interference-based harmonization stage with a classical optimization procedure grounded in tonal harmony. The quantum-inspired component enables the parallel consideration of multiple harmonic alternatives, while the classical stage refines the resulting sequences to ensure structural coherence and stylistic plausibility. The framework is evaluated on selected musical examples, including Autumn Leaves and It's a Long Way to Tipperary. Quantitative analysis shows that the optimization stage significantly reduces chord density, increases harmonic stability, and improves functional organization. At the same time, expert evaluation highlights the importance of stylistic context, demonstrating that increased harmonic complexity is not always perceived as more natural. The results suggest that harmonic generation can be interpreted as a structured decision-making process in a constrained search space. The proposed approach provides a computational model that integrates domain-specific knowledge with an interference-based search mechanism. Although preliminary, this work indicates that quantum-inspired methods may offer a useful framework for modeling complex decision processes in creative domains such as music. The proposed framework contributes to ongoing research on quantum-inspired models of cognition and decision-making in complex biological and creative systems.

Many real-world games do not admit a fixed, compact rule set: instead, their dynamics are defined by interactions among a large and often evolving collection of game pieces, making general-purpose policy learning impractical. Magic: the Gathering (MTG) exemplifies this setting, where the cards themselves define and alter gameplay rules, strategic constraints, and long-term outcomes, while the pool of available cards is ever-changing. We study Draft, a constrained deck-building format of MTG in which eight players make 39-45 sequential selections from semi-random packs to construct a 40-card deck under partial information. By isolating the card selection process from gameplay, Draft provides a tractable yet non-trivial setting for studying decision-making driven by combinatorial card synergies. We propose an encoder-based model that produces set-contextualized card embeddings to encode the draft decision sequence, with a consistent improvement over linear baselines on large-scale real-world data, establishing a first learned benchmark for outcome prediction in MTG Draft. Our code is available at github.com/akulen/MtGDraftEncoder.

Urban mobility modeling faces challenges in representing decision-making in dynamic environments. Although Multi-Agent Systems are widely used, rule-based approaches rely on fixed heuristics that limit adaptive behavior. This work investigates the integration of Large Language Models (LLMs) as decision-making components in multi-agent simulations. We propose a hybrid architecture that connects the GAMA platform to an external LLM-based module through an API, enabling agents to determine whether route replanning is necessary. Rather than replacing routing algorithms, the LLM serves as a decision layer that guides replanning behavior. The approach incorporates persistent memory, allowing past interactions to influence future decisions and promote behavioral consistency. We compare rule-based and LLM-assisted approaches across multiple road-blockage scenarios and population scales. Results indicate that LLM-enabled agents exhibit greater adaptability and contextual awareness, particularly in scenarios with higher route flexibility. Memory influences performance and behavioral consistency, with effects varying across configurations. Overall, LLMs serve as complementary cognitive layers that enrich behavioral representations in urban mobility simulations and hold potential for modeling complex decision-making in spatial multi-agent systems.

Local pairwise comparisons are a standard tool for learning how people want decision rules to work, e.g., in participatory design or alignment. However, their use builds in two strong assumptions: that local comparisons are sufficient evidence about how a person wants an automated decision rule to behave, and that people can always answer those comparisons decisively. We investigate how these assumptions may be compromised under internal pluralism: the idea that an individual evaluates decision rules according to multiple authoritative priorities about how the rule should behave. We provide a formal model of such pluralistic preferences over decision rules, which then lets us identify two distinct failures of forced local pairwise comparison data. First, priorities such as proportionality, egalitarianism, and equal treatment are inherently global: what they imply in one case can depend on what happens elsewhere, so local comparisons may fail to capture them. Second, even when priorities are representable locally, tension between strongly-held priorities can generate internal conflict, producing potentially costly behavioral distortions when comparisons are forced. We then use our model to investigate the alternative -- allowing people to report indecision -- and our findings suggest that doing so can considerably reduce the number of queries needed to learn preferences accurately. We conclude by describing how our model points toward preference-learning methods that elicit these priorities directly, yielding more faithful and interpretable accounts of what people value.

The evolution toward fully autonomous telecommunications networks (Autonomous Network Levels 4-5) requires AI/ML agents to make real-time network decisions without human intervention. However, no standardized runtime mechanism exists to intercept and validate individual inference outputs before they trigger live network state changes, creating risks of erroneous autonomous decisions. This paper proposes the Guard Rail Validation (GRV) framework, a standardizable runtime architecture for intercepting and validating AI-driven decisions before execution. The framework evaluates decisions across multiple weighted dimensions -- including action scope, action type, service criticality, agent autonomy level, reversibility, and temporal behavioural patterns -- to determine a criticality level. Based on this level, graduated validation mechanisms are applied: execute-with-logging, bounds checking, independent agent validation, or multi-agent consensus. The framework additionally provides cross-agent conflict detection with criticality-weighted priority resolution and runtime conformance logging for regulatory compliance (e.g., EU AI Act Article 14). We present the architecture, algorithmic procedures, O-RAN deployment model, and evaluate threat coverage against known AI/ML attacks in telecommunications.

We measured quantization-induced decision-boundary changes using local logit-margin radii, first-order boundary displacement, normal variation, slice-boundary Jaccard distance, grid prediction changes, multiclass junction counts, and low-margin boundary-band flips. On the digits benchmark, 8-bit weight quantization preserved all test labels while producing boundary-mask Jaccard $0.428$ on the PCA slice; at 4 bits, accuracy remained $0.9733$, while boundary Jaccard rose to $0.970$ and median local boundary shift reached $0.0290$. Interpolation between adjacent quantization levels localized the visible reconfigurations at multiclass junctions, with 12, 34, and 17 triple-junction cells in the selected transitions. Calibration-to-test stopping reduced the digits held-out flip rate from $0.0094$ to $0.0022$ and boundary Jaccard from $0.825$ to $0.524$; the same stopping rule also reduced flips on MNIST and Fashion-MNIST. On official CIFAR-10 subsets, PTQ-W selected by accuracy gave 6-bit flip $0.0367$ and boundary Jaccard $0.184$, whereas boundary-aware stopping selected 8-bit flip $0.0083$ and boundary Jaccard $0.048$. On full CIFAR-10 with three seeds, 6-bit PTQ-W lost $0.0029$ accuracy relative to float, changed $5.3\%$ of held-out decisions, and changed $24.5\%$ of low-margin boundary-band decisions. A fixed-bit boundary-gap rounding term changed the trade-off at 4 bits by reducing boundary Jaccard from $0.457$ to $0.435$ and boundary-band pair-order flip from $0.3600$ to $0.3558$, with an accuracy trade-off; the 3-bit stress test exposed the tuning limit of this surrogate. Calibration boundary Jaccard predicted held-out boundary Jaccard across PTQ-W and optimized rounding variants with $r=0.947$--$0.994$.

Multimodal Large Language Models (MLLMs) have demonstrated remarkable abilities when analyzing images, yet translating these capabilities to few-shot image classification remains challenging. To bridge this gap, we present DeCoDe, a simple yet effective technique that enables off-the-shelf MLLMs to act as strong few-shot classifiers without any additional training. Our approach builds on the idea of few-shot classification as a set of pairwise image comparisons, decomposing the task into a set of binary decisions. Given a query image and a support image from a candidate class, the MLLM is prompted to decide whether the two images depict the same class. The logit corresponding to an affirmative response is then used as a similarity score to assign the query image to the most likely class. While this already yields good results, we show that providing additional high-level information, such as the data domain, to the model further improves performance. Our evaluation provides an extensive analysis of various inference variants on a suite of twelve datasets, six established and six newly curated few-shot benchmarks spanning across diverse domains. The results show that the proposed simple decomposition technique can turn off-the-shelf MLLMs into powerful few-shot learners, significantly outperforming current state-of-the-art few-shot methods on both standard and novel domains. Code is available at https://github.com/yunhanwang1105/DeCoDe.

For virtual humans to appear believable, they must exhibit agency and spatial awareness while interacting with their environment in ways that reflect competence and intelligence. At the core of these capabilities lies effective decision-making, which strongly shapes agent behavior. With the rapid advancement of artificial intelligence, Large Language Models (LLMs) have increasingly been explored as a mechanism to support such decision-making processes. In this work, we investigate the use of LLMs to drive decision-making in virtual humans within a simulated evacuation scenario, incorporating OCEAN personality traits into agent representations. Our goal is to evaluate how personality, expressed through language-based prompts, influences both individual behaviors and collective simulation outcomes. Our results demonstrate that LLM-driven personality profiles significantly impact agents' decisions, leading to distinct behavioral patterns across different traits. These findings suggest that heterogeneous crowds composed of LLM-guided agents can enhance the realism and variability of simulated environments, offering a flexible alternative to traditional rule-based approaches.

With rapidly improving capabilities, Large Language Models (LLMs) are increasingly used in many complex real-world tasks. Beyond requiring in-depth knowledge and reasoning skills, many of these tasks exhibit a high degree of subjectivity and require that the outputs of the model can be trusted. While a lot of progress has been made to train better models, decision-making algorithms have received less attention. In this work, we present and evaluate various uncertainty-aware decision-making algorithms based on Bayesian decision theory and risk-averse decision making on the tasks of tutoring and automatic peer reviewing. Concretely, we take uncertainty over tutoring strategies and review scores into account when generating a tutor response or review and use conformal prediction to provide guarantees over strategy and score. We find empirically that these algorithms can improve the utility of the generations but need to be carefully implemented when ambiguity is high. For example, risk-averse rules can degrade performance by optimizing for generic outputs, while Bayesian methods tend to perform better. Our work uses techniques from decision theory to improve LLM-based decision-making and outlines open challenges for the community.

Decision theory provides a formal framework for how agents should make choices under uncertainty, drawing on ideas from philosophy, probability, and causality. Despite significant progress, the field still lacks a unified modeling language, and key concepts - such as the distinction between subjective and objective elements, or what it means for a decision theory to perform well - are often left implicit. This can make it difficult to evaluate and compare competing theories, particularly in controversial cases. In this paper, we address these issues by introducing a formal framework for decision theory based on nonparametric structural equation models (NPSEMs), a well-established tool in causal inference. NPSEMs provide a unified foundation for representing agents, counterfactuals, and causal relationships, allowing for unambiguous definitions of EDT and CDT. Building on this foundation, we propose a novel decision theory - personal decision theory - which instructs agents to maximize a subjective model of their own counterfactual utility. We introduce a formal performance metric based on hypothetical interventions that enforce a given decision theory across a population - such as might be achieved through education or policy -- and show that, under certain assumptions, personal decision theory is optimal with respect to this metric. Throughout, we use the smoking lesion problem as a running example and conclude with a formal analysis of Newcomb's problem. Our aim is to provide decision theory with a clearer modeling language and firmer evaluative ground, thereby enabling more rigorous comparisons and facilitating conceptual progress in the field.

Preference-based alignment often struggles to capture the reasoning that underlies human judgments. Many evaluations rely on multiple interacting criteria, yet pairwise labels reveal only the final choice rather than the considerations that shape preferences. Inverse Constitutional AI (ICAI) improves interpretability in decision making by summarizing preferences into natural-language principles, but its single-pass explanations miss much of the nuance involved in complex decisions. We introduce Democratic ICAI (DICAI), a novel approach that gathers multiple competing rationales through structured persona debate, offering a broader and more expressive account of the factors influencing each comparison. From these richer signals, we derive clearer and more comprehensive steering principles and use them to guide preference decision modeling through both LLM-based and decision-tree judges, as well as downstream model training via constitution-induced preference labels. Experiments on creative preference benchmarks, MuCE-Pref and LiTBench, across multiple creative task categories show that Democratic ICAI yields a more faithful preference structure. It improves average preference prediction across tasks relative to deliberative prompting and principle-based baselines, while producing constitutions that LLM annotators prefer.

Value-of-information (VOI) analysis is usually conducted under a single probability measure. However, in practice, the available evidence often pins the measure down only to a set. Consequently, under a set of probability measures, VOI requires different formulations. First, we explicate a rule-specific VOI that fixes a decision rule for acting under imprecision (such as Gamma-maximin) and measures what the information is worth to a decision maker who uses that rule. Second, we derive a fixed-measure envelope that evaluates the classical VOI functional over all admissible precise measures. We formalize this distinction and explicate its consequences for the expected perfect, partial, and sample information. The expected value of perfect information is concave over the credal set. Hence, when the set is generated by finitely many measures, its lower envelope endpoint is obtained exactly from the generators, while its upper endpoint may be interior and is computed by a finite linear program. The Gamma-maximin value, in contrast, can exceed the entire envelope, so a rule-specific value is not recovered from the envelope's endpoints. A continuity bound limits how much the VOI can change as the measure varies, and we identify when the partial- and sample-information endpoints can still be obtained from the generators. Because the single-measure VOI must itself be estimated, the procedure we give combines standard estimators for it with a search over the credal set. By using a worked decision problem, we show how the two quantities separate conclusions that hold across every admissible measure from conclusions that depend on one unidentified choice of measure.

Forecasting benchmarks for retrieval-augmented LLMs routinely confound model capability with information leakage: features labeled with a target's timestamp are often not observable at the system's decision time. We study leakage-controlled equity factor ranking with a retrieval-augmented 7B open-source LLM forecaster. At each month-end from 2023-04 to 2026-03, the forecaster observes only decision-time information: lag-shifted FRED macro variables, recent macro-event summaries, and the Cleveland Fed's archived daily CPI nowcast for unreleased current-month inflation. A macro-analog retrieval module selects historical states, a critic LLM compresses them into one tactical rule, and an actor LLM maps the current state and recent rules into scores for seven U.S. equity style factors. The full pipeline obtains a median monthly Spearman rank IC of +0.154, with positive means across three non-overlapping contiguous 12-month subwindows; the mean IC remains statistically underpowered, with a bootstrap 95% confidence interval that includes zero. Non-LLM baselines under the same decision-time constraint demonstrate that a kNN macro-analog model recovers a comparable median IC, indicating that real-time inflation information and macro-similar retrieval explain much of the median signal. The LLM pipeline retains higher mean IC and a stronger long-short allocation sanity check, suggesting that any marginal benefit is concentrated in the extreme rankings that drive long-short portfolio formation. A descriptive audit of the 36 critic rules and per-month case studies appears in the appendix.

Sequential decision problems often exhibit an asymmetric evolution of information and decision flexibility: as a decision cycle unfolds, the agent receives richer information while feasible actions expire due to operational cutoffs, commitments, or resource constraints. Standard MDP formulations typically flatten this structure into stage-dependent state descriptions and action masks, thereby obscuring the nested information--action asymmetry that determines which decisions are urgent and which can be deferred. We introduce Maturing Markov Decision Processes (MMDPs), a formulation built around this information--action asymmetry. We characterize one of its key consequences through an expiring-action priority principle, which identifies the actions that must be resolved before the next stage. Motivated by this structure, we develop a structure-aware reinforcement learning framework with stage-aware policy design, expiring-action abstraction, and search-augmented learning with distillation. Experiments on a controlled multi-supplier replenishment problem, simplified cash-management environments of increasing complexity, and a production-scale simulator show that explicitly modeling this asymmetry improves learning efficiency and becomes increasingly valuable as decision problems scale.

Multi-fuel compression-ignition engines offer fuel flexibility but introduce uncertain, time-varying fuel reactivity, represented by cetane number (CN), which complicates cycle-to-cycle combustion-phasing control. This work formulates CA50 regulation under latent CN variation as a partially observable sequential decision problem and systematically evaluates controllers with increasing temporal and representational capacity, including LinUCB, history-augmented contextual bandits, observation-only DDPG, recurrent DDPG, and a proposed GRU-guided RL framework. A Gaussian-process surrogate trained on experimental multi-fuel engine data provides a controlled and reproducible evaluation environment. Results show that myopic and fixed-history bandit methods degrade under CN variation, observation-only RL suffers from latent-state aliasing, and generic recurrence is insufficient when CN evolves rapidly. The proposed framework learns a compact GRU-based representation of fuel reactivity from combustion history and conditions both actor and critic on this estimated signal rather than oracle CN. By training the policy on the same imperfect fuel-reactivity information available at deployment, the controller avoids train-deploy inconsistency in conventional online estimate-then-control pipelines. Across unseen CN trajectories, the policy achieves stable CA50 regulation with mean absolute tracking error below 0.25° CA at the training setpoint, while producing smooth, physically consistent SOI and glow-plug-power actuation. These results show that combustion control under latent, continuously evolving fuel dynamics requires more than standalone estimation or generic recurrence. By aligning fuel-reactivity inference with control policy learning, the proposed framework enables reactivity-aware decision-making using the same estimated state available during deployment.

World models have become a central abstraction in modern AI. The term now refers to several different objects: action-conditioned environment models, latent imagination models, future-video predictors, interactive neural simulators, latent predictive representations, and synthetic-data engines. Evaluation has broadened along with the term. Recent papers measure video realism, perceptual similarity, instruction following, physical plausibility, policy ranking, executability, planning success, and downstream policy improvement. This produces both metric diversity and a recurring problem of claim/evidence mismatch: papers sometimes make a stronger claim about what their model is useful for than their evaluation can establish. This paper surveys the recent literature and argues that, for models presented as world models for embodied decision-making, the more decisive issue is not whether the model generates visually convincing videos, but whether it supports reliable interventional reasoning, policy evaluation, planning, and policy optimization under intervention, policy-induced distribution shift, and long-horizon rollout. We organize the survey using an L0--L7 ladder spanning visual plausibility to policy optimization utility, noting that the levels cut across several orthogonal axes and so form an evidential hierarchy rather than a single scalar. The framework foregrounds interventional action fidelity, closed-loop rollout validity, reward/value prediction, policy-ranking agreement, optimization lift, model exploitability, and uncertainty calibration, with a minimal feasible reporting set for real-robot settings.

We present SpheriCity, an expert-grounded conversational prototype designed to support trustworthy knowledge sensemaking from sustainability reports. City-level circularity assessment reports contain rich information about materials, infrastructure, and policy interventions, yet their length and heterogeneous structure make cross-document synthesis and comparison difficult for practitioners and researchers working on circular economy initiatives. While large language models (LLM) promise faster knowledge access and synthesis, their opaque reasoning, hallucinations, and lack of source transparency introduce risks for trust and interpretability, and require verification in high-stakes sustainability contexts. SpheriCity addresses these challenges through a provenance-first conversational agent that foregrounds evidence traceability, structured synthesis, and interaction scaffolds to support exploratory querying and cross-document synthesis across sustainability reports. We conducted a formative expert review with six sustainability experts using representative queries spanning cross-city comparison, policy summarization, and recommendation-oriented tasks. Experts evaluated responses across dimensions and provided qualitative reflections on the system's usefulness for sustainability knowledge work. Our results reveal that transparent sourcing, contextual explanation, interpretability, and alignment with expert workflow strongly shape expert trust and judgments of system usefulness. This work contributes (1) a conversational prototype for sustainability knowledge sensemaking, (2) an expert-grounded evaluation framework for assessing AI responses in high-stakes knowledge domains, and (3) design insights into how provenance, uncertainty communication, and integration in workflow influence expert users' trust in AI assistance for sustainability decision support.

In hierarchical reasoning, failures often originate at intermediate decision points where the agent commits to a wrong branch without recognizing that it lacks critical information. Rather than treating clarification as an external uncertainty trigger, we propose ACTION-RATING, a formulation that places it inside the agent's action space on a shared ordinal scale with navigation, so that asking competes directly with acting at every decision point and help-seeking becomes observable at intermediate states. Two structurally distinct information-seeking modes emerge from the agent's own ratings: mandatory (no viable branch) and opportunistic (residual uncertainty despite a leading candidate). On Harmonized Tariff Schedule classification (30,000-node taxonomy, three benchmarks, 9~LLMs across 4 families), we observe a regime shift from mandatory to opportunistic clarification, with Information-Seeking Effectiveness (ISE), a local diagnostic defined as the fraction of help interactions followed by a correct next navigation step (not a final-task metric), rising from 50% to 74%. Three diagnostic contrasts fail to reproduce this structure. A separability test shows that the information-seeking pattern (mode split, ISE ranking) persists when answer quality is degraded (-18.8% accuracy), supporting an empirical separation between where an agent seeks help and the quality of the help it receives. Under the controlled answer channel, accuracy gains reach +16.2% at 10-digit; we read this as an upper bound on what better localization could unlock, not a deployment estimate.

Many Markov decision processes (MDPs) in operations research have feasible actions that are state dependent and defined implicitly by various operational constraints. These features make it difficult to use standard deep reinforcement learning (DRL) algorithms, whose action interfaces typically assume either a fixed finite action catalog or a simple Euclidean space. Motivated by a Taylor expansion of the optimal action-value function, we propose Bellman--Taylor score decoding, a framework that moves policy learning to a Euclidean score space while enforcing feasibility through an action decoder. The induced latent-score MDP then can be optimized by standard DRL algorithms without differentiating through the decoder. We provide a performance guarantee showing that the optimality gap of this approach decomposes into a structural approximation error and an algorithmic learning error. Lastly, we apply this framework to a queueing network control problem, where the policy essentially learns a state-dependent index-based dispatching rule. Numerical experiments show near-optimal performance in small instances and considerable improvements over benchmarks in larger systems.

Autonomous improvement loops are hard to trust because the improvement process is usually external scaffolding bolted onto the agent: failures go unlogged, diagnoses cannot be replayed, and promote-or-discard decisions land in a side database rather than the agent's own history. We show that an event-sourced agent runtime removes that friction and turns controlled improvement into a first-class workflow. When the agent's state is a deterministic projection of an append-only event log, failures are recorded, a run replays exactly from its log, candidate patches scope to typed pipeline seams, gates are auditable, and every promotion or discard is itself an event. We demonstrate this with Regimes, a loop on the ActiveGraph runtime that diagnoses failed evaluations, proposes a repair at a pipeline point, and promotes it only after static checks, sandbox execution, in-sample evaluation, and held-out validation. The loop is target-agnostic: the same control flow runs against different tasks through a common interface. On LongMemEval-S the dominant failure is not retrieval but reconciliation: the evidence is already in the assembled context, yet the reader answers incorrectly. Across five seeded held-out splits, Regimes discovers reader-prompt repairs that improve final held-out accuracy by +0.05 to +0.10 in four splits and +0.01 in one over-promotion split; two splits are individually significant (seed 5 unadjusted for its sequential promotion structure), and the pooled count is descriptive only, since the splits share one 500-question pool. The durable contributions are ActiveGraph as an auditable substrate that makes controlled improvement loops tractable, the held-out-gated loop it supports, the failure-regime taxonomy routing each failure to a pipeline location (whose marginal value over an unrouted baseline is the primary open question), and the prompt-as-discovery-probe hypothesis.

Decision-making under risk is typically studied through single-shot lottery choices. Yet many real decisions involve combinatorial risk, where risk arises from multiple risky components, so the lottery over outcomes is induced rather than given outright and can be costly to evaluate exactly. We introduce an investment-allocation task to study decision under combinatorial risk, where investing in a component raises its success probability and thereby reshapes the outcome distribution. Participants favor the option with the larger probability increment, and, when increments are equal, the option with the higher initial success probability. Revealing the induced probability mass function (PMF) substantially changes behavior, making participants less responsive to combinatorial-risk features and reducing choice variance. To explain these patterns, we move beyond standard benchmarks and hand-crafted hypotheses with symbolic regression to discover compact descriptive models. The discovered models rely mainly on combinatorial-risk features, such as the after-investment success probability, rather than exact evaluation of the full induced distribution. Behavior under the displayed PMF is then well explained by augmenting this model with a prospect-theoretic residual model. The results show that people navigate combinatorial risk primarily through its core features, shifting toward lottery valuation only when the induced PMF is displayed.

Autonomous robotic systems are being proposed for use in hazardous environments, often to reduce the risks to human workers. In the immediate future, it is likely that human workers will continue to use and direct these autonomous robots, much like other computerised tools but with more sophisticated decision-making. Therefore, one important area on which to focus engineering effort is ensuring that these users trust the system. Recent literature suggests that explainability is closely related to how trustworthy a system is. Like safety and security properties, explainability should be designed into a system, instead of being added afterwards. This paper presents an abstract architecture that supports an autonomous system explaining its behaviour (explainable autonomy), providing a design template for implementing explainable autonomous systems. We present a worked example of how our architecture could be applied in the civil nuclear industry, where both workers and regulators need to trust the system's decision-making capabilities.

Stochastic constrained decision-making requires optimizing performance objectives while enforcing statistical requirements such as safety or fairness. However, standard primal--dual methods struggle to update multipliers robustly under stochastic mini-batch feedback, as the noise of mini-batch gradients and constraint estimates can be directly accumulated into the multiplier memory. To address this issue, we propose Residual-Controlled Multiplier Learning (RCML), which reformulates multiplier updating as projected-pressure feedback. The central idea is to decompose the projected multiplier into an effective pressure signal for primal descent and a pressure-memory residual for finite-gain multiplier tracking. To handle heterogeneous and noisy observations, we further augment this residual-integral backbone with modular stochastic stabilization components. For the convex-affine backbone, we establish finite-gain convergence, derive a stochastic residual bound under mini-batch feedback, and show that the residual feedback law admits a local KKT-residual interpretation near regular KKT points of nonconvex problems. Experiments across optimization, allocation, and fair-ranking tasks show that RCML improves feasibility control and multiplier stability while maintaining competitive objective performance. Code is released at https://anonymous.4open.science/r/RCML-3114/.

Large language model (LLM)-based agents often make suboptimal tool-use decisions, including unsupported tool invocation and hallucinated direct responses, which may accumulate errors throughout multi-step interactions. Existing approaches mainly improve these behaviors through inference-time correction or coarse-grained reward signals based on decision outcomes and structured checklists, leaving the uncertainty characteristics of agent decisions underexplored. We observe that decision-oriented reinforcement learning tends to weaken the uncertainty separation between correct and incorrect actions, resulting in overconfident mistakes and weaker exploration signals. Therefore, we propose TRUST, which incorporates uncertainty quantification into reward design as a repulsive force for maintaining uncertainty separation, and labels lightweight key-turn annotations for unified post-training of multi-turn trajectories. Experimental results across diverse tool-use benchmarks show that TRUST consistently enhances both decision quality and agent performance while maintaining more reliable uncertainty estimates during optimization.

Reliable decision making pipelines powered by machine learning models require uncertainty quantification (UQ) methods that come with explicit safety guarantees. Conformal prediction provides such UQ by wrapping ML predictions into prediction sets, and recent work by Kiyani et al. (2025b) established that these sets can be translated into optimal risk-averse decision policies -- yet only inheriting marginal safety guarantees. We generalize and strengthen their results by (i) introducing action-conditional conformal prediction, which yields safety guarantees conditioned explicitly on each action taken by the decision maker, (ii) showing that action-conditional prediction sets serve as a proxy for the feasible decision space for risk-averse decision makers aiming to optimize action-conditional value-at-risk, and (iii) proposing a principled finite-sample algorithm based on pinball-loss minimization, connecting the framework of Gibbs et al. (2025) to action-conditional guarantees. Experiments on two real-world datasets confirm that our approach significantly improves action-conditional performance over conformal baselines.

LLMs can appear cautious in risk decision-making tasks, yet cautious-looking outputs do not necessarily indicate alignment with human decision-making mechanisms. We investigate this distinction using the St. Petersburg game as a controlled testbed, a classical paradox in which the expected payoff is infinite, yet humans typically report low, finite willingness to pay. We evaluate 28 LLMs with a structured prompt suite that includes the original game; controlled decision variants that perturb truncation, repeated play, numeric endowment, and occupational identity; a human-perspective prompt that asks models to reason as human decision makers; and paired comparisons between base models and their instruction-tuned counterparts. In the original game, most models generate finite bids, creating the appearance of human-like risk behavior. However, this outcome-level resemblance masks substantial mechanism-level differences. The controlled variants reveal that rather than maintaining human-like behavior seen in the original game, models often shift to conditionally and computationally rational behavior. Human-cue prompting and instruction tuning often lower bids and reduce some visible pathologies, but most mechanism-level response patterns remain largely unchanged. These findings show that behavioral alignment in risk decision-making can be surface-level: LLMs may produce human-like risk decisions without exhibiting human-consistent mechanisms. High-stakes evaluations of LLM decision-making should therefore move beyond outcome similarity and examine whether the alignment is supported by mechanism-level consistency.

Scientific simulators are increasingly being integrated into LLM-driven systems for high-stakes simulation-driven decision-making. However, existing frameworks primarily use LLMs to generate, calibrate, or execute simulators, treating them as black-box interfaces rather than as structured mechanistic systems that can be reasoned about. As a result, current approaches lack the ability to identify, represent, and reason about the assumptions and mechanisms underlying simulator behavior, limiting transparency, auditability, and decision justification. We introduce MechSim, a mechanism-grounded neuro-symbolic reasoning framework for executable scientific simulators. Unlike prior neuro-symbolic approaches that primarily reason over static symbolic structures, MechSim enables LLM agents to reason about the mechanisms, assumptions, and execution behavior of scientific simulators. Our framework represents simulators through a shared structured schema capturing assumptions, variables, mechanism dependencies, and execution traces. On top of this representation, LLM agents operate as constrained reasoning engines that generate structured, evidence-grounded explanations linking simulator outcomes to their underlying mechanisms. We evaluate our approach across multiple high-stakes domains and show that it improves mechanism-level explanation quality, simulator analysis, and downstream decision-making reliability.

Concept bottleneck models predict outcomes from high-level concepts detected in inputs. Although concepts provide a simple way to reap benefits from interpretability, very few datasets include concept labels. This limits researchers' ability to determine which problems are suitable for these models, isolate the factors that drive their performance or lead to failures, or uncover which algorithms perform well. In this paper, we develop synthetic benchmarks for concept-bottleneck models, focusing on their two main use cases: decision support, in which models assist humans in making better decisions, and automation, in which models handle routine tasks without supervision. Our benchmarks can generate labeled datasets while controlling for properties that affect performance, including data modality, concept choice, annotation quality, and completeness. We demonstrate how the benchmarks can be used to evaluate representative classes of concept bottleneck models. Our demonstrations show how the benchmarks can diagnose failure modes and guide follow-up testing.

Large language models (LLMs) are increasingly used for everyday health questions, including whether a user can safely take another dose of an over-the-counter (OTC) medication. Yet this common safety-relevant setting remains underexplored in existing medical QA evaluations, where correct answers require tracking dose timing, computing rolling 24-hour intake, following product-label constraints, and handling incomplete medication histories. We introduce DOSEBENCH, a focused benchmark of 81 curated OTC dosing scenarios focused on adult acetaminophen and ibuprofen use, with manually annotated gold references. We evaluate four LLMs across repeated runs using metrics for decision correctness, consistency, explanation verifiability, failure types, and confidence-related signals, resulting in 1,620 model responses. Our results show that models frequently struggle with rolling-window reasoning and ambiguity-sensitive cases and that stable or confident-looking responses can still violate dosing constraints. These findings suggest that OTC dosing QA provides a narrow yet practical testbed for evaluating temporal reasoning, constraint following, and safety-relevant uncertainty handling in medical QA.

Multi-turn user-facing agents must infer user intent from incomplete requests, collect missing information through dialogue and tools, and execute valid actions. A training trajectory records this process as an interleaved sequence of user messages, agent responses, tool calls, etc. Synthesizing sufficiently complex trajectory has become a central route to train agents: existing pipelines often increase difficulty by composing multiple user requests into longer tasks, producing write-intensive trajectories that train sequential execution. We argue that a single write decision can itself be difficult when the agent must gather and compare substantial read-tool evidence before its arguments become identifiable, a challenge that write-intensive data alone cannot address. Guided by this insight, we propose WRIT (\uline{W}rite-\uline{R}ead \uline{I}ntensive \uline{T}rajectory Synthesis), a pipeline for synthesizing multi-turn agent training trajectories along two complexity axes: the number of write decisions in a task and the evidence burden of each individual decision. WRIT first generates write-intensive and read-heavy tasks. It then diversifies user behavior instructions to reflect realistic conversational variation, and finally simulates agent-user interactions in an executable environment to produce complete training trajectories. The resulting data trains agents not only for longer task execution, but also for robust, evidence-grounded decision making under high information load. With only 2K synthesized trajectories, a 4B model trained on WRIT outperforms GPT-5.1 no-think on $τ^2$-bench and substantially reduces inference-time token usage, showing that compact SFT data can convert part of expensive test-time reasoning into efficient agent behavior.

Hard constraints are usually treated as terminal vetoes: once a candidate violates a requirement, the learned rule rejects it and any repair is handled outside the decision semantics. This misses a common deployed regime in which the system already knows a finite menu of modifications, such as adding a ticket option, changing a configuration, or requesting an available service upgrade. Existing constraint-learning, soft-relaxation, and recourse methods address nearby problems, but they do not learn whether an option should be repaired before being vetoed. We introduce Repair-Augmented Constraint Learning (RACL), a contextual decision framework that lifts known repair operators into the classifier semantics. A candidate is accepted when an affordable repair makes it feasible and preferred enough; otherwise the system returns a structured rejection credit and, when applicable, a repair plan. This repair-before-veto view strictly generalizes no-repair HASSLE-style semantics, reveals an irreducible false-veto gap for terminal-veto rules, separates binary-label non-identifiability from decision-rule learnability, and gives capacity and calibration bounds for the observed-feasibility shared-weight setting. Across controlled and DB1B-derived benchmarks, RACL recovers the intended credit and repair structure. On the hardest raw-data-derived tier, validation-selected RACL reduces false vetoes to 10/4039 (FVR 0.0025), versus about 1064/4039 for the strongest repair-search black-box baseline, while making the FVR/EDR trade-off explicit.

Industrial anomaly detection has historically been a unimodal task. Recent multimodal vision-language models have produced systems that admit textual input alongside the image and are presented as enabling text-guided zero- and few-shot inspection. Yet these methods are evaluated with protocols inherited from unimodal benchmarks that hold the textual condition constant and therefore cannot measure whether language conditions the decision; whether reported gains reflect text guidance or strong pretrained visual features remains open. We introduce Text-Guided Anomaly Detection (TGAD), a structured benchmark that progressively increases the functional role of language across three scenarios: a controlled prompt-sensitivity setting on MVTec AD; a component-tagged extension of MVTec AD that requires the model to restrict its assessment to an instructed part; and the new Assembled Panel Dataset (APD), a realistic industrial setting that requires both defect-type and component-location knowledge. We evaluate one representative model per paradigm: generative large vision-language, training-free discriminative, and embedding-adaptive discriminative. In all three, the textual interface conditions the decision only superficially: prompt content is absorbed unless the object noun is removed (the generative model's I-AUROC drops from 97.4 to 82.6); component-level instructions do not constrain the decision once defects outside the instructed part are admitted as normal (from 90.3 to 66.3); and when both combine on APD, image-level discrimination collapses below the MVTec level, in one case below chance (71.2, 50.5, 31.5). These results suggest that standard benchmarks overstate the text-guided capabilities of current multimodal anomaly detection systems, and that a protocol of this kind is a prerequisite for models that can be reliably controlled through language for industrial deployment.

Standard machine learning pipelines often admit many near-optimal models. These "Rashomon sets" pose a range of challenges and opportunities for uncertainty-aware, robust decision making. They allow users to incorporate domain knowledge and preferences that would otherwise be difficult to specify directly in an objective, and they quantify diversity among valid models for a given training dataset and objective function. However, computation of Rashomon sets, even for simple, interpretable model classes such as sparse decision trees, continues to require immense memory and runtime resources. We present PRAXIS, an algorithm to approximate this Rashomon set with orders of magnitude improvement in runtime and memory usage. We validate that PRAXIS regularly recovers almost all of the full Rashomon set. PRAXIS allows researchers and practitioners to scalably model the Rashomon set for real-world datasets. Code for PRAXIS is available at https://github.com/zakk-h/PRAXIS

Reasoning-based robotic policies using large language and vision-language models achieve strong semantic planning capabilities but mostly suffer from a high inference latency that limits practical real-time deployment. In this work, we observe that robotic reasoning workloads contain substantial temporal redundancy, where consecutive observations frequently produce identical actions and subgoals. Based on this insight, we present REIS, a human cognition inspired robotic decision-making framework that minimizes unnecessary reasoning while preserving semantic adaptability. REIS combines lightweight scene gating, KV-steered affordance routing, and deliberative reasoning to accelerate robotic control under embodied constraints. Experiments on ALFRED, and real-world robotic tasks demonstrate that REIS significantly suppresses reasoning overhead while maintaining competitive task performance.

Recommender systems may operate under multiple, competing objectives. For example, audience reach, cultural values, public service mandate, and operational constraints must be balanced in editorial decisions of public service media. Existing approaches relying on fixed combinations of objectives or Pareto-based optimisation do not adapt to changing priorities across situations. In this paper, we propose Contextual Scalarisation Thompson Sampler (CSTS), a multi-objective contextual bandit method that learns to weight objectives as a function of the observed context. We evaluate CSTS on real programming data from Radio Télévision Suisse, the Swiss national broadcaster, showing improved contextual relevance and better alignment with expert curation practices compared to fixed weight and standard contextual bandit approaches.

Many theories of decision making -- planning, reinforcement learning, causal intervention, online learning, and game-theoretic equilibrium -- turn local information into globally coherent behavior. This paper proposes a common categorical formulation: a Universal Decision Learner (UDL) extends a partially specified decision functor from observed contexts to new contexts by a pair of universal constructions. Left Kan extensions express rollout, aggregation, and candidate generation; right Kan extensions express consistency, constraint satisfaction, and fixed-point semantics. The central claim is not that every decision problem has the same algorithm, but that many decision formalisms instantiate the same universal problem: extend local behavioral data canonically, then characterize the globally coherent extensions. We give the abstract UDL construction, prove its universal comparison property, define Kan-invariant behavioral equivalence and minimal abstractions, and show how Bellman equations, planning recursions, causal interventions, online regret, and equilibria arise as special cases. The supplementary material develops the reinforcement-learning specialization in more detail.

Frontier reasoning models are produced by posttraining base language models with reinforcement learning. Recent work has challenged this by showing that sampling from a sharpened version of the base model's distribution, a so-called power distribution, elicits comparable reasoning without additional training, curated datasets, or verifiers. However, making this method practical requires efficiently sampling from the power distribution. A sampler needs to "mix" to the power distribution, which necessitates moving between modes of the target distribution; intuitively, e.g., trying different reasoning strategies. The samplers proposed in prior works repeatedly select a "cut" position in the current reasoning trace uniformly at random and resample the suffix from that position onward. However, reasoning traces typically contain a few consequential decisions (e.g., the choice of proof strategy or algorithm), and we observe that a uniformly chosen cut tends to rewrite local details rather than revisit decision points. We introduce an algorithm (Entropy-Cut Metropolis-Hastings) that uses the base model's next-token entropy as a proxy to identify key decision points and resample from those positions. We empirically verify that entropy jumps are a useful proxy for decision points and, in a stylized model of reasoning, prove that our method's mixing time scales with the number of decisions in a trace rather than with the number of tokens, which can be much larger. Across MATH500, HumanEval, GPQA Diamond, and AIME26, our method consistently improves over baselines and RL-trained models.

Robust decision-making requires compression. A system that forms a rich support state cannot usually preserve its full structure at the point of action. It must retain only those distinctions needed to act, verify, abstain, or defer under the current consequence geometry. This paper formalizes support sufficiency as action-sufficient compression. Let $H$ denote a full support state, $\mathcal{A}$ a finite action set, and $Z$ a consequence geometry specifying payoff structure. For fixed $Z$, the coarsest exactly action-sufficient compression is the quotient of support space by policy equivalence. Two support states may be merged exactly when they require the same optimal action. This clarifies why content-only and scalar-confidence-only arbitration fail whenever their induced partitions cross action boundaries. Approximate sufficiency is then defined by bounded expected policy regret. In the finite single-cycle setting, this yields a rate-regret problem with source $H$, reproduction alphabet $\mathcal{A}$, and distortion given by consequence-sensitive regret. The optimal stochastic action channel inherits the standard rate-distortion Gibbs form, applied here to support states with regret distortion. The contribution is interpretive: action adequacy is distinguished from reconstruction fidelity, information-bottleneck prediction, and rational inattention. Robust single-cycle arbitration does not require preserving all support, but it does require preserving the distinctions that consequence geometry makes action-relevant.

AI-augmented classrooms generate rich teacher and student feedback before graded outcomes become available, yet these signals can be difficult to translate into timely instructional decisions. We propose an interpretable decision layer: a transparent mechanism that ranks course topics requiring attention without using grades or post-hoc outcome labels. The approach combines three signals: student learning difficulty prevalence, disagreement between learner self-reports and observed difficulties, and unresolved teacher concerns. The output is a ranked set of topic priorities with per-topic decision records explaining each ranking. In one graduate CS course offering ($n=5$ instructor interviews; $n=279$ survey responses), prioritized topics aligned with instructor concerns (top-5 overlap 3/5; Spearman $ρ=0.80$) and student-reported topic difficulty ($ρ=0.46$, $p=.048$). Multi-signal integration also surfaced learners not identified through individual signal sources alone (AUC $=0.96$ vs. $0.91$ for gap prevalence alone). Reflective thinking, help-seeking, and self-efficacy provided additional evidence that student behavioral signals align with learning-related constructs. While preliminary, these findings suggest that transparent coordination mechanisms may help support human-AI co-agency when feedback is incomplete.

Conversational artificial intelligence (AI) provides an efficient and convenient gateway to information access. However, it can cause overreliance when users blindly trust AI and accept its answers without fact-checking. Information search increasingly follows a hybrid interaction paradigm that combines conversational AI with web search, making fact-checking easier. In this paper, we examine whether this interaction paradigm is effective in curbing reliance. We further investigate the underlying factors (e.g., digital literacy and conversation warmth) that drive users to verify AI answers. We conduct a mixed-subjects question-answering experiment where participants interact with either a warm or a neutral chatbot. Our findings reveal that reliance persists despite users having access to both conversational and web search. The decision to verify is driven primarily by existing user perceptions (e.g., prior trust in chatbots) rather than answer properties, with some users fact-checking regardless of the context and others trusting chatbots by default. Warm conversational style has an indirect yet critical influence on reliance by increasing agreement with the chatbot when it is incorrect. Consulting additional AI sources predicts higher accuracy, while traditional web search does not. Our study extends overreliance research by: (a) demonstrating its persistence despite access to fact-checking, (b) identifying verification behavior as user-dependent, and (c) revealing conversational warmth's indirect effect on overreliance with implications for designing trustworthy conversational search systems.

Large Language Models (LLMs) are increasingly deployed in high-stakes decision-making settings such as legal reasoning, where consistency under factually equivalent inputs is critical. However, we find that fact-preserved but differently framed inputs can significantly destabilize LLM decisions. To systematically investigate this problem, we introduce Fragile, a large-scale benchmark that isolates fact-preserving semantic framing across three controlled dimensions: value-tinted narration, temporal slice, and narrative vividness. Our experiments reveal a high susceptibility of LLMs to framing, with an average decision flip rate of 28.6%. We find that simple prior prompt-level and activation-level interventions not only fail to suppress framing sensitivity but actively amplify it. We therefore propose Valign, a representation-level method that explicitly targets these framing dimensions by anchoring decisions to a stable value prior, steering hidden states toward the model's value-consistent direction, and projecting out temporal-vividness-sensitive directions from the model's hidden states. Valign consistently reduces framing-induced decision flips, demonstrating that robust mitigation requires directly targeting the internal pathways in which framing operates.

Clinical foundation models are evaluated with factual or exam-style medical QA, but treatment decisions must change when patient context changes. We introduce ClinPivot, an auditable treatment-decision benchmark built from biomedical relations and pivoted patient contexts. ClinPivot asks whether models change treatment choices when new clinical constraints shift the action space. We find that strong medical QA performance does not reliably predict decision-making performance: frontier models and task-adapted Qwen variants often fail to change decisions correctly, and model rankings shift across evaluation regimes. Decision-structured supervision improves pivot-sensitive decision-making and medical QA under matched knowledge budgets, while lightweight replay reduces losses in general assistant ability.

Humans increasingly make decisions with AI assistance; for example, doctors may follow AI-recommended diagnostic tests and base their diagnoses on the results. A natural question is which tests should AI recommend to balance short-term decision quality and long-term human learning when different features (e.g., test results) are correlated. While prior work establishes that stationary policies that recommend the same tests repeatedly are optimal when features are independent, we prove that feature correlations lead such policies to perform arbitrarily poorly. Instead, we prove that any optimal policy must follow an explore-then-commit structure; initially, the AI should offer diverse tests so humans can learn accurate feature coefficients, then the AI should commit to a single set of tests, with exploration length that depends on the degree of feature correlation. We prove that computing the optimal policy is NP-hard and derive a dynamic programming-based algorithm that finds the optimal policy for finite horizons. We additionally develop an approximation that plans for shorter horizons and appends a stationary suffix, achieving near-optimal performance. Our empirical results complement our theory by showing that stronger feature correlation leads to longer exploration phases.

Introduction. Early detection of malignant skin lesions is critical for prognosis, yet dermatologist shortages in Russian regions limit screening coverage. Mobile dermoscopy clinical decision support systems (CDSS) offer a promising approach, with model interpretability and standardised patient routing remaining key barriers to adoption. Aim. To develop a quantitative interpretability assessment method for cascade deep learning models and a three-zone patient routing algorithm, and to conduct a preliminary single-centre prospective clinical validation of the Melanoscope AI CDSS in Russian outpatient practice. Material and methods. Two-stage cascade classification of dermoscopic images; attention map visualisation (attention rollout for ViT and Swin; Grad-CAM for ConvNeXt and EfficientNetV2); quantitative IoU-based agreement assessment between activation maps and expert annotations; prospective single-centre validation across four "Melanoma Day" sessions (Orel, Russia, June 2025 - April 2026). Results. On 176 patients: agreement with expert assessment 88.6%; no false negatives among 5 malignant lesions (95% CI: 47.8-100.0%); specificity 88.3%. Three melanomas and two basal cell carcinomas were histologically confirmed; six dysplastic naevi placed under follow-up. Mean IoU (n=180): ViT - 0.69; Swin - 0.64; ConvNeXt - 0.53; EfficientNetV2 - 0.51. Routing thresholds: P<0.15 / 0.15-0.50 / >=0.50. Conclusion. No false negatives were observed; specificity was 88.3%, supporting screening use. The integrated cascade classification, attention map visualisation with IoU assessment, and three-zone routing provide reproducible, interpretable clinical decision support adaptable to varying resource levels.

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.

Embodied Question Answering (EQA) connects perception, reasoning, and interaction within embodied environments. However, existing datasets and benchmarks remain fragmented, each focusing on a limited subset of reasoning skills such as spatial understanding or procedural reasoning, without offering a unified large-scale framework for comprehensive evaluation. We present EQA-Decision, a large-scale embodied QA dataset that systematically covers four complementary dimensions of embodied reasoning: static scene construction, spatial understanding, task dynamics reasoning, and instant decision. The dataset contains over four million question-answer pairs with hierarchical annotations across diverse embodied scenarios. In addition, we develop RoboDecision, a strong baseline model aligned with the EQA-Decision Benchmark, providing a unified framework that jointly evaluates perception, reasoning, and action-level decision-making in embodied environments. Results demonstrate that EQA-Decision effectively benchmarks and enhances VLM capabilities in spatial and interaction reasoning, providing a solid foundation for advancing embodied intelligence research.

The process of decision-making in football is characterized by a complex interplay between spatial positioning, opponent pressure, and player intent. This work introduces a Graph Neural Network (GNN) framework designed to predict Receiver Selection, the optimal passing target, by modeling on-field interactions as dynamic graphs. Each player is represented as a node with positional and contextual features, while potential passing lines form weighted edges characterized by distance, angle, and pressure metrics. A Message-Passing Neural Network (MPNN) has been developed and trained using a combination of tracking data and event data from professional matches, synchronized through a robust pipeline based on an optimized version of the Needleman-Wunsch Algorithm. The model achieves competitive accuracy in identifying the actual chosen receiver and state-of-the-art accuracy within its top three suggestions. Our model further offers quantification of each option's likelihood, threat, and creativity, enabling performance analysts to evaluate over 1,000 passes in seconds.

Large Language Models (LLMs) and Multimodal LLMs (MLLMs) have demonstrated immense potential in autonomous driving (AD) by offering human-like reasoning and open-world generalization. However, the excessive computational overhead and high inference latency of these massive models severely hinder their deployment in resource-constrained AD systems. To address this challenge, we propose a novel decision-making framework utilizing a lightweight confidence-aware language model, which bridges the gap between complex multimodal intention reasoning and efficient inference. Specifically, we design a multi-agent collaborative workflow, comprising action voting, confidence assessment, and summarization agents, to generate high-quality, confidence-annotated decision demonstrations via explicit Chain-of-Thought (CoT) reasoning. These demonstrations are then distilled into a lightweight language model featuring a dual-head architecture, enabling the joint prediction of decision probabilities and the generation of textual rationales. The distillation is realized via a confidence-aware fine-tuning strategy coupled with Retrieval Augmented Generation (RAG) to enhance the model's adaptability and data efficiency. Comprehensive closed-loop experiments on the nuPlan benchmark demonstrate that our approach achieves state-of-the-art (SOTA) success rates in both regular and long-tail scenarios while maintaining low inference latency.

Steerable pluralism requires a model to faithfully represent one specified perspective. Organizations are a natural setting for this demand, since they deploy LLMs to make decisions that must reflect their own policy. Yet, most existing work fixes that perspective at the level of individuals or demographic groups. We rely on a decision-policy capturing method to measure process alignment in organizational settings, assessing whether an LLM faithfully reproduces the organization's decision policy rather than merely reaching the same conclusions. We find heterogeneity along two axes. Across models, baseline alignment varies strongly and tracks neither pricing nor general benchmark performance. Across organizations, the structure of alignment changes. In ECHR Article 6 decisions, process alignment predicts output accuracy ($r = 0.85$, $p < .001$), and making the organization's past decision policy explicit improves poorly aligned models. In consumer credit decisions, process alignment is low overall but varies more than output accuracy, and the models resist adopting the organization's weighting of protected attributes. Because historical credit decisions encode potentially discriminatory patterns, higher alignment there is not always desirable. Process-level measurement is therefore necessary, and depending on whether the target policy is normatively desirable, the same procedure can calibrate or audit a model. Deciding which policy to align to, and whether higher alignment is feasible or desirable, makes organizational alignment a pluralistic problem in its own right.

Formalizing legal provisions promises machine-accessible law and automated legal reasoning, and recent LLMs make it tempting to generate such formalizations directly from statutory text. However, any formalization makes implicit interpretive choices whose consequences are hard to anticipate, especially if an LLM is the author. We present a method for systematically comparing different formalizations of the same legal provision by their inferences on individual cases. Given multiple formalizations of a provision, we match them at the node level, derive a shared interface for each pair from the matching, and use a SAT solver to enumerate the edge cases on which any two formalizations disagree. Selected edge cases are then verbalized into concrete factual scenarios that a legal expert can examine and act on. We apply our method to formalizations of ten EU provisions generated by nine frontier LLMs. We find that behavioral divergence between formalizations is essentially uncorrelated with their structural agreement and that the verbalized cases reveal qualitatively distinct types of disagreement, including divergences that mirror genuine controversies in the legal commentary.

Classical noisy-label theory predicts that downstream performance under weak supervision is bounded above by the labeler's accuracy, implying a sharp crossover: once a gold-trained classifier matches the labeler, weak labels stop helping and start hurting. The prediction is theoretical; what is missing is a benchmark calibration that turns it into an instance-level statement for modern foundation-model labelers. We provide such a calibration for BiomedCLIP-generated weak labels on three medical-imaging benchmarks (PCAM, ISIC, NIH-CXR) and six downstream architectures spanning an 11x parameter range. The crossover predicted by theory appears at ng~100 on PCAM, 20-50 on ISIC, and 250-500 on NIH-CXR; weak labels above the crossover degrade AUC by up to -0.10. The location is architecture-invariant for four of five pretrained architectures, and a within-family DenseNet sweep (2.5x parameters, identical pretraining) supports the view that the labeler, not the student, is the dominant constraint. The calibration in turn produces a decision rule operable from 10-20 gold labels: compare gold-only AUC to VLM accuracy on the user's gold set. A structured-vs-random noise sign flip on NIH-CXR shows that the rate-only formulation of the bound is incomplete and identifies a concrete refinement (label-space projection) that future benchmarks can be designed to test.

Decision trees assign identical confidence to instances near and far from each split threshold. We introduce ternary decision trees, which augment each split node with an uncertainty zone of half-width delta. A decision-theoretic framework characterises the optimal zone width delta* as the solution to a node-local cost-minimisation problem; four formal properties are established: accuracy decomposition, a sufficiency condition for decided accuracy improvement, an exact efficiency characterisation (eta = Dec-Acc minus Acc_u, the accuracy gap between decided and boundary-uncertain predictions), and asymptotic consistency of the margin method. Instances within the zone receive predictions by weighted blending of both child subtrees and are flagged as boundary-uncertain. We propose and evaluate five delta-estimation methods: quality-plateau (plateau width of the split criterion curve), class-overlap (empirical class-distribution overlap), gain-ratio (split quality relative to split entropy), node-bootstrap (threshold variance under node-level resampling), and margin (SVM-inspired distance to the nearest cross-class training example). All methods reuse statistics already computed during standard CART split finding, requiring no external noise specification. Evaluated across 71 of the 72 OpenML-CC18 datasets with 5-fold cross-validation, all five methods with probabilistic routing significantly outperform standard CART on decided accuracy (Wilcoxon signed-rank, p < 0.001). The margin method achieves the best efficiency (0.104 accuracy gain per unit flagging rate), wins on 42 of 72 datasets, and requires zero hyperparameters. Analysis on Breiman synthetic benchmarks confirms margin is self-calibrating on clean data. On mammography, node-bootstrap achieves +0.71% decided accuracy by flagging 10.8% of cases as boundary-uncertain.

Medical RAG systems in high-risk QA settings are often evaluated through a single answer-or-abstain decision, but mixed evidence may support one claim, require conditions for another, and contradict a third. We study claim-selective certification: each response is decomposed into verifiable claims, scored against retrieved evidence, and mapped by an intent-aware selector to {full, partial, conflict, abstain}. On the primary weak-label certificate protocol, whose real-source-only dev/test rows cover the naturally occurring non-abstain actions, the full system records UCCR=0.0000, PAU=1.0000, PAU Precision=0.9901, and action accuracy=0.9204 on dev (n=314), and UCCR=0.0000, PAU=0.9967, PAU Precision=0.9739, and action accuracy=0.8997 on test (n=319). UCCR measures unsupported-claim risk within the certificate definition, and a source-missing counterfactual slice evaluates abstain under empty evidence. Shortcut controls quantify the action-label prior explained by source and intent metadata, while source/evidence-novel slices characterize transfer boundaries. The resulting interface separates action-label prediction from evidence-linked claim selection under mixed evidence.

As large language models (LLMs) increasingly shape how users form, refine, and extend their goals, attributing contributions in human-AI collaboration becomes critical for users calibrating their own reliance and for evaluators assessing AI-assisted work. Yet existing methods focus on final artifacts, missing the process through which goals themselves are jointly shaped. We introduce a goal-level attribution framework, CoTrace, that decomposes explicit goals into verifiable requirements and traces both direct contributions and indirect influences across dialogue turns. Applying CoTrace to 638 real-world collaboration logs, we find that while models account for only 11-26% of goal-shaping contribution, they contribute substantially more on introducing lower-level concrete requirements, and make various kinds of indirect contributions. Through controlled simulations, we show that interaction design choices significantly affect model goal-shaping behavior. In a user study, exposing participants to goal-level analyses shifts their perceived contributions by nearly 2 points on a 5-point scale, revealing systematic miscalibration in how users understand their own AI-assisted work.

Machine unlearning aims to remove the influence of specific training data from a model while preserving reliable behavior on the remaining data, making reliable prediction and uncertainty estimation essential for evaluation. Calibration is commonly used as a proxy for reliability in language models, but low calibration error does not necessarily imply reliable decision rules, as models may rely on spurious correlations while remaining well calibrated. We investigate this gap in generative language models using the multiple-choice question-answering evaluation protocol on the TOFU benchmark, measuring probabilistic reliability with calibration metrics (ECE, MCE, Brier) and decision-rule reliability via attribution-based shortcut detection with Integrated Gradients and Local Mutual Information. We find that fine-tuned models achieve low calibration error (ECE ~ 0.04) compared to pretrained models (ECE > 0.5), and models after unlearning retain similarly low calibration despite reduced accuracy on the forget split, while attribution analysis shows increased reliance on correlation-based tokens. These results demonstrate that good calibration can coexist with shortcut-based decision rules after unlearning, extending the reliability paradox to the machine unlearning setting.