Tool-use benchmarks generally evaluate whether an agent completes a workflow using appropriate tools and valid arguments. However, feasibility alone is insufficient in real-world decision settings such as route planning and fleet dispatch. Individual choices interact through shared constraints and costs, so a feasible solution may still be substantially suboptimal. This raises a harder question: can an agent turn information gathered through tools into a globally optimal decision? We introduce AlgoWorlds, a benchmark that transforms formally specified combinatorial optimization problems into partially observed decision environments with verifiable global optima. Each environment contains a hidden instance observed only through task-specific information tools, after which the agent commits to one structured decision evaluated for feasibility and optimality. AlgoWorlds contains 240 environments covering ten combinatorial optimization families and four workload levels. Family-specific deterministic programs generate the instances, exact algorithms certify their optima and determine workload levels, and two structurally different tool interfaces present each underlying instance. We evaluate seven leading LLMs, including Claude Opus 4.8 and GPT-5.6 Sol. Achieving global optimality remains highly challenging: although leading models produce feasible decisions in most cases, the best-performing model reaches exact optimality in only 38.61% of cases. Even when agents collect sufficient information to reconstruct the hidden instance, most failures end in feasible but suboptimal decisions. The challenge therefore extends beyond information acquisition to information integration, global constraint reasoning, and decision verification. The project homepage is available at https://xzx34.github.io/AlgoWorlds/, and the code is available at https://github.com/xzx34/AlgoWorlds.
Intent misinterpretation during vehicle interactions causes recurring planning failures. We study a decision layer in which a language-guided intent module reads structured descriptors, computes a smoothed intent-geometry divergence score, and gates the planned maneuver before commitment, upstream of a corridor envelope. On a replayed off-road departure and four crash clips under a frozen, disclosed implementation, gating is the only layer that repairs the plan: on the main case it fires 72 ms after the drift onset but 161 ms before the corridor exit, keeping the trajectory in the corridor in all ten replays. The first calibration draws nine false triggers in 5.9 minutes, each from scoring uncertainty as half a conflict; a preregistered redesign treating uncertainty as abstention cuts this to 0.341 per minute. Two ablations bound the model's contribution: the full score detects fastest on four of five failures under the deployed eligibility, three of five against the unvetoed rule (000871 by one cycle; 000228 by a pre-onset fire on an uncertain stretch that five clips cannot classify as signal or coincidence; dropping the confidence term costs two detections), while on in-domain tracks at equal false positives the geometric rule more than triples its detection. The evidence supports the gating mechanism; the model's demonstrated roles are the fastest detection on these failures and an uncertainty veto on the geometric rule.
Pairwise reciprocal matrices are fundamental to the Analytic Hierarchy Process (AHP), a decision-making model. While the Direct Least Squares (DLS) method provides an intuitive mechanism for deriving priority vectors without complex transformations, the DLS provides multiple solutions. Under high levels of inconsistency, such as cyclic contradictions, this non-convexity yields multiple distinct global minima, resulting in unstable priority rankings that critically depend on initial algorithmic guesses. To overcome this structural deficiency, this paper introduces the Anchored Regularized Direct Least Squares (ARDLS) optimization model. ARDLS integrates uniquely determined established prioritization operators, such as normalization techniques, the Eigenvector method, Singular Value Decomposition, Cosine Maximization, and the Pseudo-Inverse Gram Matrix (the closed-form solution of Weighted Least Squares), as theoretical anchors within a regularization penalty. This integration systematically breaks mathematical symmetries, tilting the optimization landscape to guarantee convergence upon a single, unique global minimum. Comprehensive numerical experiments and simulations validate that the ARDLS framework successfully reduces root mean square error among established priority operators, while guaranteeing strict mathematical uniqueness. The proposed ARDLS may be the ideal alternative for the AHP applied to many application domains.
Systems that ask a language model to reach a conclusion from many sources usually concatenate them into one prompt. This conflates two operations with different requirements. Interpreting a source rewards capacity and context. Combining interpretations rewards fixed arithmetic, comparability across instances, and the option to return nothing. Once separated, the design problem becomes the interface between them. We propose a four-field evidence tuple (hypothesis, reliability bucket, rationale, provenance) and show that fixing it determines both halves. The separation also reveals a failure mode in how such systems combine, which we call count-scale drift. Thresholding a sum of unnormalized weights is exactly posterior thresholding, but at an operating point that slides with the number of sources consulted. The slide grows with reader reliability. When source reliabilities differ, the vote rule and the posterior order instances differently, and no threshold reconciles them. Pooling calibrated log-likelihood ratios addresses both problems. The fix is arithmetic rather than architectural, and applies to a class of rules beyond language models: score-summing triage engines, diagnostic panels scored by counting positives, and additive multi-signal detectors. We then instantiate the principle twice on one longitudinal corpus, once after outcomes resolve and once before. The same partition helps in both, at different granularities: over reading in the first, over learning capacity in the second. There, a small sequence encoder on an easy auxiliary objective plus a tree ensemble carrying the censored survival loss reaches 0.921 AUPRC against 0.805 for a hand-crafted baseline. We separate what transfers from what must be re-estimated per domain, and state five predictions that would falsify the framework, three negative results, and which comparisons remain confounded.
Tool-use LLMs are increasingly asked to act on users' behalf, but existing benchmarks usually focus on profile recall, style imitation, generic tool use, or response-level personalization. We introduce UserToolBench , a benchmark for personalized decision making in tool-use LLMs. UserToolBench tests whether a model can infer latent user preferences from interaction history, recognize when clarification is needed, and produce user-aligned tool-call trajectories under incomplete information. The benchmark is built from privacy-sanitized real interaction traces and combines structured persona profiles, public API-style tool ecosystems, and long-horizon multi-turn trajectories. It includes 10 user profiles, 36 tool sets, 1,065 turns, 170 unique tools, and evaluation-focused task types covering lack-of-information, single-tool, and multi-tool settings. Experiments with strong tool-use LLMs show that current models still have difficulty with personalized delegation. Multi-tool coordination, missing-constraint inference, and long-horizon behavioral consistency remain major bottlenecks. These results suggest that personalization evaluation should move beyond asking whether outputs sound user-specific and instead ask whether LLMs make correct decisions for the users they represent.
Modern AI is no longer a single model but an ecosystem: classical ML predictors, deep and multimodal models, large language models, and agents, each trained and tuned over different data sources and each producing outputs at scale that become inputs to the others. Operating such an ecosystem is fundamentally a data integration problem - the knowledge it depends on is fragmented across dozens of heterogeneous, independently governed sources that must be reconciled and continually maintained. Yet integration alone is not enough. The predictions these systems make are shaped by many interacting factors, and the events, decisions, and variables that drive an outcome are routinely entangled with the ones that merely accompany it; treated as a basis for action, such correlational signals invite confounded decisions. This becomes acute once agents act autonomously: to be trustworthy and reliable, an agent must anticipate the consequences of its actions, not merely extrapolate from what has co-occurred before. Causal reasoning is what closes this gap, distinguishing the drivers of an outcome from its correlates, and enabling prescriptive and counterfactual analysis over the ecosystem's data. We therefore argue that the integrated ecosystem needs an explicit causal layer, and we propose to build it as a shared, persistent, queryable Causal World System (CWS).
Causal perception occurs when agents with competing Structural Causal Models (SCMs) of the same system infer different probability distributions, including the hypothetical distributions implied by each agent's SCM under the same set of interventions. It shapes how agents reason about the system and how they perceive its fairness. Causal perception is a promising probabilistic framework, but it has remained purely theoretical. This work provides the first implementation of the causal perception framework of Álvarez and Ruggieri (2025). We operationalize structural (agents disagree on the causal graph) and parametrical (agents agree on the causal graph but disagree on its weights) causal perception. We design algorithms for computing interventional and counterfactual distributions and propose suitable distance measures to quantify the disagreement. Using the German Credit dataset, we illustrate how causal perception affects accuracy and fairness in a multi-expert decision setting. We show that the perception verdict is sensitive to the choice of distance metric and threshold. We also show that causal perception changes fairness assessments and threshold-based decisions. Bias proves situated with respect to the agent's SCM, demonstrating that competing worldviews in fairness problems cannot be ignored.
LLM-agent evaluations often produce task outcomes long before the full benchmark run is complete. A partial score is tempting to report, but it does not show whether the observed tasks support the same conclusion as the completed evaluation. Early tasks can omit important parts of a benchmark, running cheaper tasks first can distort the observed sample, and a rule that decides only easy pairs can appear accurate while leaving many comparisons unresolved. We introduce ParEvalLayer, a decision layer that reads paired outcomes for two agent systems and a comparison policy chosen in advance. For each partial run, it records whether the tested agent system is better by the required amount, is not better by that amount, needs more evidence, or should abstain. We evaluate ParEvalLayer by replaying completed public benchmark data as if each evaluation had stopped earlier. At each point, ParEvalLayer applies the policy using only the outcomes observed so far; if it reaches one of the two comparison judgments, we check whether that judgment matches the completed data for the same system pair. With the main comparison rule, three of the public benchmarks reach the same decision as the completed evaluation after observing only 15% to 25% of task outcomes. Other benchmarks require more task outcomes. This variation shows why a partial score alone is not enough: reports should also state the decision rule and how many comparisons remain without a decision.
In dynamic multi-mode project scheduling, activities have alternative execution modes and uncertain durations, while precedence relations and limited resources constrain their execution. Heuristic priority rules support fast online decisions, but their design requires substantial domain expertise. Genetic programming (GP) hyper-heuristics can automatically evolve such rules. Large language models (LLMs), meanwhile, provide a flexible interface for interpreting scheduling information and explaining decisions. However, zero-shot LLM decisions may lack domain knowledge, consume many tokens, and vary across repeated queries. GP-evolved rules therefore provide a potential source of scheduling knowledge for guiding LLM decisions. Unlike existing LLM--GP hybrids that use LLMs to support heuristic evolution, we transfer knowledge in the reverse direction, using knowledge extracted from high-quality GP rules to guide an online LLM decision maker. We extract knowledge from high-quality GP rules and inject it through Feature Selection, Feature Hint, Rule Reference, and Rule Follow. These mechanisms are evaluated in terms of scheduling performance, token consumption, decision stability, and the feature focus expressed in generated rationales. GP-derived guidance generally improves the unguided LLM, but its representation matters. Simplifying the decision context or supplying explicit decision logic is more effective than highlighting important features. Feature Selection offers the best token efficiency, whereas Rule Follow achieves strong performance at greater token cost. Guidance also improves decision stability and changes the features expressed in generated rationales.
Chiara Marcoccia, Walter Quattrociocchi, Valerio Caprarocs.AI cs.CY cs.HC
Knowing when to say "I don't know" is fundamental to human judgment, yet AI assistants offer a fluent answer to almost any question. In five experiments (N = 3,132; four preregistered, one direct replication), participants answered difficult questions and could always decline to respond. We engineered the questions so that AI advice was wrong, separating AI use from its accuracy. Merely having access to AI nearly eliminated participants' willingness to suspend judgment, and this held whether the advice was actively requested or simply displayed. Consequently, participants answered more questions but were correct about a third as often as when AI was unavailable-yet their confidence nearly doubled. Incentivizing accuracy and penalizing inaccuracy led participants to seek and follow AI advice less, answer more accurately, and suspend judgment more often, though still far less than when AI was unavailable. As AI suggestions grow ubiquitous and unsolicited, they may not simply affect answer accuracy; they may even alter the metacognitive threshold at which people decide whether they know enough to answer.
Pairwise comparison (PC) via pairwise reciprocal matrices (PRMs) is central to the Analytic Hierarchy Process (AHP). Although the traditional eigenvector method is widely applied to derive priorities, its theoretical robustness in reflecting true priority vectors remains debated. Building upon a previous iteration of this study, this research develops the revised Least Penalty-Squared Prioritization (LPSP) optimization models, including the revised Least Product of Penalty and Direct Squares (LPPDS) and revised Weighted Squares (LPPWS), to minimize the revised Root Mean Penalty-Squared Variance (RMPSV) and the revised Root Mean Penalty-Weighted Square Variance (RMPSWV). However, solving these non-linear formulations is computationally complex for decision-makers. To overcome these limitations, this study proposes the Parallel Osprey Optimized Least Penalty-Squared Prioritization (POO-LPSP) method. By integrating an improved bio-inspired metaheuristic Parallel Osprey Optimization Algorithm (POOA), this framework efficiently solves complex LPSP models to minimize RMPSV and RMPSWV, thereby enhancing prioritization reliability. The practical utility and computational efficiency of the POO-LPSP method are validated through a numerical application focusing on a Generative AI (GAI) vendor selection problem. To extend, POO-LPSP can serve as a robust alternative to Saaty's Eigen system method for AHP applications.
Machine learning models are often intended to augment rather than replace human decision makers, by providing information that is complementary to human judgement. Yet, in practice, human decision makers routinely fail to realize such complementary gains, even when models provide useful signal. In this work, we study how asymmetric information about the quality of information available to a human decision maker vs. an AI impacts the ability of a decision maker to extract complementary value from AI predictions. We show that a key factor is the error correlation structure between human and AI predictions. In particular, when the AI's prediction errors are \textit{negatively correlated} with those of the human, the decision maker can construct robust strategies which guarantee improvements in expected utility. We empirically investigate whether these conditions for complementarity arise in practice, using real-world forecasting benchmarks.
Chenxu Wang, Yongkun Yang, Boyuan Du +2cs.CL cs.AI
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.
Stefano Calzolari, Rubens Montanha, Gabriel Schneider +5cs.GR cs.AI
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.
We identify intervention bias as a previously unquantified failure mode of zero-shot large-language-model (LLM) educational advisory agents: without task-specific training, they recommend action when a hindsight-optimal oracle policy mandates inaction. In a six-arm ablation on the Open University Learning Analytics Dataset (N=800 students, four temporal cutoffs), at day 56 -- when the oracle designates 70.1% of students as needing no intervention -- zero-shot GPT-4o recommends action for 73%, a 43 percentage-point false-positive rate. Commercial RAG and SQL-augmented retrieval are comparably miscalibrated; at 10,000 students this implies about 4,300 unnecessary advisor contacts per cycle. Supervised policy learning eliminates this bias: a trajectory-conditioned ONNX Decision Transformer (DT) and a snapshot XGBoost classifier, trained on the same oracle-labelled trajectories under strict prefix-only features, both achieve near-zero calibration error. The DT reaches macro-F1 0.79 (macro-recall 0.85) across all five action classes, predicting even the rare load-reduction action without collapsing, at a 0% action flip rate and sub-5 ms CPU decision latency. The two supervised arms are on par; the DT's edge over XGBoost at the final cutoff is indicative only (unpaired across cohorts). Scope: we validate Stage-2 decision-making (EAV state vector to supervised policy) under controlled oracle input from structured OULAD data; high fidelity reflects feature-oracle alignment, not general high-stakes-AI capability. The most robust finding is the intervention-bias contrast, not the absolute accuracies. We also show an Evaluation Gap: LLM-as-judge scoring (DeepEval G-Eval) is blind to intervention bias, rewarding fluent over-prescription rather than decision quality.
Language models turn a worded situation into a numeric plan, and the dominant pipelines (NL4Opt, OptiMUS, ORLM, OR-LLM-Agent) commit to a single objective and point-valued coefficients, then solve once. For decisions that allocate real budget, effort, or clinical attention, that confidence is the failure mode: every objectified number is an assumption, and a plan optimal only if the guesses are exactly right is fragile -- mimicry of computation. YUKTI changes the target of autoformulation. Its representation is a typed-proposition graph whose relationships carry shape priors, coefficient uncertainty, and provenance. YUKTI routes each stage to an exact, nonlinear, or evolutionary solver; couples stages by a distributional Pareto hand-off; and introduces Assumption-Robust Pareto Frontiers (ARPF), resampling assumptions (including structural epsilon-contamination) to score how often each action survives (rho). We prove a bound making rho an exact factor of decision regret, add auditable traceability, and synthesize a benchmark-faithful data foundation when none exists (SRJANA). We validate three ways: under controlled misspecification the robust compromise cuts mean and tail regret by over 90% versus a naive point plan; on a regulated commercial decision we optimize inside a lawful action space and price the downside in euros; and on a real public dataset of 41,188 decisions an out-of-sample backtest beats the logged status quo by 34% and a naive point rule by 4% while reducing the optimizer's curse. The solvers are standard; we claim no benchmark-SOTA win. A head-to-head shows an LLM given the correct numbers, and single-objective optimization, both incur about 47x the held-out regret of YUKTI -- an LLM is a formulator, not a solver. Under long-range causal coupling, the forward hand-off becomes unsound, locating where it must become a backward-induction causal policy.
Takanori Yoshimoto, Yang Hu, Naruya Kondo +1cs.LG cs.RO
Latent actions provide a compact interface between action-free video and downstream decision-making, yet existing Latent Action Models (LAMs) force every transition through a fixed-capacity bottleneck. We identify a bottleneck trade-off: overly tight codes can discard transition cues needed for action alignment, while overly loose codes preserve additional transition variation that must be resolved when alignment labels are scarce or narrowly distributed. FlexLAM replaces this fixed capacity with variable-length latent actions trained by nested dropout, yielding prefix-valid codes that capture compact transition structure first and add detail only when needed, without new architectures or losses. A single FlexLAM matches or surpasses separately trained fixed-capacity LAMs at every evaluated token budget under standard scarce-label supervision and under a low-return single-task alignment stress test, indicating that FlexLAM is not merely adjustable at inference time but learns a better latent-action interface at the same token budgets. The same model supports inference-time token-budget adjustment without retraining, and FlexLAM improves Ego4D transition reconstruction. These results suggest that variable-length latent actions are an architecture-free, drop-in upgrade to the fixed-capacity bottleneck in latent action models, latent-action world models, and video-pretrained action interfaces.
Anna C. Edmonds, Mansur M. Arief, Robert J. Moss +2cs.AI cs.LG
Decision making in lithium production is challenging, whether from an investor's perspective or a strategic production standpoint. Determining which mines to open and when to open them involves not only geological and price uncertainties, but also complexities around the choice of extraction method, from direct lithium extraction to hard rock mining. Prior work explored models of this problem and different methods to optimize mining decisions; these models did not account for uncertainty in pricing, uncertainty in demand, or different mining technologies to extract lithium. Incorporating different pricing models and extraction technology into these models enables more robust strategies for determining not only when and where to open a mine, but also which method of production to pursue. We frame the problem as a partially observable Markov decision process (POMDP) and solve using belief state planning methods to get optimal decision making. In our study, we show that POMDP solvers outperform human inspired heuristics by dynamically adapting to shifting lithium price regimes (static, linear, exponential, and stochastic) through belief state planning and explicit uncertainty management. By optimally sequencing exploration, production, and technology choice, the framework achieves higher demand fulfillment and more balanced economic environmental outcomes over the projects lifetime in all different pricing and deposit scenarios.
Large language model (LLM) agents have made rapid progress on short-horizon, well-scoped tasks, yet their ability to sustain coherent decisions in dynamic long-horizon environments remains uncertain. We introduce RetailBench, a data-grounded simulation benchmark for evaluating tool-using LLM agents in single-store supermarket operation. RetailBench models retail management as a partially observable decision process and is designed to support thousand-day-scale simulations. In this environment, agents must manage pricing, replenishment, supplier selection, shelf assortment, inventory aging, customer feedback, external events, and cash-flow constraints. We evaluate seven contemporary LLMs under representative agent frameworks over a 180-day evaluation horizon and compare them with a privileged oracle policy. Results show substantial variation across models: only a small subset survives the full evaluation horizon, and even the strongest LLM runs remain substantially behind the oracle policy in final net worth and sales outcomes. Behavioral analysis attributes these gaps to incomplete evidence acquisition, surface-level decision making, and the lack of a consistent long-horizon policy. RetailBench provides a controlled testbed for studying reliable autonomy in economically grounded long-horizon decision-making.
Appropriate reliance on AI advice has become a central research theme in human-AI collaboration. Existing frameworks have focused exclusively on point predictions as AI advice. However, set-valued AI advice (e.g., discrete sets or continuous intervals) is increasingly being used to communicate uncertainty and improve human decision making. In this paper, we develop the first formal framework for measuring appropriate reliance on set-valued AI advice within the sequential judge-advisor paradigm, spanning both classification and regression tasks. For classification, we first introduce the dimensions that are necessary for evaluating set-valued AI advice. We then define two metrics: correct reliance rate on AI and correct reliance rate on self, which jointly characterize appropriate reliance in this setting. For regression, we introduce quantity of AI reliance and quality of AI reliance, which respectively measure whether a decision maker utilized the AI advice and whether their reliance helped them get closer to the ground truth relative to their initial estimate. Through the application of our framework, we demonstrate how these metrics capture important nuances in human-AI collaboration that existing measures overlook.
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.
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.