overfeed.news
Anuncio

Privum

Construimos, protegemos y operamos tu infraestructura digital.

Software, sistemas de IA, pruebas de penetración y nube segura para empresas.

Hablar con Privum

Sección

Investigación

Papers y preprints de los feeds de investigación que seguimos.

6415documentos

arXiv AI Papers

Multitask Interactions in Recurrent Dynamics across 100 Cognitive Tasks

The brain continually learns tasks with very different computational demands. Recurrent neural networks (RNNs) have been used as dynamical surrogates for studying task solutions, with recent work extending this approach to joint training on multitask batteries. However, it remains unclear how tasks interact as these batteries grow in scale and heterogeneity: under what conditions do they transfer or interfere with one another, and how do these effects relate to task complexity and model structure? We study this question by simultaneously training hierarchical Almost-Linear RNNs (AL-RNNs) on 100 tasks spanning a wide range of cognitive demands. AL-RNNs allow us to vary the amount of nonlinearity in the recurrence, while hierarchical task features provide a low-dimensional interface for task-specific adaptation within shared dynamics. On this task battery, performance improves with both nonlinear capacity and task-feature dimensionality, with the joint hierarchical model outperforming both individually trained models and a single unstructured joint model. Many tasks are individually solvable with linear dynamics, yet cannot be solved together by a shared linear model. Through hierarchical task features, task-specific linear region usage, and task geometry, the trained model provides several related but distinct measures of task similarity that capture how computations are separated and combined within the shared backbone. Across a series of experiments, we relate these representations to individual task complexity, joint solvability, pairwise transfer learning, and leave-one-out adaptation. Together, our experiments characterize task interactions in multitask recurrent learning while demonstrating both the potential and the challenges of reusable dynamical backbones for cognitive computation.

en
arXiv AI Papers

Neural Eigenfluid Bases: Spectral Objectives, Gauge, and Topology

Reduced-order models simplify fluid simulation by representing complex flows with a small number of spatial modes. Building on Laplacian Eigenfluids, we introduce Neural Eigenfluid Bases (NEB), a neural representation whose basis functions can be evaluated anywhere in space. We enforce incompressibility and impermeable boundaries directly through differential lifts and potential boundary conditions. Geometry-local orthogonalization and Rayleigh minimization then learn an ordered basis. We connect learning in potential and velocity spaces, and derive a spectral-variance relation explaining why these objectives weight approximate modes differently, even though their exact positive spectra agree. Gauge fixing reduces the number of spatial derivatives needed for potential learning, while a Dirichlet energy loss learns independent circulation fields around obstacles. With 1024 modes, both objectives keep velocity errors below 1% in periodic vortex merger. For random flows around obstacles, potential-based learning captures more initial energy and gives lower final errors than numerical Laplacian bases of the same size. The reduced state is about a thousand times smaller than the full reference model. Three-dimensional tests separate spatial reconstruction errors from errors in coefficient evolution. Precomputed Galerkin operators allow millisecond-scale updates when the same basis is reused across simulations. This provides a physically constrained basis for continuous flow reconstruction and efficient reduced-order simulation.

en
arXiv AI Papers

Learning Population Dynamics with Variational Doob-Wasserstein Flow

This paper introduces a novel simulation-free framework for learning unbalanced population dynamics on the Riemannian Wasserstein-Fisher-Rao (WFR) manifold, termed Variational Doob-Wasserstein Flow (VDWF), built upon the theory of the unbalanced mean-field Schrödinger bridge (MFSB). First, by independently learning a geometry model equipped with a data-dependent metric, our model captures the intrinsic geometric structure of population dynamics. Furthermore, leveraging Doob's h-transform, the proposed method incorporates boundary information to improve flow-based trajectory inference. For unbalanced transport, a growth model is employed to learn the dynamics while constructing intermediate mass samples in the WFR space without simulation. Additionally, we analyze the convergence rate of the proposed framework using a uniform Log-Sobolev inequality (LSI). Finally, we validate the proposed approach on multiple real-world datasets, demonstrating competitive performance in learning both balanced and unbalanced population dynamics compared with state-of-the-art methods.

en
Anuncio

Agendator

Reservas online gratis para tu barbería o salón.

Página de reservas, agenda y recordatorios por email. Sin cookies ni anuncios para tus clientes.

Crear mi página gratis
arXiv AI Papers

Real-Time Human Trajectory Prediction from RGB-D for Mobile Robots Using Bi-Mamba

Predicting the short-term future trajectory of a person from RGB-D cameras is a key capability for mobile robots navigating in dynamic and human populated environment. The key challenge to deploying learned predictors on real robots is the train-deploy pipeline gap. Training data are often prepared with an idealized, smoothed ground truth, whereas at inference, the model is fed noisy estimates from pose detectors and depth sensors. The model is therefore evaluated on an input distribution it never encountered during training. Most existing models rely on recurrent neural networks (RNNs) or transformers, which either struggle to capture short-term temporal dependencies or suffer from computational cost. We present TrajMamba, a lightweight, bidirectional state space model for short-term human trajectory prediction using an RGB-D camera. The model uses a single shared processing path for both training and deployment, aligning human pose extraction, depth back projection, and smoothing processes. It encodes a short window of persons's hip center velocities with stacked bidirectional Mamba blocks and decodes future velocities with a GRU head. On the ETH/UCY benchmark, TrajMamba reaches an average ADE of 0.29 m FDE of 0.51 m. With 262K parameters, it runs in real time on modest hardware and is deployed on a TIAGo robot with an onboard NVIDIA Jetson Orin.

en
arXiv AI Papers

Rank-1 Weight-Corrected Trainable Weight Averaging for Out-of-Distribution Detection

Out-of-distribution (OOD) detection identifies inputs outside the training distribution. Rank-based analyses such as RankFeat and RankWeight suggest that OOD overconfidence is closely related to dominant low-rank components in feature and weight spaces. Since weight averaging operates directly in parameter space and improves model generalization, we consider it for OOD detection from a dominant-component perspective. Trainable Weight Averaging (TWA) assigns a single coefficient to each checkpoint, limiting independent control of dominant weight components. We extend TWA with leading rank-one weight components extracted by Singular Value Decomposition as correction directions, whose contributions are learned through the in-distribution classification objective. On ResNet50, our method improves over fine-tuning and standard TWA across the evaluated datasets with MSP and RankWeight, both with and without Outlier Exposure. Mahalanobis-based evaluation yields mixed results, indicating that the benefit depends on the OOD scoring protocol. Target-layer analyses with MSP and Energy favor correction near the classifier.

en
arXiv AI Papers

OS-Wizard: Scaling Computer-Using Agents to Specialized Software via Knowledge-Guided Exploration

Computer-using agents are increasingly capable of performing complex tasks in the digital world. However, high-quality interaction trajectories remain scarce for specialized desktop applications, where limited application knowledge, cumbersome GUI workflows, and incomplete exploration hinder automated collection. We introduce OS-Wizard, an automated trajectory collection framework. It combines tutorial-guided exploration with a hybrid GUI--Code action space, providing application-specific knowledge and simplifying GUI workflows through direct execution of application-native commands. The framework also checkpoints and revisits pivotal states during tree exploration to explore alternative workflows, complementing linear rollouts for broader coverage. We collect 10.9K trajectories comprising 54.9K state--action samples. Fine-tuning open-source base models on this corpus yields a best-performing model that improves performance on a benchmark of specialized desktop workflows by 58.2 percentage points to 64.1\%, surpassing reported human performance of 59.8\% and establishing a new state of the art. The fine-tuned model also improves performance on general desktop workflows using GUI actions only, suggesting that the collected supervision benefits general desktop tasks as well. Comparative experiments and ablations demonstrate the efficiency of trajectory collection and the importance of code actions.

en
arXiv AI Papers

Counterfactual Test-Time Augmentation for Shortcut Removal in Language Models

Large language models (LLMs) can exploit shortcuts, i.e., correlations present in training data that may not hold at test time. This can lead to poor predictions when correlations shift. Most existing solutions for removing shortcuts operate at training time, requiring labeled training data, model weight access, and significant computational resources. Here, we study the problem of test-time shortcut removal. We propose a family of counterfactual test-time augmentation (CTTA) methods: given an example, each method uses an auxiliary model to generate counterfactual edits in which the shortcut value is changed, and then takes a weighted average of the LLM's predictions across these edits. We prove that the optimal shortcut-invariant predictor is a member of this CTTA family, and we characterize its weights. The weights depend on the training distribution, and therefore are, in general, not identifiable from the trained model and unlabeled test data. However, we present assumptions under which the weights can be obtained using the token probabilities of the trained LLM, and propose tests to detect violations of these assumptions. We use these tests to develop Select-CTTA, an aggregate method that selects among CTTA methods. Empirically, we find that Select-CTTA outperforms test-time baselines and approaches the performance of models fine-tuned on shortcut-balanced data.

en
arXiv AI Papers

When Personas Become Harmful: Guiding LLMs with Global Citizenship Values Alignment

LLMs are increasingly being used by users from diverse demographics with pluralistic values and distinct backgrounds. Maintaining safety while respecting value-laden personas is uniquely challenging because persona-conditioned requests are often not overtly malicious, unlike those in existing safety benchmarks. Alignment methods aimed at adversarial requests therefore may miss the harm that emerges from persona use, leaving models to either refuse legitimate value expression or blindly follow unsafe personas. We construct a dataset of 11k controversial topics paired with value-based personas mapping to value dimensions from the Schwartz Value Survey. Through an agentic pipeline that iteratively refines the topic and persona, we surface and collect harmful responses from well-aligned commercial LLMs with a more than 47% success rate. We use UNESCO's global citizenship principles as a minimal common ground for distinguishing valid value expressions from harmful behaviors, and introduce a controllable alignment model that lets users balance persona adherence and safety at inference time. The resulting model is safer and more persona-adherent than baselines on most samples.

en
arXiv AI Papers

Min-Marginal Power Indices for Multi-Objective Feature Selection

Game-theoretic feature selection scores each feature by its average marginal contribution across coalitions. An average shows whether a feature helps overall, but not whether, in some coalition, adding it turns an acceptable model into an unacceptable one. Building on minimum marginal aggregation, we define the Min-Marginal Power Index (MinPI) on a binary utility-threshold game. For a fixed quota, MinPI takes the value -1, 0, or +1 and labels each feature harmful, neutral, or decisive. A harmful label carries its own evidence, an evaluated coalition in which adding the feature drops utility below the quota, so no score cutoff is needed; finite-budget estimators keep this property but may miss harmful features. We use MinPI to propose feature removals, which are accepted only if they pass a validation gate, and to prefilter multi-objective search. On six benchmark datasets over five seeds, MinPI removed 12.5% of analyzed features with almost no loss of held-out utility. On Madelon and Abalone, where it removed the most, its removals cost far less held-out utility than random removals of the same size. Prefiltering increased the dataset-averaged hypervolume of multi-objective search in all five seeds. MinPI is therefore a conservative feature-deletion step whose gains are largest where the data contain many removable features.

en
arXiv AI Papers

Intervention-Certified Amplification: A Validity Gate for σ-Weighted Post-Training

Hybrid post-training often mixes supervised fine-tuning (SFT) and reinforcement learning (RL), using training-side signals to set each sample's balance. Such signals characterize the anchor data and policy, but not whether the emphasized behavior helps in the target task and evaluation setting. This mismatch can reactivate and amplify pretrained behavior even after its literal form is removed from supervision. We demonstrate this with DIAA (Dual-Implicit Adversarial Amplification), a per-sample σ-weighted SFT/RL hybrid. With all literal Python fences removed from its anchor, DIAA emits unexecuted Tool-Integrated Reasoning (TIR) on 29% of MATH-500 prompts, three times vanilla GRPO. Paired interventions show 10.6 percentage points of accuracy recovery when TIR is suppressed and comparable contributions from SFT imitation and σ-amplification; a student trained on a 0%-TIR teacher anchor emits it at 45.8%. Intervention-Certified Amplification (ICA) gates σ with paired-rollout target evidence. Frozen and online ICA reduce TIR to 13.8% and 11.2%, halve residual drag, improve accuracy from 47.5% to 48.7% and 49.3%, and transfer to held-out GSM8K without retuning.

en
arXiv AI Papers

DIGEST: Discovery-Guided LLM Tuning for Symbolic Regression

Symbolic regression (SR) seeks to discover mathematical expressions directly from data, without requiring task-specific scientific descriptions. Despite tremendous progress in both conventional search-based methods and recent LLM-based methods, two critical limitations largely remain. First (Limited Generation Flexibility), conventional search-based methods rely on either fixed search rules or specialized learned generators, severely limiting adaptive candidate generation across diverse expression structures. Second (Underutilized Search Discoveries), most LLM-based methods cannot reliably recover ground-truth expressions because they fall short in effectively leveraging the LLM itself to thoroughly digest past expressions or adaptively guide future search. To address these limitations, we propose DIGEST. To render greater flexibility in generation, DIGEST repurposes a pretrained decoder block from a lightweight LLM into a symbolic policy for Genetic Programming (GP) population seeding, thereby leveraging the broader modeling capacity of the LLM. To more thoroughly utilize search discoveries, high-quality expressions discovered by GP are fed back to update the LLM-derived policy online, thereby enabling the LLM to progressively internalize past search discoveries and translate them into improved subsequent population generation. Experiments show that on two ground-truth benchmarks, DIGEST outperforms the strongest competitor by up to 2.59% in recovery. Among LLM-based baselines, it improves recovery by at least 54.91% while using at most 17.4% of the strongest competitor's mean search time. On 122 BlackBox datasets, DIGEST achieves the highest accuracy while maintaining a moderate model complexity.

en
arXiv AI Papers

FlashScript: Compiling Recurring Agent Workflows into Reusable Neuro-Symbolic Programs

Many agent tasks recur with new data or small changes, yet agents regenerate their reasoning and actions on each run, producing different results. Distilling a prior run into a skill helps the agent avoid earlier mistakes, but it still re-runs the full process each time, so runs can vary and incur that cost. We compile a successful agent run into a reusable neuro-symbolic program (NSP) with a set of guidelines we call FlashScript. Actions and data transformations become code, instance-specific values become parameters, and decisions that need model judgment become LLM calls. We identify three layers where these calls belong and three techniques that replace most of them with code. The compilation does not remove nondeterminism; it localizes it, so the deterministic program and its neural calls can be reviewed and tested separately. Across 120 WorkBench analytics tasks with Claude Haiku 4.5, the NSPs were correct and made identical tool calls on every run, using about 70 times fewer input tokens and a third of the runtime of a skill-guided agent whose runs were inconsistent. In a composite version of the tasks, the skill-guided agent's accuracy fell to 23%, and its output inconsistency increased, while the NSPs remained correct and identical across all runs. The NSPs successfully generalized to all 108 unseen instances of the same templates. Our findings suggest that NSPs from agent trajectories can be considered cumulative software assets for end-users to test, maintain, and reuse in their recurring workflows.

en
arXiv AI Papers

Stable Dimensionality Reduction via Isometric Centroid-Encoder

Many supervised dimensionality reduction methods promote intra-class compactness and inter-class separation but do not explicitly constrain class geometry, leading to variability in the relative arrangement of classes across independent runs. Such variability limits the reproducibility and interpretability of low-dimensional embeddings. We propose the Isometric Centroid-Encoder (ICE), a supervised dimensionality reduction framework in which class centroids are learned directly in the latent space while preserving a prescribed pairwise class-centroid geometry. Unlike existing centroid- or prototype-based methods that primarily encourage intra-class compactness, ICE explicitly regularizes the relative arrangement of latent class centroids. Unlike multidimensional scaling and many metric-learning approaches that preserve sample-level relationships, ICE operates on class centroids, preserving inter-class geometry without requiring large numbers of sample-pair or triplet constraints. We further show that the intrinsic dimensionality required to represent the centroid-distance configuration of M classes is at most M-1, explaining the observed saturation of distance-preservation measures as the latent dimensionality increases. To quantify embedding reproducibility, we introduce the Centroid Neighborhood Stability (CNS) metric, which measures the consistency of class-level neighborhood topology across independent runs and complements existing embedding quality measures. Experiments on image and biological datasets demonstrate that ICE produces stable embeddings with improved preservation of class-centroid geometry while remaining computationally efficient. Additional analyses of optimization dynamics, sensitivity, and preprocessing further provide practical insights into latent dimensionality and explicit geometry modeling for supervised dimensionality reduction.

en
arXiv AI Papers

ReGE: Stronger Agents through Experience Synthesis

Repeated attempts at interactive tasks uncover facts, useful operations, and failures that can inform subsequent execution. We introduce ReGE, a framework for turning this recorded experience into guidance for a fresh attempt. Its main implementation, ReGE-Syn, uses a single coach call to jointly synthesize bounded execution records and available artifacts into self-contained guidance, connecting task-specific findings with proposed actions and relevant pitfalls. A student starts from the task's initial environment state and adapts this guidance to current observations. Source generation, synthesis, and student execution use the same base model, without parameter updates or a stronger teacher. Across four benchmarks, ReGE improves accuracy by an average of 9.9 percentage points for GPT and 8.8 percentage points for Claude compared with unguided execution. On matched BrowseComp-Plus subsets, ReGE-Syn reduces guidance-construction tokens by 98.2\% on GPT and 95.5\% on Claude relative to adapted AggAgent, with observed success. Combined construction and execution tokens decrease by 15.7\% and 35.4\%, respectively, counting input plus output and excluding source generation. BrowseComp-Plus ablations further associate access to process information with fewer student steps and show that joint synthesis produces substantially shorter guidance than Direct history or Independent summaries, with observed success. These results demonstrate how agents can use their own recorded experience to improve subsequent task completion, and suggest a low-cost way to consolidate the execution records of parallel agent systems such as agent swarms.

en
arXiv AI Papers

Numina Fuse: Interactive Autoformalization in Lean 4

Numina Fuse is an agent-native application for formalizing mathematics in Lean 4. Since Lean can compile while not representing its intended informal meaning, and agents now write Lean faster than people can read it, we built Fuse around human supervision of agent work. A user works with an AI orchestrator on a Lean project and supervises it through views of the blueprint, the dependency graph, and the Lean code, while the backend keeps the project's derived state and runs agents for hours without the user present. We describe the development of Fuse throughout 2026, as it moved from a prescribed pipeline of agents paced by human review to an orchestrator that dispatches specialists, provers, and parallel children on its own. We designed for this shift, keeping project state, tooling, and interface design separate from orchestration so that agents could take over more of the work as models improved. We report Fuse's use in a formalization of the three-dimensional Kakeya conjecture and a study of prover models. We close with lessons for the next generation of autoformalization systems. Fuse Desktop, an open-source local version, is available at https://github.com/project-numina/fuse-desktop.

en
arXiv AI Papers

Software Engineering LLMs: Why We Need Them and How Software Engineering Helps Build Them

Software engineering (SE) expertise can shape how coding large language models (LLMs) are trained and which engineering capabilities they acquire. We examine this role through an industrial case study of capability-focused training for a 92B-parameter coding LLM serving more than 100,000 developers. We demonstrate how established SE knowledge can guide the selection of engineering capabilities, the construction of verifiable training data, and the evaluation of model improvements. To target repository-level refactoring, we developed RefactorForge, a pipeline that combines refactoring knowledge, established SE tools, and verification techniques to construct training data. Across 306 Python repositories, RefactorForge generated 5,704 executable tasks and retained 4,572 verified teacher trajectories totaling 72.51 million tokens. Incremental supervised fine-tuning on these trajectories, accounting for 0.46% of the preceding coding mixture's tokens, improved RefactorBench performance by 18.00 percentage points and SWE-Bench ProMax performance by 7.06 points. Under OpenCode, these improvements extended to SWE issue resolution, with gains of 4.97 points on SWE-Bench Verified and 1.23 points on SWE-Bench Pro. Improvements also persisted across other coding-agent harnesses, while greenfield repository generation showed mixed results. We report lessons from constructing capability-focused training data and evaluating its effects across engineering workloads. Building on this industrial experience, we propose a research agenda for expanding SE's role in transforming coding LLMs into SE LLMs: incorporating SE knowledge into model training, applying engineering methods to model development and maintenance, and systematically defining the engineering capabilities these models should acquire.

en
arXiv AI Papers

Ranking Is Not Deciding: Benchmark Shortcuts and Operating-Point Collapse in Query-Time RAG Poisoning Defenses

Query-time filters that screen each retrieved document before it reaches the generator are the dominant published defense against retrieval-augmented generation poisoning, and they report near-perfect detection on domain benchmarks. We show that this performance is predicted by how the poison set was built rather than by what the filter reads: removing a single construction cue destroys the deployed decision before it destroys the ranking. Two label-free statistics of a poison set and its clean corpus profile the cue: containment, how often the target question appears verbatim in the poison, and length overlap. PoisonedRAG's released code prepends the target question to every inserted passage. Of the 21 published defense evaluations we survey, 8 verifiably run poison built this way and 5 substitute a length cue; separately, 12 report no false-positive rate at the operating point they deploy. Deleting only that prefix from the attack authors' own passages (0.93 still retrieved for their target) takes RAGuard, a published content filter we re-implement, from AUROC 0.953 to 0.758 and its miss rate from 0.191 to 0.763. Across four corpora, four attack families and ten per-document defenses on one shared candidate set, the profile predicts where detection saturates. Padding medical poison to clean length with word-shuffled filler that carries no content takes TrustRAG's set-level stage from a miss rate of 0.000 to 0.827, and one learned scorer of ours from 0.000 to 0.986 (0.321 at a matched 5% false-positive rate) while its AUROC holds at 0.953. The ranking survives; the decision does not. A defense-aware attacker defeats our own scorer, so we claim no defense. A detection result is evidence only when it is reported with its poison set's construction profile and the false-positive rate at the threshold actually deployed; we release the script that computes the profile.

en
arXiv AI Papers

When is early stopping beneficial under label noise? A phase diagram for kernel gradient flow

Early stopping is commonly used to prevent fitting label noise from degrading generalization. Does this mean that, when a positive fraction of the training labels is intrinsically unpredictable, the best test error must occur before interpolation? Experiments on a CIFAR10 classification task with randomly labeled examples motivate the opposite possibility: although fixed-feature and shallow models exhibit late-time deterioration of the test error, the need for early stopping essentially disappears in larger, deeper convolutional networks even after the random labels have all been classified correctly. We determine when late-time deterioration disappears entirely in a solvable setting. For kernel gradient flow on a synthetic noisy classification task, we derive sharp high-dimensional learning curves and obtain a phase diagram controlled by the balance between the linear kernel component that learns the shared relation between inputs and labels and the higher-order components that enable fitting the label noise. In one regime, generalization is optimized at finite time and early stopping is necessary. In another, generalization improves until interpolation, but the endpoint is suboptimal across kernels. At the boundary, the interpolating endpoint attains the lowest generalization error across the considered kernel family and all training times. Thus, even with extensive irreducible label noise, interpolation can outperform early stopping. The neural-network experiments leave open how learned representations acquire an analogous favorable geometry.

en
arXiv AI Papers

Build, Don't Play: Self-Improving LLM Research Agents Develop a Hearthstone Battlegrounds AI That Rivals Top Players

Can LLM agents carry a hard real-world problem from raw data to a system that holds its own against people? We study this in Hearthstone Battlegrounds, an eight-player auto-battler with stochastic shops and battles, hidden information and nearly a thousand interacting cards. We present AutoTavern, a self-improving research system: specialised LLM research agents share a typed research memory, every claim passes verification gates, and live games close the loop, so the agents improve the simulator, opponents and policy and, from the same feedback, their own research process; a human sets goals and rules on ambiguous mechanics. In 20 days AutoTavern built TavernGym, the first faithful, full-content reproduction of the live game, and delivered 23 versions of TavernAgent, trained with PPO against opponents calibrated to real games. TavernAgent plays complete games on the live ladder by itself: its rating rose from 6,000 to about 15,000 and, on the public leaderboard's measure, its last 20 records average a placement of 1.60 with 80% first places, better than the server's ten highest-rated players on every statistic (2.34, 59%). TavernBench, 960 tasks in 40 scenarios, shows that the system the agents built is the strongest player: TavernAgent answers 91% of the play tasks against at most 63% for frontier LLMs, and decides in 0.03 s where they need up to 26 s; within the second a live turn allows, it keeps 90% and no LLM more than 26%. LLM agents build far better than they play. We will open-source TavernBench and TavernGym at https://github.com/MCG-NJU/AutoTavern.

en
arXiv AI Papers

Approximate Universal Prediction under Interaction

Bayesian mixtures, and Solomonoff induction in particular, provide an idealized model of prediction learned by minimizing population log loss, and they underlie universal agents such as AIXI. An agent that plans with an approximation of such a predictor decides where that predictor is evaluated, and a planner can be drawn toward branches on which its model is optimistic. We study which approximation guarantees survive this feedback. For normalized finite-horizon causal mixtures, the transfer coefficient factors into a policy likelihood ratio and task evidence available before each prediction, so task rarity and action-branch rarity can compound. Within one fixed universal mixture, infinitely many computable environments admit excess prediction error of order κη\,2^{K(μ)}, where η is the training KL budget and κ measures policy coverage. This order is sharp, and for each target a computable predictor attains it at a suitable finite horizon, so computability alone does not remove the penalty. For bounded returns, value error is controlled by the probability of entering a poorly covered branch plus a square-root term in η. Both terms are necessary, and finite maximum coverage ratios are not required. Motivated by the mentor override of Golden Handcuffs, we derive margins for preserving deferral decisions and conditional KL budgets with an unavoidable inverse-history-probability penalty, and a counterexample separates agreement of deferral decisions from task-wise event avoidance. The guarantees apply to any predictor architecture that meets explicit population approximation and coverage conditions, which gives concrete targets for implementing idealized universal agents.

en