An Alien Mind
Jakub Pachocki reflects on increasingly capable AI and the challenge of keeping it aligned. He calls for stronger safeguards and international coordination.
en
Seguridad y regulación
2481
209
Second-Order Smooth Planning with Optimal-Transport Bellman Smoothing
Planning with a generative model aims to estimate the value of a state using as few simulator calls as possible. SmoothCruiser achieves problem-independent complexity O(^{-4}) by exploiting the smoothness of the entropy-regularized Bellman backup, but its estimator is only first-order. We show that the sample-complexity exponent of SmoothCruiser-type planners is governed by the order β of the local Taylor remainder, giving oracle complexity O(^{-(2+2/(β-1))}): the first-order case β=2 recovers SmoothCruiser, while a second-order/cubic remainder β=3 yields O(^{-3}). We reach this regime with an optimal-transport-smoothed Bellman backup over action distributions, which has a closed form, a policy gradient, and a Lipschitz Hessian, and whose quadratic correction admits an unbiased cross-product estimator. The resulting SecondOrderSmoothCruiser achieves O(^{-3}) oracle complexity for fixed OT parameters, and we relate the OT, entropy-regularized, and unregularized objectives through explicit regularization-bias bounds.
en
Learning Kernels by Alignment for Multiclass Bayes Classification
Kernel methods separate data representation from decision-making, but typically require the kernel to be chosen in advance. We show that this kernel can instead be learned by alignment, and develop the resulting framework through the recently introduced Collaborative Learning and Inference (CLaI). We show that Collaborative Learning can be viewed as a kernel alignment process, in which an embedding is trained so that its induced similarity matches a label-derived target kernel. We also prove that Collaborative Inference is equivalent to kernel Bayes classification with Parzen-window density estimation. Motivated by these perspectives, we generalise CLaI by replacing cosine similarity with a learned Mahalanobis distance and extend it to multiclass classification. On CIFAR-10, PathMNIST, and SleepEDF, the Mahalanobis formulation improves accuracy, converges faster, and yields lower calibration error than the cosine-based variant. Auxiliary experiments further support these connections, showing that CLaI produces latent signals of the same form as a Gaussian process, while achieving competitive calibration on sepsis prediction. Together, these results establish a principled learned-kernel framework that unifies representation learning, kernel alignment, and Bayesian classification, and extends naturally to the multiclass setting.
en
One Step, One Lead: Mitigating Higher-Order Interference in Multi-Domain Reinforcement Learning via Cross-Step Control
Reinforcement learning (RL) across multiple domains can broaden the reasoning capabilities of large language models (LLMs), yet joint training often degrades individual-domain performance and can destabilize optimization. Existing work typically diagnoses such interference from a single-step view using first-order gradient alignment or curvature-based proxies. We show that this view can miss a critical form of sequential interference: same-point domain gradients may remain nearly orthogonal even when consecutive realized updates partially reverse one another in output space. We further show that consecutive token log-probability footprints recover this interaction directly from adjacent checkpoints as a local second-order interaction in output space, without explicitly reconstructing same-step curvature. Building on this insight, we propose OSOL, which designates a focus domain at each iteration, uses the preceding checkpoint footprint to rank token-level rebound risk, and applies a drift-ranked, adaptively scaled correction within the standard GRPO update. Our analysis shows that this correction suppresses the targeted cross-step output backtracking component. Controlled studies further show that cross-step backtracking is more strongly associated with subsequent task damage than same-point gradient diagnostics, while the preceding footprint ranks future rebound risk more accurately than Hessian-based proxies. On Qwen3-30B-A3B, OSOL reaches a domain-macro average of 0.4822, improving by 5.7% over the strongest compared baseline, without explicit higher-order differentiation.
en
Local and Global Stability in Performative Reinforcement Learning
In performative reinforcement learning the deployed policy shapes the environment that generates the learner's future data, and the natural solution concept is a performatively stable policy that is optimal in the environment it induces. Existing convergence guarantees rely on Lipschitz sensitivity assumptions on the environment map π(P_π, r_π), which are hard to verify and fail in settings such as multi-agent best-response dynamics. We instead study stability for mixtures of policies, and show that the resulting picture is fundamentally different from performative prediction, where randomization removes the need for any sensitivity assumption. We distinguish local mixed stability, an occupancy-weighted first-order relaxation that we show is equivalent to stationarity, from global mixed stability, which certifies against arbitrary deviating policies. Our first result is that a weighted per-state Hedge dynamic drives the local stability gap to zero at an O(1/{T}) rate for an arbitrary, possibly discontinuous, environment map, both with exact and with trajectory feedback. The two notions genuinely differ: we exhibit an instance where local stability is achieved exactly but every mixture has global stability gap bounded away from zero. For global stability we introduce a bounded transition range assumption, strictly weaker than Lipschitz sensitivity, under which unweighted per-state Hedge converges up to a floor of O(γε_P/(1-γ)^3), and we prove a matching-in-ε_P lower bound of Ω(γε_P/(1-γ)) under trajectory feedback, so this floor is unavoidable. Finally, we extend both notions to n-player performative Markov games, obtaining local stability with no assumption on the joint environment map or game structure, and global stability for performative Markov potential games.
en
A Theoretical Framework for Masked Pretraining (MPT)
Recently, Masked Pretraining (MPT) based on reconstruction pretraining tasks has risen to a promising self-supervised learning paradigm across various domains and achieves remarkable performance in multiple downstream tasks. However, the theoretical understanding of the working mechanism behind MPT is still limited. In this paper, we introduce a new theoretical framework to analyze MPT and understand the crucial role of masking in extracting meaningful representations. We establish theoretical connections between MPT and another popular self-supervised paradigm: contrastive learning. We prove that the masking technique implicitly creates positive pairs that are semantically similar and the reconstruction loss pulls them together in the feature space. Besides, as a result of the implicit alignment, we point out the dimensional collapse issue of MPT and propose a Uniformity-enhanced MPT (U-MPT) loss that can effectively address this issue and bring significant improvements in downstream tasks including linear evaluation, cross-dataset fine-tuning and out-of-distribution generalization on real-world data sets. Furthermore, we establish downstream guarantees of U-MPT and theoretically analyze the influence of masking strategies. Based on the theoretical analysis, we propose a new masking strategy which enhances the downstream performance of MPT and explains current improvements of masking strategies with our theoretical perspective.
en
Causal Attribution for Agentic Decisions: Estimators, Coupling, and a Traceability Specification
A provider of a high-risk AI system must keep records that make a decision traceable, and for agentic systems it has not been established what those records must contain for post-hoc causal attribution to be possible. We give the estimator framework and then the conditions under which it fails. We separate the marginal total effect that prior work measures from a common-random-numbers total effect that isolates a step's own contribution, add the natural direct effect under a pinned downstream, and check the estimators against hand derivations. Both estimands then fail, in the same direction. Under the marginal estimand a causally inert step has the identical total effect to the decisive one on every run of our planted chain, an algebraic identity and not a coincidence at one draw. Under common random numbers the decisive step returns exactly zero on the runs where the executing step flips, about one in ten, while its direct effect there is 0.25 and it demonstrably acts; an exact zero does not certify that a step did nothing, and we put that here rather than in the limitations. We derive the coupling that keeps the direct effect estimable once contexts diverge, with a closed form for its degradation, and show that the mediated share on which a natural ranking is built is not a share under suppression: where the direct and mediated paths oppose, it exceeds one and ranks a suppressed component above a pure mediator. We publish the discrepancy experiment's pre-registration rather than a result, because the live pipeline it requires was not available in the study window. We contribute the traceability specification such a filing would need, against a gap the Act's calendar opens: Article 86's right to an explanation has applied since 2 August 2026, while the Article 12 logging and Annex IV documentation that could evidence one were deferred to 2 December 2027 by Regulation (EU) 2026/1744.
en
Collision Snapshot Guided Time-Reversed Safety-Critical Scenario Generation
The generation of safety-critical traffic scenarios is essential for training and evaluating autonomous vehicles. Prior approaches typically perturb the trajectories of existing agents in a traffic scenario using simplified adversarial objectives to induce safety-critical interactions, which can limit the plausibility and diversity of the generated scenarios. Although inserting new adversarial vehicles can alleviate this limitation, determining when and where to introduce them in a scenario-specific manner remains challenging. In this work, we introduce {CO}llision {S}napshot guided {T}im{E}-{R}eversed safety-critical scenario generation (COSTER), a framework that leverages learned traffic priors to determine plausible collision times and locations. COSTER first constructs a collision snapshot by inserting a new vehicle in contact with the target vehicle at the identified collision state within a traffic scenario. Starting from this collision snapshot, a conditional variational autoencoder is used to perform a time-reversed rollout, reconstructing the trajectory of the inserted vehicle backward toward earlier timesteps. Experiments show that COSTER outperforms existing methods in plausibility, diversity, and data efficiency. Moreover, agents trained on COSTER-generated scenarios reduce collision rates by 31\% on safety-critical scenarios from the Waymo Open Motion Dataset while also improving ego task completion. The project website is available at https://anonym-121.github.io/COSTER/.
en
Visual Search Augmented Chain-of-Thought Reasoning for Attribute Value Extraction from Product Videos
Existing approaches to visual attribute value extraction (AVE) primarily rely on static product images, failing to capture temporal cues, multi-angle views and fine-grained visual details. Directly applying video vision-language models (VLMs) to product AVE results in limited performance due to the lack of domain knowledge, and fine-tuning them requires extensive high-quality data and substantial computational resources. Thus, we propose visual search augmented chain-of-thought reasoning (ViS-CoT), a training-free, plug-and-play pipeline that can be easily applied to any open-source video VLM for video-to-text AVE in e-Commerce. Specifically, ViS-CoT employs visual clustering to identify representative frames, followed by visual search to retrieve semantically similar product knowledge that can enrich attribute cues. Next, an interleaved CoT reasoning module iteratively refines reasoning through visually-aligned auxiliary texts derived from captioning and automatic speech recognition. Finally, the integrated information guides the model toward accurate and fine-grained attribute predictions. Extensive experiments across 14 product categories on the VideoAVE dataset show that ViS-CoT consistently enhances multiple state-of-the-art video VLMs, achieving an average improvement of 17.91 percentage points in micro-F1.
en
Hierarchical Wasserstein Merging for Multi-Domain Multi-Task Learning: From Specialists to a Generalist
Multi-domain multi-task learning (MD-MTL) aims to build a single generalist model that performs well across heterogeneous domains and tasks. However, joint training often suffers from interference under distribution shifts. Existing model merging methods mostly operate on model parameters while overlooking the geometric structure of latent representation distributions across domains and tasks. To address these limitations, we propose Hierarchical Wasserstein Merging (HWM), a representation-level framework that models each domain-task specialist as a distribution of hidden representations on a shared support. HWM constructs task-level and global Wasserstein barycenters to capture within-task domain variation and cross-task structure, enabling either training-free specialist aggregation by Wasserstein-derived weights or training-based generalist learning through a hybrid Wasserstein alignment loss. Experiments on four NLP tasks across four domains per task show that HWM achieves superior effectiveness and generalization capability in MD-MTL settings.
en
MetaRSI / RSI2: A Meta-Recursive Self-Improving System for Recursive Self-Improving Systems Themselves
Recursive self-improvement (RSI) lets a system improve the model-building machinery from its own failures, so every later model inherits the gain. Yet RSI has been validated almost exclusively on coding and formal benchmarks such as science QA and mathematics. This format bound limits RSI to improvement within a machine-checkable slice, not general capability where questions are open and correctness is settled by argument, replication, or measurement. We argue RSI must next operate across real, diverse scientific, engineering, and meta-scientific domains, not where formal evaluation is merely tractable. To that end we present MetaRSI-v1, where improvement is the scheduled composition of three typed operators over one unified paradigm. Data-RSI amplifies existing competence and marks its boundary; Harness-RSI edits a five-slot scaffold without touching weights; Model-RSI internalizes capability into parameters through bounded training. Sharing one loop kernel and artifact vocabulary, they make data, scaffold, and model changes composable rather than exclusive. A two-axis optimizer jointly decides operator order and each operator's proposal policy, while a meta-level policy revises the schedule across terms. We validate MetaRSI-v1 under the field's standard evaluations, on code and closed-form science, with no external teacher: the target model plays every role in its own loop. MetaRSI-v1 reframes self-improvement from a single-surface edit to a composition across the full model-production pipeline, opening two paths: a model route internalizing capability through training, and a harness route leaving weights untouched and thus extending self-improvement to any model reachable through an interface, with Data-RSI redefined as the shared substrate feeding both. The framework further yields refutable laws on where loops exist, how operators compose, and what supervision buys.
en
Cross-Lingual Representation Alignment by Token-Level Optimal Transport in a Language-Agnostic Space
Cross-lingual alignment (CLA) aims to align the representations of large language models (LLMs) across languages, enabling cross-lingual transfer to improve multilingual capabilities. Previous CLA methods often ignore language-specific information encoded in representations and only consider sentence-level alignment, which may lead to suboptimal performance and input-output language mismatch. We propose CAROT (Cross-Lingual Alignment of Representations in a Language-Agnostic Space via Optimal Transport), which consists of two steps: identifying language-specific representations in LLMs' internal states and aligning language-agnostic representations across languages at the token level by optimal transport, while explicitly preserving language-specific representations. Inference-time steering experiments show that the representations computed by CAROT are effective alignment targets, improving multilingual performance by up to 11.2 points in accuracy while maintaining input-output language consistency. We further use the representations obtained by CAROT as training targets, internalizing the aligned representations. The trained models outperform existing CLA methods in 11 of 18 evaluation settings (3 models 3 tasks ID/OOD languages). Our work provides insights into what constitutes effective alignment targets for CLA in LLMs. Code is available at https://github.com/ynklab/CAROT
en
OpenAI’s rogue agents keep escaping, with no formal process to investigate them
OpenAI’s latest agent swarm incident adds urgency to calls for independent investigations as researchers and lawmakers question whether AI labs should control the scope of…
en
Deploy a multimodal WhatsApp ordering assistant with Amazon Bedrock AgentCore
Learn how to deploy a multimodal WhatsApp ordering assistant that takes customer orders through text, voice notes, and real-time voice calls on a single business number, built on Amazon Bedrock AgentCore with Amazon Nova 2. The channel and ordering layers stay separate, and one shared memory recognizes each customer across all three channels.
en
Multi-Step Tool-Calling over Korean Open Public APIs: A Benchmark and a Data-Synthesis Recipe
Data-sovereignty regulations increasingly require public institutions to deploy open-source, on-premise LLM agents that chain multiple tool-calls across live government APIs. However, open-source models consistently underperform in this multi-step setting, and no existing benchmark measures the gap. We introduce the Korean Open Public API Benchmark (KOPA-Bench), comprising 145 real-world tasks. To close this gap, we present EDGE, an Execution-grounded Dynamic Graph for tool-calling data synthEsis driven by live execution. EDGE builds a graph of how each tool's output can feed another's input, keeps only the links that succeed when actually called against the live APIs, and traverses these verified links to synthesize executable multi-step trajectories. Fine-tuned via GRPO on the resulting dataset, our 9B model nearly matches the untuned 27B model from the same family, improving substantially not only on KOPA-Bench but also on the BFCL benchmark.
en
What Matters, When? Diagnosing and Improving Conditional Visual Grounding in Visuomotor Imitation Policies
Visuomotor imitation policies can achieve high performance under in-distribution visual conditions yet fail when visually similar objects or receptacles are introduced. We study this behavior as a problem of conditional visual grounding: the visual target required for successful control changes with the manipulation phase and, in more complex tasks, with the observed task state. Using Action Chunking with Transformers (ACT), we systematically introduce distractor objects and receptacles with controlled color and shape similarity and localize failures to picking and placement. We find that distractor sensitivity is specific to both the type of visual similarity and the manipulation stage. Guided by this diagnosis, we evaluate distractor augmentation, phase-dependent attention regularization, and appearance-based visual prompting as complementary interventions for improving target selection while preserving spatial information required for control. These interventions substantially improve robustness in simulation and on a physical UR3e. We further examine the same failure pattern in a pretrained vision-language-action policy on a state-conditioned instrument-handling task, where the observed state of a medical instrument determines the correct destination. Together, the results show that visual distractors can cause incorrect object or destination selection even when the underlying manipulation skill remains intact, and that explicitly improving target selection can substantially recover performance across distinct visuomotor policy-learning regimes.
en
Designing lifecycle policies for AgentCore memory
Long-running AI agents accumulate outdated memories that degrade quality and create compliance risk. Learn how to design memory lifecycle policies for Amazon Bedrock AgentCore: scoring, consolidating, and pruning agent memories on a nightly AWS Step Functions workflow, with a deployable AWS CDK stack.
en
What will Apple’s John Ternus era look like?
It’s officially the Ternus era at Apple. Tim Cook stepped down as CEO this week, handing the company to former hardware chief John Ternus, whose…
en
Distill Globally, Adapt Locally: Reasoning Distillation and Product-Type Test-Time Training for Scalable Trade-Up Recommendation
Trade-up recommendation identifies higher-quality alternatives that preserve a customer's purchase intent while offering upgraded benefits. Large language models (LLMs) can reason about such distinctions, but applying them directly to hundreds of millions of product pairs is operationally impractical. We introduce a two-level framework that distills LLM reasoning into an efficient non-generative student and adapts its decision boundary to product-type-specific trade-up criteria. At Level 1, a retrieval-augmented few-shot LLM teacher generates structured relation labels and natural-language rationales. These rationales supervise a compact embedding-pair classifier through alignment and contrastive objectives; at inference, the student uses only two precomputed 768-dimensional product embeddings, with no LLM calls or text generation. On a fixed human-annotated benchmark of 8,352 pairs, a 15.5M-parameter four-class reasoning-distilled student achieves AUC 0.924 (95% CI [0.918, 0.929]), compared with 0.912 for the four-class label-only student. At Level 2, product-type test-time training (PT-TTT) uses few-shot demonstrations to optimize lightweight category-specific adapters over the frozen student. PT-TTT improves AUC from 0.924 to 0.941 and average precision from 0.920 to 0.940. On a 100K-pair proxy catalog, the distilled student on a single eight-GPU machine is approximately 5,000x faster and 10,000x lower in estimated cost than direct LLM inference.
en