Papers

Block-diffusion language models are served at hand-picked operating points, such as acceptance thresholds, buffer depth, schedule, checkpoint and precision, and each point is chosen by its mean benchmark accuracy. However, a mean does not tell an operator how often a faster configuration fails on prompts that the slower one answers correctly. On the serving engine and its decode traces, the default commit rule already commits every fully resolved block, a static skip rule captures nearly all of the compute that allocation can save, and self-distillation on engine-decoded targets adds speed at unchanged accuracy. Larger speedups come from lower thresholds, which commit tokens that are still uncertain. We therefore present Redline, a finite-sample procedure that selects operating points, hand-picked or learned, from the correctness of their answers on calibration prompts. Redline keeps the reference-relative risk, the joint probability that the reference answers correctly and a candidate configuration does not, within a user-chosen budget with high probability, and deploys the fastest configuration that passes. It speeds up math at a smaller risk budget than code in both model families, and at a budget of ten percent it deploys a LLaDA2 math configuration that commits over a third more tokens in each forward. It also applies without modification to the acceptance rule of speculative decoding and to weight quantization. On the same calibration data, Redline stays within its stated failure probability, whereas each tolerance of a mean-accuracy rule either gains less speed for some model and task or exceeds the risk budget far more often for another. Code is available at https://github.com/js-lee-AI/Redline.

Large language models are trained to always produce an answer, regardless of whether they possess the relevant knowledge, which leads them to fabricate facts. Prior work has shown that LLMs' confidence estimates correspond poorly to their actual performance, and that fine-tuning can substantially improve them. However, what models actually learn during such training remains poorly understood. We investigate how LLMs acquire metacognitive monitoring, the ability to know what one knows, by training 10 open-weight LLMs to predict their own accuracy on factual multiple-choice questions before answering them. We find that trained confidence reflects two distinct signals. While on questions close to the training data, it tracks the model's true accuracy, in other domains, it instead tracks output consistency: the concentration of the model's answer distribution. Output consistency tracking emerges early in training and generalizes across datasets, whereas accuracy tracking develops later and remains local to the training distribution. These results suggest that calibration training may not teach models to generally detect errors they commit confidently, and they raise broader questions about the nature of metacognition in artificial systems.

Large language model (LLM) agentic systems increasingly rely on models communicating with one another, yet existing uncertainty and multi-agent methods rarely estimate how a particular receiver will interpret a message before it is sent. This matters in heterogeneous systems, where capable receivers can reconstruct different tasks from the same message. We model this as a sender-receiver problem with a latent receiver type and define prospective interpretation risk (PIR): the probability that a receiver reconstructs a task other than intended. Rather than model an LLM's full input-output behaviour, we use black-box probes relating messages, intended tasks, and receiver-specific reconstructions, yielding scalable supervision while separating interpretation from downstream capability failure. Offline, heterogeneous frozen receivers provide supervision for receiver-conditioned risk and the effects of predefined mutable message features. At deployment, history induces a posterior over receiver types, guiding message revision and selection. We introduce value of interpretation information (VoII), querying for receiver information only when its expected communication benefit exceeds its cost. Our theory characterises when receiver information has decision value and bounds such queries. Empirically, interpretation-failure rates vary by 4-13x across receivers. Receiver information reduces PIR calibration error by 68% relative to a receiver-agnostic predictor, largely by correcting receiver-specific risk levels. PIR-guided revision reduces interpretation failure by 44% relative to the original message and 40% relative to a generic rewrite, mostly through a repair that helps every receiver. VoII outperforms information-gain and random querying at matched cost on the interpretation objective it optimises, lowering interpretation failure from 3.84% to 3.79% while querying 18.2% of episodes.

Task-oriented dialogue requires maintaining and updating information across turns, yet language models expose no explicit belief-state object. We study how conversational state is represented, updated, and used inside eight instruction-tuned language models from four families on MultiWOZ and SGD. Structure and values separate: which domains, slots, and requests are active is linearly readable just before the model acts, whereas exact values are far more readable where the user stated them. After a user changes a value, both values remain accessible at their mentions, and causal interventions show that both continue to influence the model's action. In natural closed-loop interaction, query failures separate into cases of weak structural support, incorrect value resolution, and failure to deploy otherwise-supported constraints, with targeted interventions producing systematically different repair behavior across these cases. These findings motivate a state-action controller that starts from the base model action and selectively edits it using structural readouts, without requiring a complete predicted belief state as an intermediate representation. On held-out MultiWOZ interaction across five models, it raises the base model exact-query accuracy from .318 to .621 and task success from .272 to .371 at negligible added cost. Overall, reliable interaction requires not only retaining conversational information, but resolving which available constraints currently apply and ensuring that they govern action.

Glove-based motion capture is emerging as a scalable approach to collecting dexterous-hand demonstration data. However, due to the kinematic gap between the human and robot hand, the recorded human motions cannot be executed directly on the robot, especially for contact-rich tool-use tasks involving in-hand reorientation. Prior work bridges this gap in simulation through reinforcement learning (RL) or trajectory optimization, but the human contact pattern is hard to preserve under such formulations, often producing unnatural manipulation and unstable functional grasps. These methods also train a separate policy or solve a separate optimization for each reference trajectory, which is inefficient. To solve these problems, we propose DexTaG, a tactile-guided RL framework for dexterous manipulation. During training, tactile signals captured by the glove guide policy search toward the measured human contact pattern, reducing reliance on precise reference geometry for contact supervision. To improve efficiency, we train a single generalizable retargeter jointly on all training trajectories of the same object. The retargeter is further distilled into a tactile-free student controller conditioned on the target object trajectory for real-world deployment. On marker-pen and hammer manipulation tasks, DexTaG learns natural, contact-rich behaviors that baselines with distance-based contact heuristics fail to learn, generalizes to held-out trajectories of the same object and task, and outperforms single-trajectory baselines on OakInk2.

Convolutional EEG decoders are trained at a fixed width, usually set by their authors on other data. Growing methods add neurons during training where the loss could decrease the most, but whether they improve compared to a reference width is untested on EEG. Here, we grow three convolutional backbones on 12 motor-imagery datasets under three protocols and compare each with its reference model per subject. The growing ShallowFBCSPNet scores 2.9 points above its reference model with only half the parameters (0.57x), SCCNet changes by at most 1.2 points. Deep4Net growing models show decreased accuracy, but they require adaptation that prevent to compare faithfully the results. These differences follow the selection step, which keeps a candidate neuron relying on a dynamic threshold from singular values decomposition. Overall, these results suggest that growth helps when its criterion can rank the candidate neurons, and that the rate of skipped neuron addition tells where a decoder can be grown small from scratch.

Neural surrogates can accelerate large-scale optimization by replacing expensive or intractable model components with efficient learned approximations, but solving the resulting embedded problems can remain prohibitively costly. For instance, standard exact encodings of neural networks with ReLU activations allow the problem to be solved by mixed-integer solvers, but add large numbers of binary variables to accommodate the nonlinearity of the activations, which can render the problem computationally prohibitive. To address this, we propose DCEmbed, a heuristic for optimization problems with embedded neural surrogates that leverages the difference-of-convex (DC) representation of the network and avoids adding activation binaries. Exploiting shared structure within the DC representation of a ReLU network, we derive a reduced-size, exact formulation for its convex components that can be embedded in optimization problems using just two linear inequalities and one continuous auxiliary variable per hidden neuron. Using this, the problem is solved via an iterative penalty convex-concave procedure, where only the concave portions of the neural terms are approximated at each stage. The original objective, constraints, and any discrete decisions are retained, allowing standard convex or mixed-integer optimization solvers to optimize the host and surrogate jointly at each iteration. In experiments on quadratic programs, mixed-integer resource allocation, and neural two-stage stochastic programming, our method demonstrates much faster progress toward high-quality feasible solutions than approaches using exact mixed-integer embeddings. In particular, DCEmbed achieves $4\times$ lower normalized primal integral than the best exact baseline on the resource allocation problem, while in two-stage stochastic programming it reaches the global surrogate optimum $\sim 5\times$ faster than Gurobi ML.

Merchant matching resolves a noisy payment descriptor to a retrieved merchant entity or returns no match. A key challenge in curating training labels is distinguishing teacher abstention from evidence that no acceptable entity exists: false no-match labels contaminate pseudo-labeled data, while conservative labeling reduces coverage. We investigate whether agreement between two local large language model judges improves pseudo-label reliability. A label is retained only when the judges agree, with separate ordered thresholds for selections and abstentions that guarantee disjoint positive and negative label sets. Retrospective replay on 2,000 expert-annotated queries shows that higher selection thresholds can improve positive-label purity, whereas higher abstention thresholds increase false no-match labels. At thresholds (0.86, 0.80), Muse Glimmer 30B and Gemma 4 31B jointly label 1,633 queries (81.7% coverage) at 96.88% purity; positive and negative purities are 99.47% and 93.38%. This exceeds either constituent model at the same thresholds by more than two percentage points, with lower coverage. A split-half check finds only 0.14 percentage points of threshold-selection optimism. A symmetric threshold of 0.86 adds 40 erroneous no-match labels, while 46 false abstentions persist even with no confidence threshold. Across five matched within-model comparisons, higher reasoning effort yields no clear F0.5 gain and increases median latency by 1.8-5.0 times. These results motivate separate thresholding and auditing for positive and negative pseudo-labels. The study establishes label purity, not student utility; fresh-data curation and student fine-tuning remain necessary to demonstrate downstream value.

Outcome-only reinforcement learning gives software engineering (SWE) agents a terminal success signal but little direct guidance about intermediate decisions. We introduce Counterfactual Rollout Replay (CRR), a training-time procedure that uses forkable executable environments to obtain step-level return contrasts. CRR selects a small set of decision points, restores each state, samples an alternative action, and rolls the branch forward under the policy. It retains the realized training trajectory and replaces the advantage at selected steps with the difference between its terminal return and the sampled counterfactual return. The method needs no human process labels or learned process reward model; free refers to those supervision costs, not replay compute. With a 14B policy, CRR improves pass@1 on SWE-bench Verified, SWE-bench Live, and SWE-rebench, and combines with process-reward and trajectory-search methods. On SWE-bench Verified, an equal-wall-clock comparison on the same hardware yields 41.7% versus 36.7% for extended vanilla (outcome-only) GRPO, a 5.0-point gain with fork overhead included. These results apply to environments with affordable, reliable state restoration; stochastic continuations and expensive or imperfect replay remain limitations.

JET uses pretrained language and vision-language models to select among a finite set of answers without additional training. It evaluates candidate likelihoods directly and shares computation across candidates. Experiments on desktop CPUs and consumer GPUs assess decision accuracy and execution cost. Qwen3.6-35B-A3B achieves 87.48% accuracy on the full MMLU test set and 3.69 requests per second on a separately timed MMLU subset. The accuracy-throughput comparison covers model, hardware, and reasoning choices, with Jev as an external reference. Controlled execution experiments show 2.18-2.23-fold speedups from prefix reuse and cache management, and a 30.8% reduction in process time from input preparation optimizations, with unchanged outputs. Optional reasoning has a task-dependent accuracy-throughput trade-off. These results support local decision inference from existing models.

Robotic manipulation policies are advancing rapidly with increasing reliance on vision-language models for end-to-end decision making. However, reliable deployment remains challenging because many policies lack explicit mechanisms for predicting task outcomes and evaluating whether generated actions will achieve desired final states, causing execution errors to accumulate during long-horizon manipulation. We present Robot-GST, a geometry-aware spatio-temporal behaviour representation and evaluation framework that constructs a Gaussian-SAM robotic environment for real-to-sim policy verification and improves the reliability of real-world manipulation deployment. Our approach constructs a high-fidelity robotic environment from RGB-D observations using 3D Gaussian Splatting and SAM3D, enabling “simulation and evaluation before acting”. It integrates visual observations and language instructions with spatio-temporal reasoning for long-horizon task planning using large vision-language models. To bridge high-level planning and real-world execution, we introduce Gaussian-aware final-state estimation through geometric sampling and state-based trajectory planning. Before execution, candidate action sequences are simulated and evaluated in the Gaussian-SAM environment to filter infeasible behaviours. We validate our approach on representative manipulation tasks involving rigid, soft, and deformable objects, including cube placing, toy packing, and duck rearrangement, demonstrating that geometry-aware spatio-temporal reasoning and state-aware execution improve manipulation reliability across different object categories. Our results suggest that combining geometry-aware reconstruction with high-quality rendering and simulation provides a scalable approach for evaluating robotic manipulation behaviours. Website: https://robot-gst.github.io

The collective behaviour of large language model (LLM) societies is not the sum of their individual outputs. It yields statistically distinct, sometimes-unpredictable phenomena, for which the tools we use to study single agents may not scale. Due to recent incidents involving autonomous agentic systems, however, understanding these systems is paramount. For that we introduce a framework for measuring self-organisation in LLM social systems and apply it to three such systems: a Schelling grid, a social network (Moltbook), and a Twitter-like misinformation simulation ('Rogue'). All three exhibit statistically significant self-organisation. Moreover, their relaxation dynamics vary with the environmental information available to the agents, with open-ended systems (Moltbook, Rogue) exhibiting sharp, phase-transition-like dynamics. Further results show that population-level pathologies can emerge even when the LLMs are safety-tuned or monitored, being primarily driven by the coordinated activity of a population subset. We also show when self-organisation does not emerge under two additional scenarios (a commons dilemma, GovSim, and a LLM-as-a-judge deliberation scheme, ChatEval). We argue that measuring signatures of this kind offers a lightweight, agent-agnostic diagnostic layer for detecting coordinated collective behaviour in deployed multi-agent systems without relying on natural language or model versioning.

LLM agents increasingly solve long-horizon tasks by autonomously interacting with their environment. In doing so, their strategies rely on assumptions about that environment: which resources and tools exist, where they are located, and how they behave. When these assumptions no longer hold, reliable agents must detect the change and adapt while pursuing the same goal. We study this adaptation capability through environmental novelty: a change that keeps the task objective fixed while invalidating an assumption underlying an otherwise successful trajectory. We introduce AGNI, an automated pipeline that extracts trajectory-relevant assumptions, injects targeted environmental changes, and validates that the resulting novel tasks remain solvable. Across three terminal benchmarks, AGNI produces diverse novelties spanning resources, interfaces, constraints, and execution semantics. Evaluating multiple LLM agents reveals a substantial adaptation gap between base and novel tasks. Trajectory analysis suggests that agents often encounter evidence of the change but fail to diagnose its cause and revise their strategy. Finally, post-training for environmental novelty improves adaptation to held-out novel tasks while also improving performance on base tasks. Our results highlight a gap between task competence and adaptive capability and motivate environmental variation as a core dimension of agent training and evaluation.

LLM-based agents can improve themselves across tasks by reusing and revising the skills they orchestrate into executable procedures. Flow-based training fits this loop: it samples procedures in proportion to reward, and the flow through each skill credits it for the next library revision. Three obstacles stand in the way of making this self-improvement reliable: flow training suffers strategy collapse over tree-structured histories; nonnegative flow-based credit rewards frequent use as if it were benefit; and library edits rest on the task reward the policy optimizes. We introduce R$^2$ Flow, a recursive self-improvement framework that alternates policy learning, independent verification, and versioned skill-library updates on a shared-state orchestration graph. The graph merges histories that differ only in the order of independent steps, allowing flow training to pool evidence across equivalent executions. A flow-share readout of the trained flow, invariant to the backward policy, and a separate signed utility rank which skills to change, verifier evidence decides whether an edit is warranted, and a residual-variance plateau sets when to update. Committed edits reshape the graph the next policy learns on, realizing recursive skill evolution. Across question answering, mathematical reasoning, interactive decision making, and code generation, R$^2$ Flow improves task accuracy and library-edit precision over heuristic orchestration, reinforcement learning, and skill-evolution baselines, and transfers across executors. Code is available at https://github.com/beita6969/r2flow.

In-context learning offers an appealing approach to adapt automatic speech recognition (ASR) models to new speakers, accents, and domains by providing speech-text pairs as demonstrations at inference time. Recent work shows that some LLM-based speech models are capable of ASR in-context adaptation, when providing interleaved speech-text demonstrations. In this work, we ask whether in-context adaptation is an inherent ability for all encoder-decoder models. We study two forms of demonstration, collated and interleaved demonstration, across six encoder-decoder models, spanning conventional cross-attention-based and LLM-based architectures. We find that all tested models are able to perform in-context adaptation out of the box, achieving up to 30% relative improvement in the oracle experiments and up to 23% using first-pass hypotheses. Through controlled experiments on three English datasets, we show that lexical and speaker information both contribute to successful adaptation. While interleaved demonstration is effective in certain cases, collated demonstration brings consistent adaptation across the board. Our results suggest that in-context adaptation for ASR is not unique to specific architectures, training, or demonstration approaches.

Open access publishing has moved much of the cost of scholarly communication from readers to authors, while the labor of peer review remains unpaid and unevenly shared. This paper describes the design of Quorum: An Open Journal of Information Technology (jquorum.org), a journal that charges neither readers nor authors and uses peer review as its currency instead. Every first complete review a scholar writes on a manuscript earns one credit, and one credit pays for one submission. Each manuscript receives three double-blind reviews from reviewers matched automatically by expertise, and editorial decisions follow published rules rather than editor discretion. The paper documents the credit ledger, a bootstrapping mechanism called the genesis block, a reviewer search that widens after seven days and opens the paper to volunteers, the decision rules, and the integrity safeguards. An agent-based simulation, run for two simulated years with 40 replications per scenario, evaluates these choices. Without the genesis block, no paper was submitted in any replication. With it, a community growing from 40 to about 330 members submitted about 603 papers, and papers waited a median of 7 days for a full review panel. The day-7 escalation had a modest effect in a large community but a decisive one in a small community of about 60 members, where removing it left 48.8% of papers without a panel after 60 days, compared with 4.6% with it. Unspent credits also accumulated to about 3.7 per member after two years, which points to a policy choice the journal will face as it grows.

This manuscript is an English translation and extended version of a paper originally published in Japanese(otomo 2021) Recent years have seen a rapid expansion in applying satellite remote sensing and big data to economic analysis. In particular, satellite-observed nighttime light intensity has proven to be closely correlated with key socio-economic indicators, including gross domestic product, employment rates, population density, and educational attainment across countries. In this paper, I first outline the methodology for calculating regional nightlight intensity across Japanese prefectures and municipalities. Next, to evaluate the versatility of nightlight data, I examine the relationship between city-level nightlight intensity and various public socio-economic metrics, using Japan as a case study. The findings suggest that nightlight intensity can serve as a effective proxy for these diverse indicators. Finally, I explore the potential of nightlight data for enabling rapid economic impact assessments during sudden social disruptions, such as the COVID-19 pandemic.

This manuscript is an English translation and extended version of a paper originally published in Japanese (2022). Driven by remarkable advances in remote sensing and big data processing, spatial technologies are increasingly leveraged in economic research. While satellite nighttime light intensity is widely recognized for tracking macroeconomic parameters - such as regional GDP, employment, and population - less attention has been paid to fine-grained spatial processing methodologies for local tourism economies. This study first details a raster processing technique applied to nightlight imagery. It then focuses on Yuzawa Town (Uonuma District, Niigata Prefecture), analyzing the local economy and sports/tourist attractions. Specifically, I investigate the spatio-temporal relationships between tourist arrivals and various local statistical datasets. Furthermore, this paper highlights how nightlight data can capture intra-municipal economic dynamics that remain undetectable through standard macroeconomic indicators.

Recovering hidden transport mechanisms from sparse spatiotemporal observations is a fundamental inverse problem in scientific machine learning. In brain tracer imaging, dynamic contrast-enhanced MRI (DCE-MRI) provides time-resolved measurements of tracer concentration, while the underlying velocity and source mechanisms governing tracer propagation remain unobserved. We formulate this problem as physics-informed latent-state inference, in which the transport field itself is the primary object of inference rather than an auxiliary variable used only to reconstruct observed densities. We propose Physics-Informed Neural Optimal Mass Transport (PI-NOMT), a framework that represents density, velocity, and source as continuous neural fields and combines a continuous neural density teacher, recursive differentiable advection–diffusion–source rollout, unbalanced optimal-transport regularization, and governing-equation supervision. Physical laws act as structural priors that constrain the space of admissible transport mechanisms, while observed tracer dynamics provide evidence for estimating the latent transport state. We evaluate PI-NOMT on a synthetic benchmark with known ground-truth transport and on DCE-MRI sequences from nine control rats. On the synthetic benchmark, PI-NOMT accurately recovers the prescribed velocity field, including its magnitude, direction, and integrated trajectories, rather than merely reconstructing endpoint densities. Across the nine rat datasets, the framework yields sub-percent local endpoint error, consistent physical speed scales, and low post-training PDE and incompressibility residuals. These results support physics-informed latent-state inference as a general framework for recovering hidden transport mechanisms from observed dynamic scalar fields.

Self-evolving vision-language models train on questions they generate from unlabeled images. Since these questions have no gold answers, prior methods label them by majority vote over sampled answers or by a model judge. In a human evaluation, we find that 24% of majority-vote labels and 18% of model-judge labels produced during self-evolution are wrong. To address this problem, we present Verifiable QA Generation for Self-Evolving Models (VQS), which changes how the model judges answers. Instead of voting on an answer, the model parses each image into a structured record, such as a scene graph, a chart table, or a diagram graph. Fixed programs then write a question from the record and compute its answer. The model still acts as a visual checker, but it only confirms the individual facts the program reads, one short claim at a time. These claim-level checks select the parser's training targets, so the parser also improves without labels. Human raters find 94% of VQS answers correct, against 76% for majority voting. Across ten benchmarks, VQS improves Qwen3-VL by up to 3.18 points at the 2B, 4B, and 8B scales and outperforms the strongest self-evolving baseline at each. Gains keep growing over three training rounds, reaching 3.84 points at 2B. Code is released at https://github.com/ahmedheakl/VQS

Driving policies require capabilities of scene understanding and future evolution prediction. To achieve this goal, current end-to-end models typically construct complex perception-planning pipelines or introduce world models that explicitly predict future states, resulting in a complex system architecture. Inspired by the transferability of general-purpose visual representations, we argue that combining sufficiently strong visual representations with representation world modeling can support effective planning without relying on complex inference-time auxiliary modules. Based on this insight, we present ReDrive, an end-to-end driving framework that strengthens planning-oriented visual features via future representation prediction. To achieve this, ReDrive adopts a three-stage training pipeline consisting of driving video pretraining, joint world-modeling and planning training, and planner adaptation. This yields a strong planning-oriented representation and a high-performance planner, while requiring neither auxiliary perception modules nor future prediction at inference time. Experiments on NAVSIM demonstrate strong performance, achieving 91.0 PDMS on NAVSIM v1 and 90.8 EPDMS on NAVSIM v2. These results show that shaping representations with world modeling is sufficient to enable high-performance end-to-end planning while retaining a simple encoder-planner inference pipeline.

Target-speaker automatic speech recognition (TS-ASR) aims to recognize a designated speaker while suppressing interfering speech in multi-talker environments. Conventional TS-ASR typically relies on an enrollment utterance, whereas text-guided methods use known lexical content, such as a wake word, to identify the target speaker from the observed mixture. These two cues provide complementary information but are usually studied separately. We propose a Unified Dual-Cue TS-ASR framework that supports text cues, enrollment speech, or both within a single model. Text cues interact with the mixture representation to extract target-speaker information conditioned on known lexical content, while an independent enrollment utterance provides complementary speaker information. Cross-attention cue-conditioning modules are integrated into shared Conformer blocks, and negative-cue sampling provides cue-validity supervision during dual-cue training. Experiments on 30,000 two-speaker mixtures across five recording/domain conditions and four oracle text-cue lengths show that, with five-character text cues, the concatenated dual-cue method achieves 8.80% CER, compared with 17.32% for text-only and 29.06% for enrollment-only inference. It also outperforms parallel dual-cue fusion (9.49% CER) and yields lower dual-cue CER across all five evaluation subsets. These results demonstrate the benefit of jointly exploiting complementary lexical and speaker information for target-speaker ASR.

Contextualization, the core operation of language modeling, transmits information across words to build sentence-specific word representations. Prior works mainly study contextualization, focusing on individual words and attention heads as a growing discrete dictionary, lacking a global view of their general behavior. Therefore, we propose a general principle: Globally, we find and estimate that different words carry different amounts of information, and less-informative words tend to absorb more contextual information. Specifically, these low-information words do not absorb contextual words uniformly, and finer-grained selectivity enables more precise routing to promote information transmission between matched words. Moreover, to find what mechanism causes such processing, we reinterpret attention heads as channels gated by their singular vectors and find that: (1) these singular vectors point to the hidden states of more informative words, allowing such words to write their information to others more strongly to act as information sources, and vice versa; and (2) these singular vectors can be viewed equally as hidden state features, enabling automated interpretation of attention heads beyond prior heuristic head discovery, also embedding heads into a continuous space rather than treating them as discrete, independent dictionary entries.

This paper revisits the 1996 article Internet and Enterprise Strategy and assesses how its propositions were confirmed, transformed, or contradicted as digital connectivity evolved into an AI-enabled enterprise environment by 2026. The reassessment combines historical interpretation with a structured comparison of Internet-enabled capabilities, industry structure, value-chain transformation, platform intermediation, cybersecurity, data governance, artificial intelligence, and digital sovereignty. The analysis shows that the article correctly anticipated the strategic relevance of electronic markets, cybermediaries, transaction security, online communities, and internal rules for Internet use. However, the contemporary Internet exceeds the original framing: it is now a platformized, data-intensive, cloud-dependent, regulated, geopolitically contested, and increasingly AI-mediated environment. The paper argues that this progression from connectivity to AI-enabled enterprise systems does not replace Internet strategy; it extends it. For many firms, enterprise strategy is now enacted through digital infrastructures, algorithmic coordination, ecosystem participation, and governance capabilities.

Large language model (LLM) agents increasingly undertake extreme-long (xlong) horizon tasks, where a single execution can span hours, hundreds of model–environment interactions, and nearly 1M tokens per rollout. Applying online reinforcement learning (RL) to such executions poses two fundamental challenges: (1) severe execution variance and prolonged rollout delays cause massive GPU idling; and (2) complex non-linear branching generates massive trajectory redundancy, crippling training efficiency. To address these, we presents QwenGyre, an end-to-end framework for xlong-horizon online RL. QwenGyre elastically reallocates GPUs between rollout and training without interrupting live executions, while its trajectory processor reconstructs branching histories, scores partial progress, and deduplicates redundant paths to bound training costs. Scaled to our flagship model, Qwen~3.8 2.4T, with 700K tokens per rollout, QwenGyre yields a 6.0% absolute gain on NL2RepoBench (52.5% $\to$ 58.5%) in 48 steps. Across our evaluations on diverse domains of training datasets, QwenGyre delivers up to $1.85\times$ and $1.78\times$ speedups over Colocate and Async, respectively.

Cloud computing and high-performance computing (HPC) typically follow different paradigms: cloud services are often orchestrated using Kubernetes, whereas HPC workloads are managed through batch schedulers such as Slurm. Growing demand for shared computational resources increases the need for interoperability between these environments. This study uses Podman as a user-accessible tool to benchmark quantum chemistry software distributed as precompiled executables. Containerized and on-system execution are compared across CPU-optimized builds and multiple compute nodes, without additional network optimizations. The results demonstrate that performance depends on software compilation, startup overhead, and execution configuration. Container preparation can dominate short-task workflows, while long-running calculations require monitoring of computational progress. These findings highlight the importance of workload-specific benchmarking and user-level monitoring when deploying scientific applications in containers on HPC systems.

Evaluating code data as a single corpus can obscure which types of code data benefit which models and downstream tasks. Effective data selection requires understanding both the benefits of individual categories and whether these benefits persist when categories are combined. We introduce a decompositional lens for studying these effects in LLM post-training. We first decompose an execution-verified code corpus into interpretable categories based on the computational patterns of its solutions. Through controlled fine-tuning experiments, we compare individual categories with a balanced mixture across instruction-tuned models on question answering, mathematics, and code generation. The resulting response maps reveal recurring gains in average question-answering performance, while the same category can improve one model or task and degrade another. The best-performing category also varies with the starting model and target task. We then compose compact mixtures guided by these results and examine whether benefits observed in individual categories persist under joint training. On selected model–task pairs, mixtures whose constituents each improve the target task outperform both their best constituent and full-corpus training while using roughly 10–15% of the full corpus. These exploratory findings illustrate a less is more pattern and highlight how the value of code data in post training depends on which categories are combined for which model and task.

Modeling temporal dependence and uncertainty is central to forecasting with world models. The Visual Bayesian Regression World Model combines visual features, physical histories and known covariates through interpretable regression, within a modular architecture supporting trend, seasonal and cycle dynamics. Visual compression reduces representation dimension, while Bayesian variable selection reduces active regression dimension. Posterior prediction combines forecasts across predictor subsets using their posterior probabilities as weights and accounts for parameter uncertainty and future disturbances. The model forecasts joint visual–physical states recursively and physical targets directly. Across four forecasting tasks spanning object motion, vegetation greenness and solar power, ViBR-WM achieves lower mean overall physical-target error than Temporal Straightening, ConvLSTM, PredRNN and SimVP on every task. Repeated fitting and resampling support these overall gains.

The shipped Laya Typed-Decisions checkpoint, a 421M-parameter ModernBERT-large assessor that answers typed choice/noul/score questions over workflow state, is uniformly under-confident. The signed confidence-accuracy gap is $-0.214$, every occupied reliability bin's accuracy exceeds its confidence, and that sign uniformity collapses every binned ECE variant to the same value, $0.214$. The card frames the risk as over-confidence; the measured direction is the opposite, and the direction decides which way a confidence-gated cascade fails. A single disjointly fitted temperature ($T=0.469$, sharpening) removes most of the miscalibration (held-out ECE $0.204$ to $0.037$) and outperforms the shipped per-option-count table. The frozen selection rule instead chose isotonic regression, which overfit and failed its held-out NLL contrast on both tracks, so hypothesis H2 is not supported. Re-running the released checkpoint on its full official test split reproduces the card's headline accuracy ($0.767$ vs. $0.766$). The retrospective E1 reproduction preceded the analysis freeze; E2-E8 were prospectively preregistered, and 20 of 22 executed confirmatory tests reject under Benjamini-Hochberg FDR at $q=0.05$ (two descoped). The frozen gate beats random escalation but misses its 10% accepted-set error target on both tracks, an exploratory out-of-distribution probe finds no zero-shot transfer (accuracy $0.617$), and every score measures agreement with a synthetic teacher whose self-agreement ceiling ($0.735$) the specialist exceeds. Per-decision predictions, run manifests, and the frozen preregistration are in the ancillary files. The author has no affiliation with the model's publisher, the dataset's publisher, or TypeSafe.

Riftbound: League of Legends Trading Card Game is a trading card game about capturing and holding locations in a king-of-the-hill style contest. Originally released in China in August of 2025, and later released in the United States in October of 2025, the game has been well received for its depth and complexity. In this paper we demonstrate a facet of this complexity by providing sequences of valid game states which construct Universal Turing machines within the game. Each of these machines are constructed with tournament legal decks at the time of writing and strategies assigned are directed by the game state. We also show that given an appropriate board state the machine may be constructed and the computation may be performed in one game turn.