Social systems consist of networks of individuals who influence one another through social interactions. Studying how processes evolve on these networks can help us better understand patterns of social behavior. We study a system that couples online and offline social activity and investigate how to learn effective models directly from data using Weak Form Sparse Identification of Nonlinear Dynamics (WSINDy), a method for discovering governing equations. We assess learning performance using data generated by a mean-field approximation model of a stochastic interaction process on networks and test how accurately the system can be recovered under different noise levels. Our results show that using more trajectories improves accuracy when noise is high, but only a small number of additional trajectories is needed to gain most of the benefit, with little improvement beyond that. We also learn effective ODE models from averaged stochastic data on networks. When traditional mean-field approximations fail, identifying continuum ODEs directly from stochastic processes yields efficient models that better match the data and provide deeper insight into the underlying dynamics.

We present the first end-to-end demonstration of fine-tuning and serving Google's Gemma 4 31B model on TPU hardware, providing an empirical comparison of TPU and GPU platforms for large language model adaptation. Using LoRA on a Google TPU v5p-8 for training and TPU v6e-8 (Trillium) for inference, we document the full set of code-level adaptations required to port a GPU-native training recipe - built on PyTorch, HuggingFace TRL, and FSDP - to the JAX + Tunix/Qwix stack. These adaptations span mesh configuration, LoRA module naming conventions, sharding annotation corrections, gradient checkpoint, data pipeline restructuring, and a custom Orbax-to-safetensor checkpoint merging procedure. For inference, we detail the vLLM-TPU Docker setup necessary to serve Gemma 4 on v6e-8 and characterize the resulting latency and throughput profile. Compared with a similar-costing 2xH100 GPU baseline under identical hyperparameters, TPU training completes 1.61x faster at 2.12x lower cost. For inference, we cover the vLLM-TPU Docker setup required to serve Gemma 4 on v6e-8 and explain the observed latency and throughput characteristics across a QPS sweep spanning 512 to 16k input tokens. Across both workloads we compare performance and cost against a 2xH100 GPU baseline running identical hyperparameters. The TPU completes training 1.61x faster at 2.12x lower cost. For inference, TPU v6e-8 matches GPU at short context (<=2048 tokens) and decisively outperforms at long context: 66% higher throughput and 23.6x faster TTFT at 4096-token inputs (61 ms vs 1,443 ms at QPS=4). Our work removes a critical gap in the open tooling ecosystem and provides practitioners with a recipe for Gemma 4 Dense 31B deployment on the TPU infrastructure.

As Very Large Scale Integration (VLSI) designs continue to scale in size and complexity, layout verification has become a central challenge in modern Electronic Design Automation (EDA) workflows. In practice, congestion can only be accurately identified after detailed routing, making traditional verification both time-consuming and costly. Learning-based approaches have therefore been explored to enable early-stage congestion prediction and reduce routing iterations. However, although prior methods incorporate both netlist connectivity and layout features, they often model the two in a loosely coupled manner and primarily produce numerical congestion estimates. We propose VeriHGN, a verification framework built on an enhanced heterogeneous graph that unifies circuit components and spatial grids into a single relational representation, enabling more faithful modeling of the interaction between logical intent and physical realization. Experiments on industrial benchmarks, including ISPD2015, CircuitNet-N14, and CircuitNet-N28, demonstrate that VeriHGN achieves the best or near-best performance over state-of-the-art methods in prediction accuracy and correlation metrics.

Issues faced when using software are reported in the form of bug reports. However, many bug reports are invalid, meaning they do not require code changes, and are resolved with a no-code fix. Manually determining the root cause of the invalid bug reports and providing actionable resolutions by the customer support causes a serious waste of resources. Our goal is to introduce a standardized taxonomy for root-cause oriented invalid bug report subclassification, and perform experiments to test the accuracy of various approaches on invalid subclassification and no-code fix generation. We study how different configurations perform on a gold-standard benchmark we have created. Using a manually curated benchmark for higher quality analysis, we experimented with vanilla LLMs, Retrieval Augmented Generation, and agentic web search to identify invalid subclasses and generate no-code fixes. We evaluated the results against manually labeled ground truth data that includes the invalid subclass and no-code fixes from the original bug reports. We measured subclass detection performance with weighted F1-Score, and assessed no-code fix suggestions using BERTScore and Judge LLM success rates. For subclassification, retrieval augmented generation achieves the highest overall performance with 0.66 weighted F1, slightly outperforming vanilla LLMs at 0.65 and agentic web search at 0.64. At the subclass level, performance peaks at 0.85 F1 for Non-reproducibility and 0.79 for Feature Request and Question, while Wrong Version remains the most challenging with scores between 0.00 and 0.29. For no-code fix generation, agentic web search achieves the highest overall Judge LLM success rate at 68.9%, compared to 64.4% for RAG applications and 64.9% for vanilla LLMs, with subclass-level peaks of 87.4% for Working as Designed and 72.2% for Question.

Code review has evolved for decades, from informal peer checking to today's pull request (PR) workflows, yet it remains a largely manual and cognitively demanding process. The rise of Artificial Intelligence (AI) coding assistants has intensified this challenge: while these tools increase code production velocity, they also expand the volume of code requiring review, turning code review into a growing bottleneck. Current AI support in code review remains fragmented, with tools focusing on isolated tasks such as reviewer recommendation, PR description generation, or comment suggestion rather than the end-to-end PR review workflow. We address this gap by treating review effectiveness as an outcome of the full code review lifecycle rather than a single stage, proposing a framework that carries context across stage boundaries. We propose a future vision for code review in which reviewers transition from manual inspectors into supervisory operators of agents. In this vision, staged, AI-powered workflows aim to align the pace of code generation with shared understanding and accountable engineering. In this paper, we review the historical evolution of code review practices, identify challenges in traditional code review systems, and examine the shift driven by large language models (LLMs) and agentic AI systems. We then present a vision for an AI-powered code review workflow combining specialized agents with human-controlled quality gates. Our framework spans five stages: PR Creation, PR Augmentation, Reviewer Selection, AI-Assisted Code Review, and PR Retrospective, with humans retained at key decision points to preserve judgment, accountability, and team-level understanding. Finally, we identify key adoption challenges and outline research directions for evaluation, governance, and responsible human-AI collaboration.

Trotter Suzuki product formulas are the standard route to Hamiltonian evolution on noisy intermediate-scale quantum (\NISQ{}) hardware, but their accuracy depends on three coupled choices: term grouping, product-formula order, and time-step allocation. Grouping and order are discrete, which makes direct gradient optimization infeasible and forces existing compilers to rely on static heuristics. We describe P-GONE, a method that combines a conditional diffusion model (D3PM + DDPM), a graph neural network (\GNN{}) encoder, and closed-loop REINFORCE fine-tuning to jointly learn grouping, order, and time-step optimization over a mixed discrete-continuous space. Under fidelity-matched conditions ($F \geq 0.95$), the method achieves circuit depth 86 versus 1673 for Qiskit fourth-order (ungrouped, Suzuki-4), about $19.4\times$ compression, and 141 for Paulihedral (first-order Trotter), about $1.6\times$ compression. At $T=0.90$ the method also beats the Qiskit group-commuting teacher (65 vs 103, $1.6\times$ compression), though at $T=0.95$ the teacher still leads -- a stratified pattern that points toward fidelity-aware fine-tuning. Under a standard depolarizing noise model, the method achieves noisy fidelity roughly $2\times$ the Qiskit fourth-order baseline (0.743 vs 0.380). Ablation shows a clear hierarchy: order learning $>$ time allocation $>$ grouping. Best-of-N sampling ($N=32$ is a practical sweet spot) and CFG guidance give flexible fidelity-depth trade-offs at inference. The method works well on structured Hamiltonians (TFIM, Heisenberg), but random Pauli Hamiltonians fail entirely at $T \geq 0.95$ -- a boundary that defines where the method applies.

Autonomous agents are beginning to transform scientific research from tool-assisted workflows toward self-sustaining discovery processes. Computational catalysis provides a representative challenge, as catalyst discovery requires high-level questions to be translated into coordinated model construction, atomistic simulation, mechanistic analysis, and iterative design across multiple scales. Here we introduce CatMaster, a catalysis-native agentic research system that recasts computational catalysis as a low-barrier virtual ecosystem for autonomous research. CatMaster maintains an evolving research state and extends capabilities through self-feedback across model construction, calculation, critique and catalyst-design decisions within one extensible environment. Across progressively challenging tasks, CatMaster converts natural-language requests into concrete computational studies, from essential atomistic modelling and standard calculations to mechanism exploration and closed-loop catalyst design. It showed robust execution in representative computational-catalysis scenarios and near-leading performance across selected MatBench tasks, with phonons scenario demonstrating its modelling self-evolution capability. In the independent CO2-to-CO catalyst design case, CatMaster used iterative self-critique and evidence refinement to identify competitive B-CoN4 and NiN3B/N-NiN3B motifs. These results establish a virtual-ecosystem paradigm in which AI agents move beyond simulation execution toward end-to-end computational research, providing a foundation for autonomous discovery in catalysis and materials science.

We propose an implicit neural formulation of optimal transport that eliminates adversarial min--max optimization and multi-network architectures commonly used in existing approaches. Our key idea is to parameterize a single potential in the Kantorovich dual and reformulate the associated c-transform as a proximal fixed-point problem. This yields a stable single-network framework in which dual feasibility is enforced exactly through proximal optimality conditions rather than adversarial training. Despite the inner fixed-point computation, gradients can be computed without differentiating through the fixed-point iterations, enabling efficient training without requiring implicit differentiation. We further establish convergence of stochastic gradient descent. The resulting framework is efficient, scalable, and broadly applicable: it simultaneously recovers forward and backward transport maps and naturally extends to class-conditional settings. Experiments on high-dimensional Gaussian benchmarks, physical datasets, and image translation tasks demonstrate strong transport accuracy together with improved training stability and favorable computational and memory efficiency.

Software engineering agents are increasingly deployed in evaluable engineering environments, yet post-failure recovery remains costly, manual, and ad hoc. Existing systems expose traces or generate follow-up feedback, but they do not convert heterogeneous runtime evidence into grounded, bounded recovery guidance for a subsequent attempt. We present PROBE, a failure-anchored framework for structured recovery in software engineering agents. PROBE organizes failed-run telemetry into structured evidence, structured diagnosis, and bounded recovery guidance through a Telemetry Layer, a Diagnosis Layer, and a Guidance Gate. The Telemetry Layer preserves fine-grained runtime signals, the Diagnosis Layer fuses cross-signal evidence into grounded diagnoses, and the Guidance Gate produces diagnosis-derived guidance only when it is evidence-grounded, actionable, and within the scope of agent-side behavior. We evaluate PROBE across three settings: repository-level software repair, enterprise workflow recovery, and AIOps service mitigation. On 257 initially unresolved cases, PROBE achieves 65.37% Top-1 diagnosis accuracy and a 21.79% recovery rate, outperforming the strongest non-PROBE baseline by 43.58 and 12.45 percentage points. The results reveal a diagnosis-recovery gap: accurate diagnosis is necessary but insufficient unless translated into bounded guidance that a subsequent attempt can execute and verify. Beyond controlled evaluation, a Microsoft IcM prototype shows that PROBE can attach as a non-intrusive side channel to existing service-diagnosis workflows without changing the agent policy, toolset, or execution budget. These results suggest that telemetry-grounded, failure-anchored recovery can improve post-failure recoverability under realistic engineering constraints.

Retrieval-augmented agents are increasingly the interface to large knowledge bases, yet most treat retrieval as a black box: they issue exploratory queries, inspect snippets, and reformulate until evidence emerges. This resembles how a newcomer searches an unfamiliar database rather than how an expert navigates it with strong priors about terminology and likely evidence, causing extra retrieval rounds, latency, and poor recall. We introduce \textit{Superintelligent Retrieval Agent} (SIRA), which casts \emph{superintelligence} in retrieval as compressing multi-round exploratory search into a single corpus-discriminative retrieval action. SIRA does not merely ask which terms are relevant; it asks which terms separate the desired evidence from corpus-level confusers. Offline, an LLM enriches each document with missing search vocabulary; at query time, it predicts evidence vocabulary the query omits; and corpus statistics serve as tool calls that filter terms that are absent, overly common, or unlikely to create retrieval margin. The final step is a single weighted BM25 call combining the query with the validated expansion. Across ten BEIR benchmarks, SIRA achieves the strongest average retrieval performance in our comparison, beating dense retrievers, learned sparse retrievers, and LLM search-agent baselines while using no relevance labels or retriever fine-tuning. On downstream QA, its retrieval-only answer coverage exceeds recent RL-trained agentic QA systems on NQ and HotpotQA. We also introduce \textbf{BrowseComp-Wikipedia}, a hard-search benchmark of 232 BrowseComp-derived queries over a 25,587,229-document Wikipedia index. Even without index-time enrichment, using only grounded Wikipedia categories, SIRA outperforms multi-round Perplexity agents at every budget, reaching 9.70% Recall@1, 15.27% Recall@10, and 36.14% Recall@100.

Multiconfiguration pair-density functional theory (MC-PDFT) provides an efficient and accurate framework for computing electronic energies in strongly correlated molecular systems, with the quality of the on-top functional being a key determinant of its predictive accuracy. Here, we introduce MMCDDB26, a rigorously curated benchmark database comprising 76 datasets and 1,495 reactions. We further propose a constrained, large-language-model-assisted optimization workflow for the development and assessment of MC-PDFT functionals. Using this workflow, we optimized the parameters of the MC23/MC25 functionals on MMCDDB26 to obtain MC26. Compared with earlier functionals of the same class, MC26 improves the accuracy on the training set and achieves a more balanced overall performance. In addition, we developed the hybrid meta-functional COF26. We find that COF26 delivers superior performance for both strongly and weakly correlated systems, and therefore recommend COF26 for future MC-PDFT calculations.

Recent advances in large language model agents offer the promise of automating end-to-end software development from natural language requirements. However, existing approaches largely adopt linear, waterfall-style pipelines, which oversimplify the iterative nature of real-world development and struggle with complex, large-scale projects. To address these limitations, we propose EvoDev, an iterative software development framework inspired by feature-driven development. EvoDev decomposes user requirements into a set of user-valued features and constructs a Feature Map, a directed acyclic graph that explicitly models dependencies between features. Each feature node in the feature map maintains multi-layer contexts, including business logic, software design, and code implementation, which are propagated along dependencies to provide context for subsequent development iterations. We evaluate EvoDev on challenging Android development tasks and show that it outperforms the best-performing baseline, Claude Code, by 57.3%, while improving single-agent performance by 16.0%-58.5% across different base LLMs, highlighting the importance of feature decomposition, dependency modeling, context propagation, and workflow-aware agent design for end-to-end software development. Moreover, our work summarizes practical insights for designing iterative, LLM-driven development frameworks and informs future training of base LLMs to better support iterative software development.

Android malware detectors built with machine learning often suffer from temporal bias: models are trained and evaluated without respecting apps' actual release times, inflating accuracy and weakening real-world robustness. We address this by constructing a time-stamped dataset of benign and malicious Android apps and introducing a timestamp-verification procedure to ensure temporal accuracy. We then propose a detection framework that uses Bootstrap Your Own Latent (BYOL) for self-supervised pre-training to learn obfuscation-resilient representations, followed by supervised classification. Under time-aware evaluation, the method attains 98% accuracy and 89% F1. We further characterize malware behavior by analyzing true positives and false negatives using VirusTotal and the MITRE ATT&CK framework. To support reproducibility and further innovation, we release our dataset and source code.

Large Language Models (LLMs) have demonstrated remarkable capabilities across various cybersecurity tasks, including vulnerability classification, detection, and patching. However, their potential in automated vulnerability report documentation and analysis remains underexplored. We present RAVEN (Retrieval Augmented Vulnerability Exploration Network), a framework leveraging LLM agents and Retrieval Augmented Generation (RAG) to synthesize comprehensive vulnerability analysis reports. Given vulnerable source code, RAVEN generates reports following the Google Project Zero Root Cause Analysis template. The framework uses four modules: an Explorer agent for vulnerability identification, a RAG engine retrieving relevant knowledge from curated databases including Google Project Zero reports and CWE entries, an Analyst agent for impact and exploitation assessment, and a Reporter agent for structured report generation. To ensure quality, RAVEN includes a task specific LLM Judge evaluating reports across structural integrity, ground truth alignment, code reasoning quality, and remediation quality. We evaluate RAVEN on 105 vulnerable code samples covering 15 CWE types from the NIST-SARD dataset. Results show an average quality score of 54.21%, supporting the effectiveness of our approach for automated vulnerability documentation.

Engineering rulebooks and technical standards contain multimodal information like dense text, tables, and illustrations that are challenging for retrieval augmented generation (RAG) systems. Building upon the DesignQA framework [1], which relied on full-text ingestion and text-based retrieval, this work establishes a Multimodal ColPali Enhanced Retrieval and Reasoning Framework (MCERF), a system that couples a multimodal retriever with large language model reasoning for accurate and efficient question answering from engineering documents. The system employs the ColPali, which retrieves both textual and visual information, and multiple retrieval and reasoning strategies: (i) Hybrid Lookup mode for explicit rule mentions, (ii) Vision to Text fusion for figure and table guided queries, (iii) High Reasoning LLM mode for complex multi modal questions, and (iv) SelfConsistency decision to stabilize responses. The modular framework design provides a reusable template for future multimodal systems regardless of underlying model architecture. Furthermore, this work establishes and compares two routing approaches: a single case routing approach and a multi-agent system, both of which dynamically allocate queries to optimal pipelines. Evaluation on the DesignQA benchmark illustrates that this system improves average accuracy across all tasks with a relative gain of +41.1% from baseline RAG best results, which is a significant improvement in multimodal and reasoning-intensive tasks without complete rulebook ingestion. This shows how vision language retrieval, modular reasoning, and adaptive routing enable scalable document comprehension in engineering use cases.

Large language model (LLM) agents increasingly coordinate in multi-agent systems, yet we lack an understanding of where and why cooperation fails. Many real-world coordination problems are not social dilemmas: helping others -- sharing documentation, unblocking a teammate -- costs the helper almost nothing while producing substantial collective benefit. Whether LLM agents cooperate in this regime, where helping is free and they are explicitly instructed to do so, remains unknown. We build a turn-based multi-agent environment that strips away all strategic complexity, making cooperation costless and trivially optimal. Across eight widely used LLMs, capability does not predict cooperation: OpenAI o3 reaches only 17% of optimal collective performance while the weaker o3-mini reaches 50%, despite identical instructions to maximize group revenue. Using a causal decomposition that automates one side of agent communication, we separate cooperation failures from competence failures, and find that several capable models actively withhold information despite gaining nothing from withholding. Targeted interventions address each mode: explicit protocols roughly double the performance of competence-limited models, while small sharing incentives unlock cooperation-limited ones. Our results suggest that scaling intelligence alone will not solve coordination in multi-agent systems, and will require deliberate cooperative design, even when helping costs nothing.

Gait analysis is essential in post-stroke rehabilitation but remains time-intensive and cognitively demanding, especially when clinicians must integrate gait videos and motion-capture data into structured reports. We present OGA-AID, a clinician-in-the-loop multi-agent large language model system for multimodal report drafting. The system coordinates 3 specialized agents to synthesize patient movement recordings, kinematic trajectories, and clinical profiles into structured assessments. Evaluated with expert physiotherapists on real patient data, OGA-AID consistently outperforms single-pass multimodal baselines with low error. In clinician-in-the-loop settings, brief expert preliminary notes further reduce error compared to reference assessments. Our findings demonstrate the feasibility of multimodal agentic systems for structured clinical gait assessment and highlight the complementary relationship between AI-assisted analysis and human clinical judgment in rehabilitation workflows.

The Agentic Web is emerging as a paradigm in which autonomous software agents interact with online resources and with each other to accomplish user goals. However, the capacity of Agentic Web is still limited by insufficient autonomous software agent population, which has become a crucial challenge for scaling Agentic Web. In order to alleviate this, we study the task of automatically converting existing code repositories into autonomous software agents via coding agents, decompose the process into critical stages, and identify key technical hurdles. To systematically evaluate this capability, we propose SoftWare Agent generation for Agentic Web Bench (SW-$A^2$-Bench), the first benchmark designed for software agent generation. SW-$A^2$-Bench evaluates not only whether software agents can be generated, but also whether generated software agents are faithful to the source repositories and interoperable with other agents in multi-agent workflows. Our experiments demonstrate that our approach effectively activates the functional capabilities of code repositories and enables interoperable multi-agent collaboration in Agentic Web. We believe that this work will provide a standardized evaluation for software agent generation and will contribute to the future of scaling the capacity of Agentic Web.

Can targeted user training unlock the productive potential of generative artificial intelligence in professional settings? We study this question using a randomized experiment in which 164 law students completed an issue-spotting examination under one of three conditions: no GenAI access, optional access to a large language model (LLM), or LLM access with a brief training intervention. Untrained LLM access proved counterproductive: relative to participants without any LLM access, untrained users wrote significantly shorter answers, committed more case misstatements, and scored marginally lower, though most differences fall short of conventional significance. Training reversed this pattern. Trained participants adopted the LLM at higher rates (41% vs. 26%; p = 0.044), scored 0.27 grade points higher than untrained users--roughly one fine grade--(p = 0.027), and stated applicable rules more accurately (p = 0.014). Principal stratification analysis suggests training operates primarily through adoption rather than effectiveness--the adoption lower bound (1.06) exceeds the effectiveness upper bound (0.42) at strict mean dominance--though confidence intervals are wide. More broadly, these findings challenge the view that GenAI primarily benefits lower-skilled workers: without training, higher-ability practitioners opt out while lower-ability users adopt but unproductively. Realizing GenAI's productivity gains requires investment in both access and instruction.

Systematic literature reviews (SLRs) are a demanding and high-stakes form of scientific knowledge synthesis that remains underspecified as an evaluation setting for large language models (LLMs). We introduce AgentSLR, a large-scale evaluation harness comprising an SLR automation workflow and an expert annotated dataset covering 16,248 articles, designed to test LLM capabilities across the stages of SLRs in epidemiology. Reference annotations were derived from peer-reviewed studies on WHO priority pathogens and produced by domain experts. The harness evaluates each review stage as a separate unit with dedicated metrics enabling targeted failure analysis. We evaluated five frontier reasoning models and found that no single model dominated across all tasks, showing sub-task specialisation often hidden by aggregate benchmarks. Structured data extraction is a major bottleneck, with no model exceeding an average field-level F1 of 0.67. Estimated costs vary substantially, by up to 96 times across evaluated models. Documented failure modes suggest that the evaluated models are not yet reliable enough for unsupervised deployment in epidemiology, where findings can inform public policy.

Hard-negative source selection for dense retrieval is usually decided only after fine-tuning and downstream evaluation. We propose $\mathrm{ECI}_{\mathrm{sem}}$, a semantic residual variant of Effective Contrastive Information (ECI) that ranks candidate negative sources using frozen target-encoder embeddings. $\mathrm{ECI}_{\mathrm{sem}}$ is training-free, not label-free: each scored example requires a query, a labeled positive, and an explicit candidate negative. $\mathrm{ECI}_{\mathrm{sem}}$ builds a weighted residual information matrix from target consistency, semantic locality, lexical residuality, and a log-determinant diversity objective. On MS MARCO negative sources, in-family $\mathrm{ECI}_{\mathrm{sem}}$ ranks LLM negatives highest among non-hybrid sources and Dense+LLM highest among hybrid sources, matching the strongest aggregate BEIR transfer results across DistilBERT, E5-base, and Contriever. Controlled ablations show that this alignment depends on using the target encoder family, while additional ablations show stability under sample-size, temperature, tokenizer, and IDF-corpus perturbations. The theory gives a local linearized link to loss reduction, while the empirical study treats downstream evaluation as the final test.

One of the most common machine learning setups is logistic regression. In many classification models, including neural networks, the final prediction is obtained by applying a logistic link function to a linear score. In binary logistic regression, the feedback can be either soft labels, corresponding to the true conditional probability of the data (as in distillation), or sampled hard labels (taking values $\pm 1$). We point out a fundamental problem that arises even in a particularly favorable setting, where the goal is to learn a noise-free soft target of the form $σ(\mathbf{x}^{\top}\mathbf{w}^{\star})$. In the over-constrained case (i.e. the number of samples $n$ exceeds the input dimension $d$) with examples $(\mathbf{x}_i,σ(\mathbf{x}_i^{\top}\mathbf{w}^{\star}))$, it is sufficient to recover $\mathbf{w}^{\star}$ and hence achieve the Bayes risk. However, we prove that when the examples are labeled by hard labels $y_i$ sampled from the same conditional distribution $σ(\mathbf{x}_i^{\top}\mathbf{w}^{\star})$ and $\mathbf{w}^{\star}$ is $s$-sparse, then rotation-invariant algorithms are provably suboptimal: they incur an excess risk $Ω\!\left(\frac{d-1}{n}\right)$, while there are simple non-rotation invariant algorithms with excess risk $O(\frac{s\log d}{n})$. The simplest rotation invariant algorithm is gradient descent on the logistic loss (with early stopping). A simple non-rotation-invariant algorithm for sparse targets that achieves the above upper bounds uses gradient descent on the weights $u_i,v_i$, where now the linear weight $w_i$ is reparameterized as $u_iv_i$.

With AI agents increasingly deployed as long-running systems, it becomes essential to autonomously construct and continuously evolve customized software to enable interaction within dynamic environments. Yet, existing benchmarks evaluate agents on isolated, one-off coding tasks, neglecting the temporal dependencies and technical debt inherent in real-world software evolution. To bridge this gap, we introduce DeepCommit, an agentic pipeline that reconstructs verifiable Milestone DAGs from noisy commit logs, where milestones are defined as functionally cohesive development goals. These executable sequences enable EvoClaw, a novel benchmark that requires agents to sustain system integrity and limit error accumulation, dimensions of long-term software evolution largely missing from current benchmarks. Our evaluation of 12 frontier models across 4 agent frameworks reveals a critical vulnerability: overall performance scores drop significantly from >80% on isolated tasks to at most 38% in continuous settings, exposing agents' profound struggle with long-term maintenance and error propagation.

World models simulate environmental dynamics to enable agents to plan and reason about future states. While existing approaches have primarily focused on visual observations, real-world perception inherently involves multiple sensory modalities. Audio provides crucial spatial and temporal cues such as sound source localization and acoustic scene properties, yet its integration into world models remains relatively underexplored. Prior work has not established a commonly adopted formulation for audio-visual world modeling under low-level action control or clarified how to jointly capture physically grounded binaural audio and visual dynamics. This work presents a unified formulation of Audio-Visual World Models (AVWM), casting multimodal environment simulation as a partially observable Markov decision process with synchronized audio-visual observations. As a foundational step toward this problem, we construct AVW-4k, a controlled benchmark comprising 30 hours of binaural audio-visual trajectories with action annotations across 76 indoor environments. We propose AV-CDiT, an Audio-Visual Conditional Diffusion Transformer with a novel modality expert architecture that balances visual and auditory learning, optimized through a three-stage training strategy for effective multimodal integration. Extensive experiments on this benchmark demonstrate that AV-CDiT achieves high-fidelity multimodal prediction across visual and auditory modalities. Furthermore, we validate its practical utility in embodied navigation, demonstrating that AVWM improves a vision-language-model-guided agent in continuous audio-visual navigation.

LLMs are increasingly used for code generation, but their outputs often follow recurring templates that can induce predictable vulnerabilities. We study vulnerability persistence in LLM-generated software and introduce Feature--Security Table (FSTab) with two components. First, FSTab enables a black-box attack that predicts likely backend vulnerabilities from observable frontend features and knowledge of the source LLM, without access to the backend or source code. Second, FSTab provides a model-centric evaluation that quantifies how consistently a model reproduces the same vulnerabilities across programs, semantics-preserving rephrasings, and application domains. We evaluate FSTab on state-of-the-art code LLMs, including GPT-5.2, Claude-4.5 Opus, and Gemini-3 Pro, across diverse application domains. Our results show strong cross-domain transfer: even when the target domain is excluded from training, FSTab achieves up to 94% attack success and 93% vulnerability coverage on Internal Tools (Claude-4.5 Opus). These findings expose an underexplored attack surface in LLM-generated software and highlight the security risks of code generation. Our code is available at https://github.com/fstabicml2026/FSTab

Transformers used for evidence-grounded binary adjudication (e.g., support/refute, yes/no, or verifier-backed pass/fail decisions) can be sensitive to the order in which exchangeable evidence is presented, producing dispersion across permutations and unreliable attempted answers under a verifier-relative Bernoulli predicate. We treat evidence order as a nuisance variable and formalize an expectation-realization gap: next-token training can minimize expected conditional description length over orderings while a fixed ordering remains position-sensitive. Our Quantified Martingale Violation (QMV) bound predicts the dispersion induced by adjacent-rank positional sensitivity, with $O(\log n)$ growth in the harmonic regime; our Expectation-level Decompression Law (EDFL) specializes a KL convexity/data-processing bound to Bernoulli predicates, yielding Bits-to-Trust (B2T), Risk-of-Hallucination (RoH), and an Information Sufficiency Ratio (ISR) gate for answer/abstain decisions. On 3,059 grounded items from FEVER, HotpotQA, NQ-Open, PopQA, and Controls, we observe logarithmic dispersion and positive Jensen gains from uniform permutation mixtures. In one pre-specified held-out audit (528 items), the analytically fixed ISR$=1$ gate attains 0.0-0.7% hallucination with 20.6-27.9% abstention (95% CIs), supporting the operating point without claiming universal calibration across all model families or unrestricted generation.

Allegro is a machine learning interatomic potential model designed to predict atomic properties in molecules using E(3) equivariant neural networks. When training this model, there tends to be a trade-off between accuracy and inference time. For this reason, we apply multi-objective hyperparameter optimization to both objectives. Additionally, we experiment with modified architectures by constructing variants of Allegro: one extended with additional classical layers and one incorporating quantum-classical hybrid layers. We evaluate all models on QM9, rMD17-aspirin, rMD17-benzene, and a self-generated dataset of copper-lithium structures. As results, both variants surpass Allegro in force prediction accuracy across multiple datasets. The classical variant consistently improves over the baseline, while the quantum-classical hybrid variant achieves the best overall force prediction accuracy on the Cu-Li dataset, where it was fully optimized, outperforming the classical variant by approximately 13%. Notably, the hybrid variant also achieves competitive results on the remaining datasets despite using hyperparameters transferred from Cu-Li without dataset-specific optimization, suggesting that quantum-classical hybridization is a promising direction for enhancing MLIP architectures.

We present TokaMind, to our knowledge the first open-source foundation model for tokamak plasma dynamics, based on a Multi-Modal Transformer (MMT) and pretrained on heterogeneous diagnostics from the publicly available MAST dataset. TokaMind supports multiple data modalities (time-series, 2D profiles, and videos) with different sampling rates, robust missing-signal handling, and efficient task adaptation via selectively loading and freezing four model components. To represent multi-modal signals, we use a lightweight fixed-basis Discrete Cosine Transform embedding (DCT3D) and provide a clean interface for alternative embeddings (e.g., Variational Autoencoders). We evaluate TokaMind on the recently introduced MAST benchmark TokaMark, which comprises 14 tasks with heterogeneous reconstruction and forecasting objectives. Our results show that fine-tuned TokaMind outperforms the strongest benchmark baseline on all but one task. Compared with training the same architecture from scratch under a matched epoch budget, warm-start adaptation is most beneficial on demanding downstream settings, including long-horizon forecasting and high-dimensional equilibrium objectives. These findings highlight the value of multi-modal pretraining for tokamak plasma dynamics and provide a practical, extensible foundation for future fusion modeling tasks. Training code and model weights are publicly available at github.com/UKAEA-IBM-STFC-Fusion-FMs/tokamind and huggingface.co/UKAEA-IBM-STFC, respectively.

Neural-network techniques are often transferred across architecture families by analogy, but such transfer is valid only when the assumptions required by a technique are preserved. We introduce this idea as inheritance between model classes. Using a unified node-level framework with tensor-valued activations, we prove that generalized feedforward networks (GFFNs) form a strict subset of generalized convolutional networks (GCNNs), so GCNN properties transfer directly to GFFNs. The reverse direction is not automatic: standard CNN nodes use spatial kernels, while FFN nodes use one scalar weight per input contribution. We introduce model projection to recover a restricted reverse inheritance path. Projection freezes each convolutional input-channel sub-function and learns one scalar coefficient for each input-output channel contribution, giving projected CNN nodes the GFFN-style trainable structure of scalar-weighted input recombination. This inherited structure leads naturally to parameter-efficient transfer learning. Across multiple ImageNet-pretrained CNN backbones and downstream image-classification datasets, model projection is competitive with standard and PEFT baselines and provides an effective initialization for subsequent full fine-tuning.

We develop an information-theoretic framework connecting stability, privacy, and generalization for quantum learning algorithms. Learning procedures are modeled as quantum instruments with classical-quantum outputs, and losses are represented by observables. We prove that under a classical-quantum sub-Gaussian condition, an information-theoretic stability measure controls the expected generalization error. Furthermore, we establish a high-probability generalization bound using quantum Rényi divergences to manage higher-order dependencies under non-commutativity. In the trusted Data Processor setting, quantum differential privacy (QDP) provides a mechanism for stability. We show that one-neighbor QDP strictly bounds the information leaked by the classical-quantum output. Combining this with our stability theorem yields a direct privacy-to-generalization guarantee. We also explore an untrusted Data Processor setting. Here, output privacy alone is insufficient since an adversarial processor could perform a highly informative procedure before applying noisy post-processing. To combat this, we introduce Information-Theoretic Admissibility (ITA), a certification condition ensuring the prescribed procedure is not just a degraded version of a strictly more informative, physically allowed operation on the encoded ensemble. We prove a fundamental separation: while admissibility and privacy are in strong tension in classical models, quantum non-orthogonality makes them compatible. A quantum measurement can be ITA - exhausting all relevant accessible information - without perfectly recovering the classical dataset. We illustrate this separation through a concrete quantum ITA example.