Papers

Industrial agentic AI systems increasingly exhibit a gap between prototype capability and production deployment. In particular, adaptive agents may generate plausible outputs while remaining difficult to verify under non-determinism, confidentiality constraints, limited context, and weak observability. This paper formulates a bounded verification protocol for adaptive agentic controllers represented by finite symbolic rules, explicit diagnostic predicates, explanation logs, and held-out re-evaluation. The central research question is: when an adaptive agentic controller is represented through finite rules, explicit diagnostic predicates, explanation logs, and held-out re-evaluation, which classes of controller failure can be detected, locally repaired, or rejected without relying on unrestricted human-in-the-loop judgment? The proposed framework treats the controller as a finite revisable object. Diagnostic failures are mapped to predefined rule-level edits, including rule addition, rule deletion, and priority revision. Repaired controllers are then evaluated on held-out simulation seeds or cloned initial states. Experiments in a stylized financially constrained inventory-control benchmark show three outcomes: resource-induced failures that remain non-repairable by one rule edit, partial repairs that are rejected because they violate thresholds or guardrails, and a local one-step repair of an order-volatility failure induced by removing a smoothing rule. The contribution is methodological and provides a simulation-compatible procedure for testing whether specific controller-level failures can be made observable, explainable, locally revisable, and empirically re-tested under controlled conditions.

The paper presents a voice anonymization model focusing on preserving content rather than producing realistic speech. It relies on content embeddings extracted from a frozen pretrained wav2vec2 encoder. These embeddings are decoded into an anonymized signal using vector quantization and a HiFi-GAN vocoder, both trained on LibriTTS without any waveform reconstruction loss or speaker embedding mapping. The training objective enforces that embeddings of the anonymized signal match those of the original one. While training, an auxiliary speaker classification branch with a gradient reversal layer is used to discard speakerspecific information. Results show that this straightforward embedding-based approach achieves very low WER (2.53) with an anonymization performance (EER 13.39) ranking within first level for VPC. Notably, emotions are partially preserved (UAR 43.91), even without a supporting training objective, while the anonymized voice is audible without reconstruction loss.

AI agents are increasingly deployed in shared environments where they pursue diverse goals and compete for rewards. This multi-agent competition can lead to behaviors that serve individual gains at collective cost – for instance, marketing agents may post misleading content as a result of competing for engagement on social media. Human societies address such problems through norms that constrain acceptable behavior, supported by enforcement mechanisms that detect and penalize violations. Motivated by this, we study norm enforcement mechanisms for language model agents. We find that simple enforcement mechanisms are exploited by misaligned agents for competitive advantage, even when they are not explicitly trained or prompted to do so. We thus turn our attention to designing more robust mechanisms, and identify two key ingredients: estimating each agent's reliability over time, and updating this estimate with escalating penalties for repeated misbehavior. Across three simulated environments and a variety of agent populations, mechanisms built on these principles resist exploitation, while still penalizing norm violations at comparable or lower cost than baselines. Our results position norm enforcement mechanisms as scalable levers for shaping agents' behavior, but only when designed to anticipate becoming part of the system they govern. Our code and data are available at https://yaowenye.com/norm-enforcement.

A cheap swarm of unreliable agents can be steered to a correct consensus by a few strong, expensive "oracle" correctors. We ask how much one must spend, and where to place the oracles. We model the swarm as a consensus on a graph in which each oracle pins one node toward the truth at a cost-coupled, concave strength, and measure quality by the coherence H(R)=tr M(R)^{-1}. Our first result is that H stays submodular (each added oracle helps less than the last) even when the oracles differ in strength, so a cost-benefit greedy comes within 1-1/e of the best placement at any budget. Inverting the budget gives the budget-correctness frontier B*(eps), the least spend that guarantees an eps-correct consensus: closed-form on the complete graph, and a minimal oracle count k* when oracles cost the same. Whether a budget then buys a few strong oracles or many medium onese curvature of the cost-quality law: diminishing returns favour spreadsharply increasion. Measured onthe Qwen3 ladder (0.6-32B), the law is concave for math verificatio convex foremergent code tracing, so the verdict is genuinely task-dependent.https://github.com/YehudaItkin/budgeted-oracle-placemen

The synthesis of safety-critical scenarios (SCS) and their evaluation through closed-loop simulations are crucial for developing robust autonomous driving systems. A key aspect of this process involves editing agent states in both appearance and trajectory levels within existing scenes. However, current methods struggle to preserve data fidelity after scene editing and fail to efficiently generate high-quality SCS through such modifications. To overcome these limitations, we propose OmniSCS, an innovative system that generates photorealistic SCS with high physical fidelity while enabling closed-loop testing in synthetic environments. OmniSCS comprises two key modules: 1) A Fully Editable Driving World Construction module that maintains high-fidelity agent appearance and background during scene editing via dual-strategy agent reconstruction and depth-refinement background reconstruction methods. 2) A SCS Synthesis module that facilitates object insertion and agent trajectory editing to synthesize diverse SCS while preserving data fidelity. Experiments on nuScenes, Waymo, and KITTI datasets show that OmniSCS outperforms state-of-the-art methods in edited scene fidelity. We further validate its ability to enhance autonomous driving algorithms and support real-time (13Hz) closed-loop testing. Overall, OmniSCS provides a safer, more effective, and cost-efficient solution for SCS optimization and testing in autonomous driving.

Engineering shape optimization faces challenges in both expert-dependent problem setup and surrogate-model reliability. In practical aerodynamic design, optimization settings such as editable regions, deformation ranges, and design-preservation constraints are typically specified manually by experienced engineers, while surrogate-based optimization may become unreliable for heterogeneous geometry databases and out-of-distribution designs. To address these challenges, we propose a knowledge-constrained shape-optimization framework that translates knowledge-based constraints and user intent into quantifiable parameters of DFFD-based deformation operators, enabling engineering-aware and controllable constrained optimization. We further develop a Mixture-of-Experts Neural Operator (MoE-NO) to improve drag prediction and trend consistency over heterogeneous aerodynamic datasets. Based on the MoE-NO encoder and Mahalanobis distance, an uncertainty-estimation strategy is introduced to detect out-of-distribution geometries and selectively trigger physics-solver feedback for local sample enrichment. Experiments on in-house MPV, SUV, and Sedan datasets show that MoE-NO achieves a test-set MAPE of $1.16\%$ and a trend-prediction accuracy of $94.34\%$, outperforming the best baseline results of $1.52\%$ and $90.34\%$, respectively. Vehicle shape-optimization experiments further yield CFD-validated drag coefficient reductions of approximately $4\%$ to $10\%$.

Sepsis is a leading cause of mortality, yet optimal treatment policies remain contested. Existing reinforcement learning (RL) approaches learn fixed strategies for sepsis treatment, limiting adaptability to changing clinical objectives during inference. We propose EHRMPC, a framework that decouples learning patient dynamics from optimizing treatment by training a patient digital twin in the form of a generative electronic health record (EHR) model. The digital twin predicts clinical trajectories under interventions and enables model predictive control (MPC) to optimize treatments via inference-time planning over simulations. We evaluate EHR-MPC on a multicenter ICU sepsis cohort spanning 8 hospitals in the Mass General Brigham health system using both off-policy importance sampling and on-policy simulation-based evaluation. Relative to RL baselines, EHR-MPC achieves comparable off-policy performance and improved simulation performance. Unlike RL, this work frames sepsis treatment optimization as inference-time control over learned patient dynamics, establishing a general framework for decision making with generative clinical models.

Large language models (LLMs) are increasingly applied to reverse-engineering tasks, and recent threat-intelligence reporting shows them operating inside live offensive-security workflows. Claims about their capability, however, outpace our ability to measure it. Existing benchmarks for LLM-assisted binary analysis treat the construction of function-level ground truth as a solved pre-processing step and report accuracy without disclosing how many functions were reliably evaluable. We argue that the principal obstacle to fair evaluation is not model capability but the reliability of binary-to-source alignment under compiler optimization. This paper presents Reforge, a provenance-tracked pipeline that constructs function-level ground truth from C source through compilation, DWARF and syntactic extraction, alignment, and decompilation, and that operationalizes alignment uncertainty as an eight-gate confidence funnel with three-tier stratification. On a controlled micro-benchmark, high-confidence yield falls from 87.2% to 65.9% across optimization levels, and unpaired comparisons overstate optimization-induced performance decay through survivorship bias. A proof-of-concept evaluation of seven contemporary LLMs on function naming demonstrates the validity of the concept and generally motivates an uncertainty-aware benchmarking practice.

Reinforcement learning agents for imperfect-information card games are only as strong as the opponents they train against, and they are hard to grade, since they beat a random opponent over 99 percent of the time and only tie copies of themselves. So we build a strong, fixed, rule-based expert for Gin Rummy and use it only as a yardstick, never for training. It beats every agent we trained 70 to 99 percent of the time. Across more than a hundred runs, we isolate what makes a lightweight agent stronger. Trust region updates, a well-aimed reward, a curriculum of tougher opponents, warm starting, and keeping the best checkpoint all help, and stacking them lifts a self-play champion from about 30 to 36 percent against the expert. Several ideas did not pay off. Short-term and longer-term reward shaping, learned state embeddings, imitation and DAgger, and a live large language model opponent were each unhelpful, too slow, or too heavy to train at scale. Comparing MLP, convolutional, set-based, attention, and recurrent encoders shows that extra capacity does little to break the ceiling, suggesting the limit is information rather than network size. We add standard baselines (neural fictitious self-play and information set Monte Carlo search) and confirm the approach carries over to Leduc Hold'em, where the optimum is computable. The result is a lightweight, game-agnostic recipe that trains competitive agents without training on the expert, for any game a small model can handle, reported with robust statistics and released as a reusable package.

Speech-to-text alignment means finding the temporal boundaries of each word in the audio. Some models provide such an alignment directly and others do not. Connectionist temporal classification (CTC) and transducer models have an alignment by construction, whereas attention-based encoder-decoders (AED) and speech large language models (LLMs) do not, and their word timings are usually read off the attention weights instead. All of these signals live on the encoder frame grid, which bounds their temporal precision. We study a generic gradient-based alignment that applies to any differentiable ASR model. We take the gradient of each teacher-forced token log probability with respect to the input, reduce it to a per-frame saliency, and decode the resulting matrix into word boundaries with a single dynamic-programming pass. The method needs no training, no model modification and no alignment heads, works across all model families including the speech LLMs, and aligns on the input grid rather than on the coarser encoder grid. We evaluate it on sixteen models from four families, on read (TIMIT) and spontaneous (Buckeye) speech, each against the model's own native or attention-based alignment. We find that the gradient yields a usable alignment for every model, that it is usually somewhat behind a strong native aligner but better where the native alignment is weak, as for the streaming models, and that its main disadvantage is the cost of one backward pass per token.

Recent advances in AI for Mathematics have focused largely on autoformalization and theorem proving, leaving the role of Computer Algebra Systems (CAS) in agentic LLM workflows underexplored. We propose a ReAct-style agentic setup that combines LLM reasoning with verifiable feedback from SageMath, together with Context7 for the up-to-date documentation. We evaluate this agentic setup across frontier models for solving research-level mathematical problems from the RealMath benchmark in a setting that emulates a computational-mathematics research loop. We also propose a refinement to the RealMath benchmark by introducing a multi-step post-processing procedure and a multi-stage validation pipeline, both of which improve the quality and reliability of the extracted problem set. Our experiments reveal substantial performance gains from SageMath access across all evaluated models on +9.7~pp on average, the gains range from 1.5~pp to 27.8~pp and narrow the gap between open-weight and closed models. Qwen~3.7-Max benefits from SageMath the most, while GPT-5.5 achieves the highest solve rate of $75.2\%$ and the lowest token usage among tool-enabled configurations. Our findings suggest that CAS-augmented agents represent a promising direction for assisting mathematicians in computational exploration, and we believe that this work is a step towards automated conjecture discovery. The project repository is available online.

For any E-commerce website it is a nontrivial problem to build enduring advertisements that attract shoppers. It is hard to pass the creative quality bar of the website, especially at a large scale. We thus propose a programmatic solution to generate product advertising headlines using retail content. We propose a state of the art application of Reinforcement Learning (RL) Policy gradient methods on Transformer based Masked Language Models. Our method creates the advertising headline by jointly conditioning on multiple products that a seller wishes to advertise. We demonstrate that our method outperforms existing Transformer and LSTM + RL methods in overlap metrics and quality audits. We also show that our model-generated headlines outperform human submitted headlines in terms of both grammar and creative quality as determined by audits.

While enabling effective collaboration on complex tasks, LLM-based Multi-Agent Systems (MAS) face critical security challenges due to vulnerabilities at the agent and interaction levels. Most existing MAS security defenses are built upon two core assumptions: semantically-explicit malicious attacks and explicit graph-based modeling of the MAS topology and agent-level interactions. In practice, real-world attacks are becoming more semantically stealthy, while MAS execution is typically asynchronous without the temporal alignment assumed by graph-based propagation models. To address these limitations, we propose AcMAS, an activation-based framework for malicious-behavior detection in MAS. By analyzing internal reasoning states in the activation space of local agents, AcMAS detects even stealthy attacks in a synchronization-robust fashion, without relying on explicit interaction graphs. Moreover, our activation analysis provides critical signals to guide AcMAS in restoring the functionality of compromised agents, rather than the disruptive agent isolation commonly used by the state-of-the-art methods. Comprehensive evaluation demonstrates that AcMAS significantly outperforms graph-based baselines against stealthy attacks, by +0.22 F1 in synchronous settings (0.94 vs. 0.72) and by +0.55 F1 in asynchronous settings (0.93 vs. 0.38), with generalization across diverse open-source LLM backbones, attack intensity, and MAS scale.

Open physiological corpora are heterogeneous: they use different sensors, labels, sampling rates, recording settings, and clinical endpoints. They can support detector design, but they do not directly specify which detector rules should be built for a new contactless monitoring platform. We report a controlled four-analyst large-language-model (LLM) workflow for converting 68 public physiological corpora, screened for commercial-use compatibility, into an auditable library of candidate rule shapes for prospective validation. Four independent commercial LLM families read the corpus documentation under a controlled prompt and produced 695 candidate rule markers (top-markers). Deduplication retained 649 rule records; a threshold-bounds audit then flagged 51 sanity violations for clamping or curator review. Cross-corpus consolidation produced 436 unique rule shapes. Gate-tagging against two hard invariants, native target-hardware channel availability and no multi-night per-patient personalization, identified 94 build-now detector components across four detector-family buckets. The pipeline does not produce a validated clinical detector. It produces an auditable engineering cascade in which analyst disagreement, threshold checks, curator review, and automated continuous-integration (CI) checks route literature-derived rules toward prospective hardware validation.

Evaluating uncertainty in AI-generated SQL queries requires estimating whether a query is correct, where correct means it executes to the same result as a human-written reference. We study which signals predict correctness on hard multi-table text-to-SQL, using AUROC to measure how well each ranks correct queries above incorrect ones. On BIRD and Spider, black-box signals such as string, structural, and execution self-consistency, a schema-relevance score, and query executability all fall between about 0.61 and 0.68 AUROC, with string self-consistency strongest at 0.675; white-box log-probability is similar (0.67). The signals that move past this ceiling are verification-based: an LLM judge scores from 0.72 (GPT-4o-mini) to 0.78 (Claude). Judges from different providers make different errors, so a two-provider ensemble reaches 0.82 AUROC with a well-calibrated probability (expected calibration error 0.03) and supports useful abstention frontiers (for example, answering 27% of questions at 24% selective risk) where self-consistency offers no valid low-risk subset. The pattern holds across two benchmarks, two generators, and two judge providers. We also ask whether a verifier can be trained. Fine-tuned verifiers, both encoder and generative, reach about 0.77 to 0.79 AUROC in-distribution but fall to about 0.66 on unseen schemas; scaling to 7B, adding schema diversity, distilling a strong judge's rationales, and cross-benchmark training all fail to close that gap. Cross-schema transfer appears to track model scale and reasoning rather than fine-tuning. In practice, correctness uncertainty for text-to-SQL lives in reasoning-based signals: a fine-tuned verifier is a good in-domain tool, but a verifier that generalizes across schemas currently means a large frozen reasoning model.

Deep learning has achieved remarkable success in various domains including time series analysis, computer vision and natural language processing. However, high computational and memory demands of state-of-the-art architectures pose challenges for deployment in resource-limited environments. Knowledge Distillation (KD) addresses this by transferring knowledge from a large teacher model to a smaller, more efficient student model while maintaining competitive performance. In this work, we investigate the effectiveness of KD for Time Series Classification (TSC) across three architectures: the classical Fully Convolutional Network (FCN), the convolutional Inception model and the transformer-based ConvTran model. We evaluate our approach on UCR Archive, the largest benchmark repository of time series datasets, by modifying architectural components such as convolutional filters, Inception modules and attention heads across the three architectures. Our results consistently show that KD most effectively benefits student models of intermediate complexity across all three architectures, with the distilled FCN student reducing parameters by a factor of 38, the distilled Inception student achieving nearly the same performance as the teacher with 42% fewer parameters and the distilled ConvTran student with 2 attention heads showing the most significant improvement through distillation. To encourage further research and reproducibility, we provide our implementation at https://github.com/MSD-IRIMAS/KD-4-TSC.

Standards bodies, including TM Forum, 3GPP, and ETSI, are converging on Agentic AI as the foundation for next-generation network management, where Large AI Model (LAM)-based agents autonomously interpret intent, coordinate resources, and adapt operational behaviors at runtime. However, achieving this vision at the scale and complexity of 6G networks requires management systems that can generate and evolve their own automation software during operation. We introduce Autogenic network management, a reference architecture that extends agentic capabilities with self-programming, self reflection, self-orienting, and self-architecting capabilities. The architecture supports practical staged deployment beginning with human-supervised LAM-based agents and progressing toward autonomous operation as confidence builds. We demonstrate the approach through high-priority operator scenarios drawn from TM Forum's autonomous network use cases, showing how autogenic management addresses real operational challenges. We conclude with a research roadmap outlining the technical advances needed to make autogenic network management realistic in future 6G networks.

This paper investigates over-the-air federated learning (AirFL) in wireless systems where the access point is equipped with a multi-waveguide pinching antenna system (PASS). We adopt the widely studied learning-oriented AirFL formulation, which seeks to maximize the number of selected devices while keeping the aggregation distortion below a prescribed threshold. The resulting joint optimization of device selection, receive beamforming, and pinching-antenna placement is highly nonconvex due to the intricate coupling among these system variables. To address this challenge, we develop AirPASS, an alternating optimization framework with two main components: a homotopy-Riemannian margin-consolidation method for device selection and receive beamforming under a fixed PASS configuration, and a homotopy-assisted geometry optimization method for updating the pinching-antenna positions under fixed selected devices and beamformer.

Recent progress on ARC-AGI-1 from disclosed architectures has come broadly from two regimes: heavy test-time compute over frontier models (evolutionary search, exhaustive sampling, extended chain-of-thought), or benchmark-specific training in which small models are fine-tuned on ARC data, often with task-specialized architectures. We study a third regime: an open-weight model in non-thinking mode (DeepSeek V3.2) under a strict budget, with no ARC-specific fine-tuning. We study what is recoverable through architecture alone, building agentic harnesses that decompose pattern-discovery and program-synthesis stages explicitly. First, we introduce an Explorer-Definer Pipeline that separates pattern discovery from executable transformation synthesis, implemented as a two-stage agent pipeline. Next, we present the Reflective Orchestrator, which augments the pipeline with autonomous exploration of new transformations when previous hypotheses fail on training pairs. On the ARC-AGI-1 public 400-task evaluation set, the pipeline reaches 57.50% pass@2 at \$0.25 per task, and the orchestrator reaches 67.25% pass@2 at \$0.62 per task. Together these architectures lift a 15.50% one-shot baseline by ~52 points without benchmark-specific training or heavy test-time compute. Furthermore, the orchestrator-driven lift tests a falsifiable diagnostic the pipeline produces; unbiased pass@k analysis suggests the pipeline is generation-bound, not selection-bound (selection via training-pair accuracy captures ~95% of the candidate ceiling) and predicts that significant improvement requires broader generation, not better ranking. The orchestrator implements this prediction via adaptive re-exploration and confirms it (unbiased pass@1 lift +9.81 pp, matching selection-mediated pass@2 lift). An additional pipeline ablation identifies its think tool as a significant component, with removal reducing pass@2 by 5.75 pp.

Autonomous systems under partial observability act on beliefs, not raw sensor events. QANTIS treats the quantum processor as a calibrated belief-update service in that loop: it receives a prior and an observation model, estimates the rare-event evidence term, and returns an ordinary posterior to a classical planner. This paper asks whether that service can be reused across a sequential Tiger POMDP horizon on present IBM Heron hardware without corrupting the planner-facing posterior. We answer with a controlled hardware case study rather than an end-to-end autonomy or wall-clock speedup claim. The study compares no amplification, guarded Grover amplification, and all-step fixed-point amplification on the same trajectory, then checks whether the returned posterior would change the downstream action. All-step FPAA preserves the Tiger posterior across the reported 8-step and 12-step primary runs, and the 20-step and 32-step controls remain inside the same operating band. In every reported decision check, the hardware posterior and the exact Bayes posterior select the same immediate action. Boundary-aware BIQAE stabilizes amplitude estimation near zero and near one, while a rare-event sweep maps the logical sample-complexity envelope for one-in-a-million evidence. The result is an operating envelope for a hardware-calibrated belief-update primitive, not a standalone hardware-advantage claim.

Agent-based modeling (ABM) has the capability to model millions of individuals and their interactions, which is useful for policy making. However, ABMs have traditionally relied on static prior, which prevents the models from adapting to real-time changes. Our research provides a novel approach to addressing this information gap. Large language models (LLMs) offer new opportunities to predict human decision-making. Here, we introduce a scalable Hybrid Agent-based and Language-driven Epidemic (HALE) modeling framework that leverages LLMs to predict human decision-making in an ABM simulation. As a proof-of-concept, we use HALE to simulate COVID-19 and its effects in Salt Lake County, UT.

Smart home automation platforms increasingly rely on user-authored YAML configuration files to define device behaviors, but these files are prone to syntax, formatting, and semantic logic errors that can cause automation failures and safety risks. Existing YAML validators, static analysis tools, and general-purpose large language models offer limited support for end-to-end diagnosis and repair because they lack domain-specific understanding and validated correction workflows. This paper presents SmartHomeSecure, a prototype for automated detection and repair of Home Assistant configuration errors using lightweight program analysis and constraint-guided large language model generation. SmartHomeSecure parses YAML files, detects syntactic and common semantic errors, normalizes error context, applies deterministic auto-fixes for routine defects, and constructs constrained prompts that guide LLMs toward minimal and structurally valid repairs. The system is implemented as a modular web application with four layers: UI Shell, Feature Orchestrator, Domain Engine, and Integration Layer. Its repair pipeline was evaluated on 100 real-world Home Assistant YAML files with manually injected errors across five categories: syntax/parsing, indentation, mapping, sequence, and scalar quoting errors. Four models were tested: gpt-oss-20b, gpt-oss-120b, llama-3.1-8b, and llama-3.3-70b. Results show that three models achieved 100% error detection accuracy, with repair success rates ranging from 87% to 93%. Manual verification found no hallucinated or incorrect repairs among successful outputs. These findings suggest that combining domain-aware program analysis with constrained generative AI is a feasible approach for improving the reliability and usability of smart home configuration repair.

Soft robots have attracted significant attention in applications such as medical intervention, rehabilitation, and robotic manipulation due to their inherent compliance, flexibility, and high degrees of freedom. Modular soft robots (MSRs), composed of multiple interconnected segments, represent an emerging class of robotic systems with highly deformable and reconfigurable structures capable of performing complex tasks. However, designing controllers for MSRs remains challenging due to their nonlinear dynamics, modeling complexity, and hyper-redundant nature. Existing approaches typically require controllers to be retrained from scratch whenever the robot morphology changes. In this work, we address these challenges through a continual learning inspired control framework capable of incrementally adapting to changes in robot morphology while preserving previously acquired knowledge. Specifically, the proposed framework enables the controller to sequentially learn new MSR configurations without forgetting previously learned ones. In addition, for MSRs with fixed configurations, the same framework can be employed in a distributed manner to learn module-specific dynamics, enabling localized control and improved precision. The proposed approach is validated through closed-loop trajectory tracking experiments in simulation using a tendon-driven soft robot, as well as on a real-world three-module pneumatic soft robotic arm. Furthermore, we demonstrate the adaptive capabilities of the framework through a reaching experiment in which the controller selectively activates only the necessary modules to reach a virtual target position, thereby reducing computational overhead.

Training large language models (LLMs) with extended reasoning has enabled in-context search, in which models iteratively generate, critique, and revise solution attempts. We provide a theoretical analysis of in-context search by modeling it as approximate inference over reasoning traces, where the base model defines a prior and self-reflection provides feedback for posterior updates, and study the resulting inference-time sampling complexity - the number of sequential attempts needed to achieve high success probability. We show that when reflections reliably localize early mistakes, in-context search can yield exponential improvements over the base model, solving problems with exponentially small zero-shot pass rates using only a polynomial number of sequential attempts, whereas when this property fails, conditioning on past attempts offers no asymptotic benefit over parallel sampling. We further show that these gains are robust and learnable: approximate posterior updates suffice, and cross-entropy training on search rollouts recovers the required behavior with polynomial sample complexity. Finally, we show that under a stagewise abstraction of reinforcement learning with verifiable rewards, the optimal policy extension implements the same posterior reweighting rule. We validate key qualitative predictions of the theory on real large reasoning models.

Large language models are rapidly moving towards closing the development cycle, transitioning from simple assistive companions to autonomous contributors deeply embedded into collaborative development environments. Despite their accelerated adoption, existing evaluation techniques are limited due to their fragmented nature and distorted projection of true model capabilities, often obtained from hypothetical syntactic scenarios. This research aims to bridge this gap by providing a comprehensive evaluation methodology for LLM-powered agents that is grounded in real-world software development practice. Our evaluation approach focuses on contamination-awareness, in-the-wild agentic behavior assessment, and trajectory-aware benchmarks and metrics capturing realistic coding contexts, human-aligned behavior, and model failure modes.

Vision Language Action (VLA) models unify visual perception, natural-language understanding, and action generation within a single foundation model, allowing a robot to follow instructions such as fold the towel or fly to the red building directly from camera images. Because VLAs inherit world knowledge from internet-scale pre-training, they have become the dominant framework for learning-based manipulation, with bimanual coordination serving as the most demanding testbed: two arms with 7 degrees of freedom each must move in concert to fold, assemble, and reorient objects. Unmanned aerial robotics faces a structurally similar challenge: a drone must coordinate thrust, attitude, and increasingly gripper commands from visual observations under strict latency and payload constraints. This review covers 183 contributions spanning 2017-2026 and organized along seven dimensions: VLA architectures, training recipes, action representations, bimanual coordination (2022-2026), unmanned aerial vehicle (UAV) navigation and control (2017-2026), language grounding, and cross-cutting concerns including memory and world models. We show that the coordination strategies, training recipes, and action representations developed for bimanual VLAs transfer to unmanned aerial systems and identify fourteen research directions across both domains.

Interactive simulators have become powerful tools for training embodied agents and generating synthetic visual data, but existing photorealistic simulators suffer from limited generality, programmability, and rendering speed. We address these limitations by introducing SPEAR: A Simulator for Photorealistic Embodied AI Research. At its core, SPEAR is a Python library that can connect to, and programmatically control, any Unreal Engine (UE) application via a modular plugin architecture. SPEAR exposes over 14K unique UE functions to Python, representing an order-of-magnitude increase in programmable functionality over existing UE-based simulators. Additionally, a single SPEAR instance can render 1920x1080 photorealistic beauty images directly into a user's NumPy array at 73 frames per second - an order of magnitude faster than existing UE plugins - while also providing ground truth image modalities that are not available in any existing UE-based simulator (e.g., a non-diffuse intrinsic image decomposition, material IDs, and physically based shading parameters). Finally, SPEAR introduces an expressive high-level programming model that enables users to specify complex graphs of UE work with arbitrary data dependencies among work items, and to execute these graphs deterministically within a single UE frame. We demonstrate the utility of SPEAR through a diverse collection of example applications: controlling multiple embodied agents with distinct action spaces (e.g., humans, cars, and robots) across several in-the-wild UE projects; rendering photorealistic city-scale environments; manipulating UE's procedural content generation systems; rendering synchronized multi-view images of detailed human faces; coordinating an interactive co-simulation with the MuJoCo physics simulator; and editing scenes with natural language via an AI coding assistant.

Finance, sensing, and demand streams violate the exchangeability that IID conformal prediction and the IID bootstrap assume, and existing libraries implement either a general resampling engine or conformal calibration without the other. tsbootstrap provides block, residual, sieve, and wild resampling, classical bootstrap confidence intervals, and adaptive conformal calibrators (EnbPI, ACI, NexCP, AgACI) through a single typed API in which a specification object selects each method. In a controlled coverage study the IID bootstrap undercovers sharply under dependence; dependence-aware methods reduce the coverage deficit, the sieve nearest to nominal under short-memory linear dependence. On the shared fixed-statistic path a compiled backend runs several times faster than arch, and a streaming reduce avoids materializing the $O(Bn)$ replicate tensor, limiting peak extra memory to $O(B)$ for the statistic array. The software is MIT licensed (v0.6.1).

Knowledge workers switch between applications thousands of times per day, spending nearly a tenth of the work year transitioning between digital applications in a process called digital fragmentation. Whether this fragmentation reflects who an employee is, where they work, or what kind of day they are having, has remained an open question. We analyzed 103 million application events recorded second-by-second from 1,017 employees across eight organizations that largely employ knowledge workers (e.g., law, financial services). Day-to-day variation in fragmentation within individual employees accounted for 44.6% of the variation in digital fragmentation, slightly exceeding stable individual differences between employees (35.8%), and far exceeding variation between organizations (19.6%). Fragmentation rose over the work week and reset after weekends and holidays. Higher-than-typical use of communication applications coincided with more fragmented work. Generative AI use also occurred on more fragmented days, but the period following AI use was marked by narrower, longer, and more predictable application use. These findings identify the workday as a key level for understanding and intervening on digital fragmentation and suggest that AI may help structure fragmented work rather than merely intensify it.

This paper introduces Diffusion Semi-Relaxed Fused Gromov-Wasserstein (DsrFGW), a novel method for graph comparison that unifies node features and structural connectivity through optimal transport. While traditional Gromov-Wasserstein and semi-relaxed variants (srGW, srFGW) capture graph structure, they often struggle with sparse, noisy, or partially observed graphs. Inspired by Graph Diffusion Distance, which posits graphs are similar if they enable similar information transmission patterns, DsrFGW incorporates diffusion processes allowing information propagation across nodes, capturing local and global structural patterns while reducing sensitivity to noise or missing edges. An extensive evaluation on 36 synthetic pairwise graph matching tasks (easy, medium, hard) demonstrates consistent superiority over srFGW, achieving accuracy improvements of 0-20 percentage points and dramatic Adjusted Rand Index (ARI) gains: in medium-difficulty scenarios, srFGW often achieves negative ARI (worse than random) while DsrFGW offers better performance in terms of both internal and external clustering quality measures (i.e., Adjusted Rank Index and Accuracy with respect to the true underlying clusters, respectively). Even under severe noise, DsrFGW improves clustering quality in 92% of the synthetic tasks with optimal diffusion scales adapting to problem difficulty, establishing DsrFGW as a robust framework for graph comparison under structural uncertainty.