Intelligent production requires systems to make decisions and organize work according to production goals and operating conditions. It also requires continuous adjustment through feedback. This paper analyzes intelligence in human production organizations from a complex adaptive systems (CAS) perspective. The analysis identifies two coupled mechanisms: individual autonomy and collective coordination. Individual autonomy enables actors to form local decisions using available information. Collective coordination aligns these decisions with shared goals and joint constraints. Learning and adaptation improve both mechanisms over time. A production-system model formalizes how local decision rules and coordination jointly form system decisions. On this basis, we propose the Recursive Autonomous Agent (RAA) framework, which combines goal-driven autonomous agents with a recursive organizational structure. Goal contracts define local objectives and operating boundaries, while capability contracts support the selection and composition of production units. Common interfaces allow coordinated groups to participate as units in larger organizations, connecting equipment, production lines, and factories. RAA thus provides an engineering approach to next-generation intelligent manufacturing, translating the requirements of intelligence, openness, and system-wide integration into mechanisms for autonomous and coordinated production.
Security-by-design emphasises integrating security into software design and development. Security pattern catalogues operationalise this principle by prescribing reusable architectural solutions to recurring security problems. However, recovering their implementations from source code remains challenging because security patterns are abstract, span multiple components, and admit many valid implementations. We present SecPatRec, a hybrid approach for automated security pattern recovery from source code repositories. We treat a security pattern as a reference architecture and frame its recovery as a deductive task: determining which prescribed roles are present, grounding them in code entities, and recovering their interaction sequences. SecPatRec pairs a ReAct-style LLM agent equipped with semantic and lexical code search for role detection and grounding with static code property graph analysis for interaction recovery. We curate a human-validated ground-truth dataset of 100 pattern instances covering five security patterns across 93 open-source Java and Python repositories, and introduce a three-level evaluation framework measuring recovery correctness against this ground truth. We evaluate SecPatRec using four LLMs, including proprietary and open-source models. Averaged over all models and pattern instances, SecPatRec achieves role-detection accuracy of 0.84, role-grounding similarity of 0.84, and an interaction-recovery score of 0.66. Compared to a one-shot end-to-end LLM baseline, SecPatRec achieves higher aggregate recovery scores and lower estimated LLM API costs per run, while processing repositories that exceed the baseline's configured input limit. The recovered role mappings and statically derived interaction sequences provide structural and behavioural evidence that can support inspection of security-pattern implementations.
Office documents are now routinely uploaded to large language models (LLMs) for processing. However, an LLM does not always see what a human sees, because it typically reads the text that an extractor produces from the document's underlying Office Open XML (OOXML) files. Depending on the implementation, extractors differ in which OOXML parts they read and how they interpret them, so their output can differ from what Office applications display. For example, by slightly shifting the positions of text boxes on a slide, an adversary can swap the order in which the model reads them while the slide looks unchanged. We show that this extraction divergence is an attack surface for LLM applications. In this work, we first measure what an adversary can exploit by analyzing the widely used extractors that LLM applications rely on. By combining static source code analysis with dynamic analysis, we identify 19 OOXML channels where extractors read content a human cannot see and 12 where they drop content a human can. We also find that widely used extractors ignore display formatting and reading order, so even visible content reaches the model in a different form. Building on these findings, we construct five attacks that lead the model to interpret a document differently from a human reviewer, without injecting any instruction. We test the attacks on four major chat assistants (ChatGPT, Claude, Gemini, and Microsoft 365 Copilot) and four coding agents (Codex, Claude Code, Antigravity, and GitHub Copilot CLI), and every one of them is misled by at least one attack. Finally, we propose Prism, a lightweight defense that reconstructs the human view from the OOXML specification before passing the text to the model. Prism also generalizes to unseen attack payloads.
Recognizing visual content from neural-network weights requires separating functional information from arbitrary parameter coordinates. We audit this separation with hidden-neuron permutations and positive ReLU rescalings that preserve the represented function. The study contains 480 independently fitted shape fields and 1,000 MNIST fields, with transformed copies grouped by origin. On shape recognition, a statistics reader falls from \ShapeRawStats\% to \ShapeJointStats\% accuracy under joint transformations; a normalized set reader retains \ShapeNormSet\% with unchanged predictions. Four small frozen language models obtain \LMRange\% raw accuracy with next-token scoring. A separate four-configuration reasoning experiment with 1,920 scored sessions obtains \FrontRawRange\% raw accuracy with generated answers, while fresh identical raw prompts disagree on \FrontRawRepeatRange\% of origins. Canonicalization makes equivalent prompts identical, but this neither establishes recognition nor guarantees identical generated responses. Joint correctness/agreement metrics, semantic-cue controls, fresh repeats, and exact-rational rounding bounds separate these failure modes. The result is an inspectable evaluation protocol for visual weight readers, with claims restricted to the tested fields, prompts, and execution configurations.
Short-horizon model predictive control (MPC) is fast but myopic. ZipMPC compensates by learning a context-dependent correction of the short-horizon cost that imitates a long-horizon expert. We observe that the optimal correction is often multimodal: when a slower opponent can be passed on either side, good corrections of opposite sign coexist, and the expert's choice between them hinges on tiny cost differences. Deterministic regression then averages modes or inherits inconsistent expert tie-breaking. We propose ZipDrift, which trains a one-step drifting generator over MPC cost corrections, tilted toward low closed-loop cost and learned only from cost evaluations of candidate corrections, without differentiating through the optimiser. A few generated candidates are ranked by a learned critic, and the model-based MPC then enforces dynamics and constraints. In a kinematic overtaking benchmark derived from ZipMPC, more than half of the contexts are bimodal and the manual short-horizon MPC crashes in 28% of them. With an eight-dimensional stagewise correction, evaluated on 1000 fresh contexts and five training seeds, ZipDrift with eight candidates crashes in 0.74% of episodes, compared with 3.4% for an idealised ZipMPC-style regressor and 2.1% for critic-ranked random candidates with the same budget. A mixture density network (MDN) with the same selection is equally good (0.76%). The benefit of drifting lies in sample quality: in a pre-specified test on further unseen contexts, a single drifting sample crashes in 8.7% of episodes against 13.2% for the MDN, and ZipDrift needs four candidates instead of eight to fall below 1%. With many candidates, all methods degrade as selection exploits errors of the critic.
Large language model (LLM) agents increasingly rely on external memory stores to retain information across conversations, typically via dense vector embeddings searched with approximate nearest-neighbor methods. The fruit fly's olfactory circuit computes a locality-sensitive hash of sensory input using a strikingly different mechanism - sparse random projection followed by winner-take-all competition - and prior work (Dasgupta et al., 2017) showed this scheme, dubbed FlyHash, preserves neighbor structure better per bit than conventional random-hyperplane hashing (SimHash) on several benchmarks. We apply FlyHash, to our knowledge for the first time, to LLM agent memory retrieval, and ask three questions a practitioner actually needs answered: does the quality advantage hold under a correctly matched-bit protocol (it does, robustly, across 10 seeds and four datasets spanning two modalities, with one specific, previously undocumented comparison pitfall identified and corrected along the way); does that advantage translate into real memory and latency savings, including against the dense-vector indexing (HNSW) practitioners default to today (no: at equal bits FlyHash's codes are larger and slower to compare than SimHash's, and HNSW dominates both hash methods at ordinary scale; a sparse-set comparison we introduce recovers most but not all of a naive latency gap, leaving hashing's practical case narrower and more specific than the quality result alone implies); and does the advantage survive genuine, non-circular agent-memory relevance labels rather than the nearest-neighbor-by-embedding proxy this literature otherwise relies on (it does). We report all three answers precisely, including the two that narrow rather than flatter the headline result, and release our implementation, a working agent-memory demo, and a full account of the methodological pitfalls we found and corrected.
Observed populations of rotating neutron stars~(NSs) with millisecond-order periods are powerful probes of fundamental physics. Mass-radius measurements inform poorly constrained properties of degenerate nuclear matter, whereas high-fidelity population synthesis connects unknowns in NS formation and binary evolution to large radio-timing surveys. However, repeated structure calculations are prohibitive due to the computational cost of solving the highly coupled partial differential equations of axisymmetric general relativistic hydrostatic equilibrium that govern rotating NS interiors. Non-rotating calculations or approximate rotational corrections can bias equation of state inference and limit the fidelity of population synthesis in tracing the evolutionary history of progenitors and propagating equation of state uncertainties. In this \textit{Letter}, we develop physics-informed neural operators that can solve the axisymmetric problem with high accuracy and negligible computational cost. \textit{Our solvers are trained in a fully unsupervised setting, with the training objective informed solely by the partial differential equations, and achieve a $10^3\times$ speed-up with negligible accuracy loss}. These solvers enable scalable EoS inference that self-consistently accounts for rotation and repeated stellar-structure calculations during binary evolution, making spin predictions that account for rotational structure and EoS uncertainties computationally accessible to population synthesis.
Recent advances in large language models (LLMs) have established human-agent collaboration as a promising paradigm for data science. Effective collaboration requires a shared computational abstraction that enables agents to reason about processing logic while allowing human analysts to understand, guide, and refine the analysis. Although scripts written in Python or SQL provide precise control, their syntax and execution details can be difficult for analysts to understand and modify. In this paper, we argue that dataflows are an effective abstraction for human-agent collaboration in data science. We introduce BobFlow, a system that combines the dataflow abstraction with the ReAct paradigm. It enables agents to iteratively construct and execute dataflows for data science tasks while allowing analysts to inspect the analysis and provide feedback. Our user study shows that BobFlow helps analysts understand, inspect, and verify agent-generated analyses. A thorough experimental evaluation across proprietary and open-weight LLMs shows accuracy score gains of up to 18.6 points at just over 1/3 of a script-based ReAct agent's inference cost.
Before an AI agent takes on a paid job, someone has to judge whether it is likely to succeed. We test whether frontier language models can make this call before any attempt. We propose PAYWORTHY which contains 1{,}494 real freelance job postings, sampled from 18.8M postings made between 2020 and 2026 on a freelancing platform. An agent attempts each job from the posting alone in a single run, and an LLM judge acting as the client decides whether to accept the work. We ask 18 models to forecast how likely the agent is to succeed and measure how well each model's forecasts rank the accepted jobs above the rejected ones (AUC, where 0.5 is a random ranking). The answer depends on how the agent is described. Told what the agent cannot do, every model ranks the jobs well (AUC 0.66--0.86). Told instead that it is a generic agent with a browser and code execution, the same models rank the same jobs about as well as a random ordering (0.45--0.56). These results hold under judges from four other model families (Claude, GLM, Kimi and Qwen), and the informed forecasts also rank the verdicts of two human raters. Code is available at https://github.com/upwork/Payworthy
Organizations accumulate evidence in conversations, documents, decisions and relationships, but they act on interpretations: judgements assembled from several observations, resting on assumptions, and revised as circumstances change. Existing retrieval, knowledge graphs and agent memory keep the records and lose the interpretation. We propose a four-layer architecture, Signals, Domains, Claims and Dimensions, in which interpretations persist with their justifications and standing, a truth-maintenance network revises that standing as evidence changes, and validated, versioned Dimensions position interpretations on named axes. We call the result a shared organizational cortex. In a registered retrieval experiment, the Dimension term gains 0.028 nDCG@10 (p = 0.002). In system-level comparisons, the full retrieval configuration improves nDCG@10 by 0.081 over Signals-only and 0.053 over graph-augmented Signals-only retrieval (both reported p < 0.001). The architecture gives organizations a persistent, revisable basis for shared judgement.
Large language models (LLM) have been the key focus of recent machine learning breakthroughs. As the model size grows exponentially, the computation needed for training is astronomical. A GPU can do a huge amount of arithmetic. However, the data its compute units need is not always available when they are ready. This data may still be in slow memory or on another GPU. While the chip waits, expensive compute sits idle, and at scale even a small drop in utilization translates into substantial cost. In this paper, we treat this waiting time as the primary bottleneck. We focus on hardware features designed for explicit data movement. These features load data from off-chip memory onto the chip, rearrange it into the layout the computation requires as it is loaded, and transfer it between GPUs. By orchestrating them, we keep a steady pipeline of data flowing to the compute units so that they remain busy. We present kernel and framework implementations that address this bottleneck using three key data-movement instructions and hardware features. The Tensor Data Mover (TDM) moves tensor data from high-bandwidth memory (HBM) into on-chip memory. Transpose-load instructions transpose tensor data into the layout that LLM computations require as it is loaded on-chip. Finally, System DMA (SDMA) and Remote DMA (RDMA) move data between GPUs over the scale-up and scale-out networks, respectively. Our results show that TDM and transpose-load provide on average 1.88x and 1.19x speedup at the kernel level, respectively. The SDMA and RDMA lead to on average 1.16x and 1.33x speedup for computation overlapped with communication. This is the first AMD LLM training system to utilize all the GPU data pipelining features. Our implementation has been integrated into open source framework and library for AMD GPUs. https://github.com/AMD-AGI/Primus-Turbo https://github.com/AMD-AGI/Primus
Evaluating and improving domain-specific LLM responses requires high-quality reference data and rubrics, yet expert authoring is slow and expensive, and synthetic datasets may fail to capture practitioner preferences unless they are grounded in expert judgment. We present SME-C (Subject Matter Expert Critique), a human-AI workflow that captures expertise through lightweight critiques of candidate responses and complements it with LLM-driven analysis and refinement to iteratively curate response datasets and evaluation rubrics. We validate SME-C in the domain of financial business briefs, collecting 3,853 critiques from 411 finance professionals on 520 queries across two survey rounds. We evaluate two LLM-driven refinement strategies: one guided by the experts' written critiques and one that infers critique solely from their preference votes. In a blind validation survey with 100 additional professionals, we found that both strategies significantly improved quality over the experts' top-ranked baseline responses. The gains were concentrated among weaker original responses, and the two strategies excelled in different ways: critique-based refinement produced more domain-grounded improvements, whereas vote-based refinement was more effective at identifying and removing irrelevant content. The resulting rubrics and refined dataset support reproducible offline evaluation and benchmarking of LLMs, suggesting that structured expert critique is a viable alternative to expert authoring for building high-quality, domain-specific evaluation resources more quickly, at scale, and at lower cost.
Coding agents must deliver correct software while respecting users' expertise, preferences, and working conditions. Existing benchmarks increasingly incorporate interaction, yet personalized requirement fulfillment remains underexplored. We introduce PersonaCodeBench, which turns user characteristics into verifiable obligations in persona-driven multi-turn coding sessions. Our persona pool spans roles, technical abilities, interaction preferences, and practical constraints, yielding task-grounded evolved requirements for implementation, permissions, testing, explanation, and delivery. At runtime, a controller governs user simulator responses and requirement disclosure, using online requirement evaluation to provide feedback and advance the interaction. Requirements emerge progressively, with their content, disclosure conditions, and acceptance criteria fixed before evaluation. A completion verifier and a personalization verifier separately assess native correctness and persona fulfillment. Joint pass requires both adherence to the declared budget and compliance with validity conditions. We evaluate all major frontier agents, establish a comprehensive leaderboard, and conduct detailed experimental analyses to validate effectiveness. PersonaCodeBench supports reproducible evaluation of coding agents' ability to meet explicit, personalized user expectations alongside coding objectives.
Olfaction provides critical information about airborne chemical cues, yet it remains largely underexplored in embodied AI, with limited prior machine olfaction work focusing primarily on semantic odor perception. We introduce OdorSpaces, a physics-based simulation platform and benchmark for visual-olfactory embodied navigation. OdorSpaces augments Habitat-Sim with 3D odor transport and dispersion simulated by Fire Dynamics Simulator (FDS), enabling agents to navigate photorealistic indoor environments using both visual and olfactory observations. The benchmark includes two representative source-seeking scenarios: invisible gas-leak localization and early-stage fire localization. We develop an initial multimodal reinforcement learning policy that integrates visual observations and olfactory measurements over time. Experiments show that the policy outperforms a diverse set of baselines, establishing a strong reference for future research on visual-olfactory embodied navigation.
Conceptual abstraction and gender are two equally central aspects of the human mind, yet they have traditionally been studied in isolation from one another, as though they were fundamentally separate. Here, we find gender and abstraction are systematically linked throughout the space of concepts spanning single (N = 40,000) and multi-word expressions (N = 67,000): across billions of words and millions of images on the internet --- and across numerous measurement techniques, including human and AI classifications --- more abstract concepts are more associated with men, a pattern we show replicates in languages around the world. This male abstraction bias not only holds across semantic domains, but it also maps onto grammatical structure: verbs and adverbs are more abstract and more male-coded, revealing a system-wide trace of stereotypes accentuating agentic qualities in men. Furthermore, we show this bias readily emerges in the free associations humans and AIs produce in controlled online tasks, indicating its psychological internalization and its algorithmic reproduction. These findings identify a latent structure in conceptual space that unifies a range of stereotypes: for example, framings of women as more embodied, emotional, and warm, versus men as more cognitive, rational, and competent; as well as erroneous views of men as better at mathematics, science, and engineering. More broadly, by analyzing an unprecedentedly large, multimodal sample of online data, we provide culture-wide evidence of gender as a core organizing principle shaping conceptual space far beyond the characterization of people and social roles.
With scalable Laplacian solvers now available, the next frontier is to exploit them more effectively for high-quality hypergraph partitioning. In this work, we revisit spectral hypergraph partitioning from the perspective of spectral embedding geometry. Through a systematic analysis of circuit hypergraphs and controlled synthetic (hyper)graphs, we identify a ray-like embedding structure that helps explain the effectiveness of projection-based partitioning. We further show that the geometry of spectral embeddings can be systematically influenced through Laplacian design and hyperedge reweighting. Guided by these insights, we propose FRESHPart, a feedback-reshaped spectral partitioning framework that refines the spectral embedding through Geometry Feedback and Search Feedback, producing embeddings that are better aligned with projection-based partitioning. On the Titan23 benchmark, FRESHPart achieves average cut reductions over hMETIS of 13.09% at $\epsilon=2\%$ and 25.21% at $\epsilon=20\%$, surpassing the strongest previously reported results (12.16% and 22.53%, respectively), while completing every benchmark in under 120 s on a single GPU.
Facial Expression Recognition (FER) on optomyographic (OMG) smart glasses such as OCOsense enables privacy-preserving, camera-free affect sensing for health and well-being. Most FER systems are fully supervised, i.e., they rely either on hand-crafted expert features with classical machine learning, or on end-to-end deep models trained from labelled data. Both depend on large quantities of labelled expressions, which are costly to collect and limit deployment in real-world, personalized settings. We investigate Self-Supervised Learning (SSL) as a route to label-efficient FER on these glasses. We pretrain a Vision Transformer with a masked-autoencoder objective on unlabelled OCOsense recordings and finetune it for five-class FER under person-independent cross-validation. Across label budgets from 5% to 100%, pretraining consistently improves performance; with only 5% of the labels, the pretrained model outperforms the from-scratch model trained with all labels. Our results show that SSL pretraining is a practical way to reduce labelling cost for smart eyewear FER, and we discuss the implications for future personalization and continual adaptation.
LLM agent distillation transfers agentic capabilities to student models by training on complete teacher trajectories that typically interleave thoughts and actions. We question how critical thought supervision is for agents' ultimate action performance. To answer this, we disentangle their impacts by independently perturbing teacher thoughts and actions during distillation. On widely adopted agent benchmarks across model scales, altering or discarding thoughts has little effect on student performance. We find, however, that thought supervision becomes important when information about the thought is not disclosed in the corresponding action during training. By identifying such discrepant cases, our findings challenge the common practice of distilling entire teacher trajectories for LLM agents, and offer a new insight that thought supervision can be a discernible choice for efficiency depending on whether the information of thought is disclosed in the action.
Structural Causal Models and Bayesian Networks are the dominant framework for representing causal relations. They are fundamentally type-level formalisms since their estimands, Average Treatment Effects and Conditional Average Treatment Effects, are properties of distributions over populations, not of individual units. When treatment effects exhibit unbounded heterogeneity, these estimands collapse. What persists is the structural, token-level core of causation. We argue that Petri Nets under the Individual Token Philosophy are the natural representation of these token-level causal structures. We develop a formal translation from Bayesian Networks to Petri Nets, providing a two-layer account of individualized causality. The PN layer provides a structural representation of causal mechanisms that does not rest on distributional assumptions. In turn, a conformal prediction layer quantifies causal effects with finite-sample coverage guarantees. Together they constitute a complete account of individual causal effects.
Qualitative data can tell software teams what their stakeholders need, yet rigorously analyzing thousands of qualitative responses takes expert time that few teams can afford or justify. Teams therefore often face a false choice: leave the responses unanalyzed, or hand them to a large language model and accept its interpretation and judgment. In this paper, we take a pragmatic approach to AI-assisted qualitative analysis and present TACT (Traceable AI Council for Thematic analysis), a procedure that enables such analysis at scale while keeping teams in control of interpretation and judgment. TACT comes in two variants: TACT-Lite, the core AI council procedure, and TACT-Full, which adds adversaries (models from other model families that critique each model's output) and a decision model that surfaces high-uncertainty code assignments. We evaluated TACT on an independent dataset of 256 Stack Overflow threads qualitatively coded by other researchers. Against their labels, TACT's candidate codebook achieved an F1 of 0.75-0.77 and its final coding an F1 of 0.71-0.72. On a held-out sample, agreement between our own manual coding and TACT's coding was Cohen's $\kappa$ of 0.79-0.85. TACT is also economical: model calls cost \$13.77 (TACT-Lite) to \$33.59 (TACT-Full) per 100 threads. Finally, drawing on our experience building and validating TACT, we identify pitfalls in AI-assisted qualitative analysis, describe safeguards to address them, and offer guidance for teams and researchers applying TACT in practice.