Sección

Investigación

Papers y preprints de los feeds de investigación que seguimos.

6415documentos

An Analytical-Prior Framework for Data-Efficient Prediction of Sound-Reduction Frequencies in Rectangular Side-Branch Helmholtz Resonators

High-fidelity finite-element simulations can provide accurate numerical predictions for side-branch resonators, but large simulation datasets are expensive to generate and purely data-driven surrogates may become unreliable when simulation-labelled data are scarce. This study develops an analytical-prior learning framework that reuses a low-cost analytical model to improve data efficiency under limited high-fidelity simulation budgets. Two complementary routes are considered. When the analytical model remains available at inference, it is retained as an explicit baseline and the simulation data are used to learn only the analytical-to-simulation discrepancy. When a self-contained predictor is required, the analytical mapping is first distilled from abundant low-cost evaluations into a learned prior and then calibrated with the limited simulation data. The framework is evaluated on rectangular side-branch Helmholtz resonators using 86 simulation-labelled geometries and 8,998 non-overlapping analytical-only geometries. The analytical model achieved a mean absolute error (MAE) of 1.333 Hz. Direct support vector regression (SVR) achieved 3.375 Hz, while residual SVR reduced the MAE to 0.426 Hz. A direct multilayer perceptron (MLP) achieved 1.109 Hz, whereas analytical-prior pretraining reduced the error to 0.556 Hz with frozen-prior residual adaptation and 0.371 Hz with full-model fine-tuning. Across training budgets of 20 to 70 simulation-labelled cases, both analytical correction and analytical-prior pretraining consistently improved data efficiency relative to direct learning. These results show that analytical prior information can substantially improve high-fidelity prediction when simulation data are scarce, with explicit correction and prior distillation serving complementary deployment needs.

arXiv AI Papershace 3 meses

Data-Efficient and Interpretable Classification of Circulating Tumor Cell Phenotypes in Microfluidic Devices via Deep Learning

Accurate classification of circulating tumor cell (CTC) phenotypes can provide valuable information for assessing metastatic potential. Label free microfluidic devices provide a hydrodynamic obstacle course that transforms subtle biophysical characteristics of CTCs, including size and deformability, into distinct kinematic trajectories. However, the highly nonlinear fluid structure interactions governing these trajectories make the inverse problem of inferring cellular phenotype from trajectory data analytically intractable. While deep neural networks (DNNs) have emerged as a powerful approach for addressing this inverse problem, their effectiveness is constrained by the limited availability of trajectory data and the lack of physical interpretability. To address these challenges, we propose an interpretable and data efficient DNN framework for trajectory based CTC classification. To mitigate the scarcity of data, we develop Subsequence (SubSeq), a targeted augmentation strategy that randomly extracts informative local trajectory segments during training to promote learning from localized patterns. We further apply Gradient Weighted Class Activation Mapping to identify the trajectory features and physical regions of the microfluidic device that drive model predictions. Experimental results demonstrate that SubSeq improves classification accuracy over the evaluated baseline and augmentation methods. Furthermore, interpretability analysis suggests that localized trajectory segments contain substantial biophysical information relevant to accurate classification. This provides justification for SubSeq and also highlights the redundancy of full-length trajectories. More broadly, the proposed framework views microfluidic geometries as physical encoders of cellular mechanical properties, providing mechanistic insights that may inform the future design of diagnostic devices.

arXiv AI Papershace 3 meses

Towards Computational Provenance: Carrying Causal-State Evidence in Generated Text

A language model's output does not by itself provide verifiable evidence about the internal computation that produced it. We study computational provenance: whether generated text can carry detectable evidence of which causally relevant internal state occurred. We test a bounded form of this idea in two controlled architectures: a modular feed-forward neural network and a transformer-based model. Both architectures are trained on the same arithmetic task with a mandatory pathway through two discrete intermediate states, allowing different internal paths to produce the same answer. We deliberately switch between these paths, authenticate the state actually used, and let that verified state determine a subtle statistical pattern in the generated text that can later be detected. The feed-forward and transformer systems each passed all 128 matched pairs in both their public and separately sealed protected end-to-end evaluations, with the detector recovering the signal associated with the authenticated internal state. The required causal computation also reproduced across five independently trained feed-forward models and three independently trained transformers. In a separate answer-only transformer experiment, our linear probes did not recover a naturally learned intermediate state. These results provide a controlled proof of concept that information about a verified, causally relevant internal state can be preserved in generated text even when the answer is unchanged.

arXiv AI Papershace 3 meses

Non-Crossing Deep Quantile Regression for Distributional Survival Prediction

In survival analysis the way covariates act on the risk of an event often differs between early and late failure times, yet hazard- and mean-based summaries collapse this variation into a single number. Quantile-based modeling instead describes the full conditional distribution on the original time scale, but existing censored-data methods are either inflexible or produce logically inconsistent crossing quantile curves. We propose a Censored Non-crossing Quantile (CNQ) framework for right-censored data that jointly estimates several conditional survival quantiles and guarantees valid ordering by construction, with flexibility supplied by Kolmogorov-Arnold and Transformer backbones, and we establish a finite-sample excess-risk bound holding jointly across all fitted quantile levels. Across 27 simulation settings and six cohorts the framework attains lower pinball loss than quantile-, hazard- and tree-based competitors whenever the conditional distribution is asymmetric, with interval coverage closer to nominal on all six. In two clinical case studies (METABRIC, breast cancer; FLCHAIN, population mortality) it recovers covariate effects that vary across the survival distribution and would be hidden by a single hazard ratio, and yields coherent individualized quantile milestones. Code: https://github.com/BIG-S2/deepcnq

arXiv AI Papershace 3 meses

The canonical facets of multi-separator polytopes

We initiate a polyhedral study of the graph multi-separator problem proposed by Irmai et al. (2024) as an alternative to the lifted multicut problem for application to the task of image segmentation. Starting with an integer linear program (ILP) formulation and the multi-separator polytope spanned by its feasible solutions, we characterize in terms of efficiently-decidable, graph-theoretic conditions all facets induced by inequalities of the ILP. We proceed by strengthening these inequalities and describing additional facets of some multi-separator polytopes induced by the stronger inequalities. Specifically, we obtain a totally dual integral description of the multi-separator polytope for paths in the case where separation is considered for all vertex pairs. Finally, we relate the multi-separator polytope to the boolean quadric polytope, showing that facets induced by odd-cycle inequalities do not transfer generally, and to the lifted multicut polytope, showing that either polytope is a projection of a face of the other.

arXiv AI Papershace 3 meses

zLend: A Dual-Scope Cash-Flow Reconstruction Framework for On-Chain Credit Underwriting

Decentralized lending lacks a credit bureau: a borrower's capacity to repay must be inferred entirely from public on-chain activity, without income verification or a liability record. This paper presents zLend, a deployed cash-flow underwriting framework that reconstructs a wallet's daily balance history from raw token transfers and derives short-duration repayment-capacity signals from it. The reconstruction is performed twice per wallet, once restricted to a fixed stablecoin basket and once over all fungible transfers, on the premise that a wallet's total token holdings and its liquid, spendable balance are distinct quantities whose conflation misprices risk. From each series we derive liquidity coverage against a fixed loan size, cash-flow volatility and regularity, a drawdown-and-recovery statistic adapted from quantitative finance, and a recurring-counterparty detector that identifies salary-like payment cadence from transfer timing alone. The two views are then compared: a wallet with large aggregate holdings whose stablecoin reserve rarely covers the loan size is flagged as a liquidity mismatch irrespective of total wealth. We specify the pipeline formally, document the golden-master methodology used to verify a cross-language production migration to numerical tolerance 1e-9, and characterize the tier function's parameter sensitivity with an independent reimplementation validated to exact agreement (78 of 78 field assertions) against the deployed system's reference fixtures. Tier assignment is governed predominantly by the reference loan size, with four of six reference wallets changing tier across loan sizes from USD 10 to USD 25,000; the drawdown and coverage criteria bind on disjoint wallets, so neither subsumes the other; and no criterion in the tier rule is inert. zLend is deployed in production, informing real lending decisions via third-party API integrations.

arXiv AI Papershace 3 meses

What Do Compliance Detectors Read? An Audit of Activation Probes and Guard Models

Regulatory compliance monitoring in deployed language models is increasingly implemented as a legal and audit control, checking model outputs against written rules spanning data protection, healthcare, financial regulation, and platform policy. Such monitoring is meaningful only if a detector's verdict depends on the stated rule rather than on surface features of the scenario. We show this condition fails across the current class of compliance detectors, a failure we call rule blindness. Deleting, permuting, or substituting the governing rule leaves detection accuracy unchanged for every guard and activation probe we test, including a policy-conditioned guard that correctly cites the governing clause yet barely changes its verdict when that clause is swapped for its permissive counterpart. A purpose-built benchmark crossing two rules with two scenarios, so that neither alone predicts the label, confirms the failure under a design no prior benchmark rules out, and shows that step by step reasoning, not any fast detector we test, is what escapes it. Auditing at scale requires a retraining-free detector, so we introduce the Internal Compliance Score (ICS): a training-free activation readout calibrated from ten labelled pairs and scored by a single projection. We hold ICS to the same scrutiny as the guards it audits: a pre-registered criterion for beating trivial baselines is not met, and a bag-of-words model matches its pooled generalisation exactly. It remains useful because it is inexpensive, letting us audit four deployed guard models, an 8B zero-shot judge, and thirteen benchmarks, and it raises the mechanically verified pass rate when used to rank candidate responses, though an adaptive white-box attack removes this gain. We release the counterfactual protocol and crossed-rule benchmark so rule blindness can be tested in future probe and guard claims.

arXiv AI Papershace 3 meses

Proteus: Incremental Memory Activation for Long-Context Sequence Modeling

The quadratic cost of attention-based sequence models for long contexts has motivated a growing line of research on memory-based models that can compress context into a compact state. However, most existing memory models expose a static memory throughout the entire sequence. Because early tokens face no compression pressure, they occupy too many degrees of freedom and "pollute" the memory state, leaving little capacity for later context and increasing interference between what is stored and what arrives next. We study a new paradigm of incremental memory activation, where the effective capacity of memory is progressively expanded as the context grows. Imposing an early bottleneck forces the model to compress history more effectively, while unlocking fresh capacity over time reduces interference and improves retention of later context. We instantiate this paradigm in Proteus, a straightforward mechanism that can be incorporated into a broad class of neural memory architectures at no additional cost. We apply Proteus to state-of-the-art models, including SWLA, Comba, Titans, and Hope-Attention, and observe consistent improvements on standard language modeling and reasoning, as well as on long-context retrieval and understanding, with gains that grow at longer context lengths. Overall, our results show that static memory is suboptimal and that scheduling effective capacity is a simple and broadly applicable tool for sequence modeling.

arXiv AI Papershace 3 meses

HAF: Adapting Generalist VLAs to Humanoid Whole-Body Loco-manipulation via Hierarchical Action Flow and Spectral Latent RL

Humanoid robots hold great promise as general-purpose agents in human-centered environments, yet generalist vision-language-action (VLA) foundation models are not readily applicable to humanoid whole-body loco-manipulation. The high dimensionality and interdependence of humanoid motions make it challenging for conventional single-stage VLA architectures to coordinate locomotion, waist posture, and dual-arm manipulation effectively. Moreover, policies trained through offline behavior cloning can remain suboptimal during real-world deployment. Although online reinforcement learning can refine policies through real-world interaction, directly tuning large VLA backbones demands excessive computation and may introduce safety risks during real-robot exploration. To address these bottlenecks, we introduce HAF (Humanoid Adaptation Framework), a two-part framework consisting of HAF-VLA and HAF-Steer that transfers off-the-shelf generalist VLA foundation models to humanoid whole-body loco-manipulation. HAF-VLA is a hierarchical action-flow generator built on a pretrained flow-matching VLA. It splits full-body action denoising into three sequential stages with stage embeddings and cross-stage KV caches that retain kinematic dependencies, avoiding incoherent whole-body actions from one-shot generation. On top of the frozen HAF-VLA, HAF-Steer is a latent offline-to-online RL pipeline that leverages flow-matching invertibility and DCT-based dimensionality reduction to restrict RL optimization to a compact noise subspace and train a regularized SAC policy. This avoids updating the large VLA backbone and enables efficient real-world policy refinement. Evaluated on seven real-world humanoid loco-manipulation tasks, HAF surpasses vanilla single-stage VLA baselines and improves whole-body coordination and task performance. Project website: https://grange007.github.io/HAF .

arXiv AI Papershace 3 meses

Model Hypnosis: Strong control of AI via additive subliminal effects

We demonstrate that AI models are broadly susceptible to a phenomenon we call model hypnosis, in which individually weak and seemingly irrelevant cues in the prompt can be systematically combined to strongly control model behavior. Model hypnosis occurs across model families and scales, including in frontier reasoning models, and hypnotic prompts can transfer between models. Because the model is controlled by inconspicuous textual choices, such as paraphrases and typos, model hypnosis presents new challenges and avenues for AI safety, and is a major hurdle for AI interpretability.

arXiv AI Papershace 3 meses

Time-Aware Validation of Machine Learning Fuel Consumption Models: Evidence from 1\,Hz Operational Data, CCGS Sir Wilfrid Laurier

Ship fuel consumption (SFC) prediction supports vessel operation optimisation, emissions estimation, and decision support systems (DSS) for sustainable maritime transportation. Numerous data-driven fuel models have been developed over the past two decades, but a critical and often overlooked limitation lies in their validation practices: most studies evaluate performance using random train--test splits, which, applied to high-frequency records, admit temporal leakage and yield optimistic results that do not reflect deployment conditions. This paper examines that gap using time-aware evaluation, specifically Time Series Cross-Validation (TSCV) and Blocked TSCV (BTSCV). Using the Canadian Coast Guard Ship (CCGS) Sir Wilfrid Laurier as a case study, six regression models and a physics baseline are tuned under three time-aware schemes and three feature configurations, then evaluated on a common chronological hold-out set drawn from approximately 3.88 million steady-state 1\,Hz records.

arXiv AI Papershace 3 meses

Policy Iteration with Human Feedback: Bringing Post-Training RL to In-context Learning

Generative pretraining established reusable task representations; later work on language-based task conditioning and in-context learning showed that a fixed model could adapt its behavior from instructions and demonstrations. Policy Iteration with Human Feedback (PIHF) builds on this development and the recurrent evaluate-and-improve structure of generalized policy iteration. PIHF uses a pretrained language model as its execution substrate and moves persistent revision to a versioned natural-language policy and tool set. A language-model critic and clinical expert review complete-panel reasoning and tool-use trajectories to localize recurrent failures and form candidate revisions; the expert may reinterpret the evidence and retains authority over admission and rollback, while Recall@1 and Recall@5 validate outcomes after candidate execution. Across cumulative ablations and ultra-rare-disease benchmarks, a PIHF-derived policy improved Recall@1 in one proprietary executor and three open-weight executors spanning 3 to 49 billion active parameters. Gains were 32.7 percentage points for GPT-5.4 and 31.1 points for Qwen3.6-35B, a difference of 1.7 points. These results support the feasibility of using pretrained language models as fixed-weight execution substrates for expert-guided policy development in rare-disease diagnosis.

arXiv AI Papershace 3 meses

CaliBench: Are the Stochastic Dynamics of Video World Models Physically Calibrated?

Video world models approximate the stochastic distribution of physical outcomes through generative sampling, but existing benchmarks score individual generations or compare distributions coarsely over a whole dataset, leaving the fine-grained aleatoric uncertainty of specific phenomena untested. We introduce CaliBench, which scores outcomes in a physically interpretable discrete space - a bin index, a die face, a suit, a colour - rather than a learned feature space such as in FID, so the distance from a known reference distribution is measured directly. We curate outcome spaces whose reference is known in closed form (binomial Galton boards, Bernoulli forks, uniform dice/cards/lottery, a skewed European-roulette colour), enabling an exact calibration test. We decompose performance into two orthogonal axes that a single accuracy metric conflates: scorability, the fraction of generations yielding a scoreable outcome, and calibration, the total variation distance from the reference on that sample. A chi-squared test assesses significance; as calibration is its null hypothesis it can evidence only miscalibration, and at N=32 per cell detects only large deviations. We apply it to nine scenes and six image-to-video models (WAN-2.7, SeeDance-2.0, HappyHorse-1.0, Veo 3.1, Runway Gen-4.5, Cosmos3-Super), 32 generations each. Models consistently concentrate probability mass on a few outcomes rather than reproducing the reference. Most scene-model combinations are significantly miscalibrated, in the extreme collapsing to one outcome, as Veo 3.1 does on dice. On roulette, generations often leave the ball ambiguously placed, giving several models low scorability. Performance varies by scene: no model dominates all nine. We release the protocol and a metric (mean normalised total variation, mnTV) for comparing new models against our results.

arXiv AI Papershace 3 meses

GEO-Flag: Detecting and Measuring GEO-Optimized Web Content

Generative Engine Optimization (GEO) modifies web content to increase its likelihood of being selected and cited by generative search engines. This can give strategically optimized pages visibility disproportionate to their authority or relevance and even make weak or false information appear well supported. Unlike conventional search, generative search synthesizes information into direct answers rather than presenting competing sources, which can further amplify these risks, as assessing source provenance and authority requires additional user interaction. Despite these concerns, systematic methods for detecting GEO-optimized webpages remain underexplored. We introduce GEOFlagBench, a benchmark of 3,200 webpages spanning 400 queries, four domains, and eight GEO optimizer families, and use it to systematically evaluate existing GEO detection methods. Although the strongest baseline achieves an aggregate F1 of 0.880, method-level and authorship-conditioned evaluations reveal substantial weaknesses and potential reliance on authorship-related shortcuts. We therefore propose Intervention-Paired Training (IPT), which supervises detector responses to GEO interventions and non-GEO AI polishing; on ModernBERT, IPT improves F1 from 0.862 to 0.944 and worst-group accuracy from 0.725 to 0.883. We develop a GEO-gated Agent system for auditing the Source Tier and verifiability of Citation URLs in detected GEO pages. Finally, we deploy the complete pipeline on released Google Search and Gemini-grounded retrieval results for 1,000 real-user queries. Across 10,095 available pages, we estimate an overall GEO prevalence of 8.90\%, reaching 16.36\% among pages modified in 2026. Our results establish a foundation for systematically detecting, auditing, and measuring GEO in real-world search ecosystems.

arXiv AI Papershace 3 meses

Quipu: A Governed Bitemporal Knowledge Graph Store

Agents now write knowledge graphs, but knowledge-graph stores still carry defaults set when humans curated them: accept writes now and clean later, keep one time axis or none, treat every writer's facts as equally trustworthy, and leave governance to dashboards and middleware. These four defaults are individually convenient and jointly untenable under agent workloads. We present Quipu, an embeddable store that inverts all four: no fact enters except through a gate whose predicates evaluate the pending post-state; data, trust labels, verdicts, and the rules themselves are bitemporal; named graphs are the unit of authority and trust, composed under a lattice whose one invariant is that composition never widens; and the governance specification Σ, the trace, and signed verdicts are facts in the store they govern, making the audit T Σ a query. We evaluate with Census, a deterministic multi-writer lifecycle whose single seeded run scores every research question against planted ground truth: the gated store ends with 0 of 6 planted defects versus 6 of 6 ungated; all 7 composition probes uphold the lattice contract; 50 of 50 satisfied verdicts re-derive faithfully as of their instant while all 50 would be misreported under a latest-only rule set; and the SARC reference checker agrees with the in-store audit verdict-for-verdict, differing only on coverage semantics. A recorded trace from a governed writer surfaces a live enforcement gap the audit names with its remediation. On DEMM-Bench, an external decision-evidence sufficiency benchmark, a content-only reading of the exported records answers all 512 property-level governance questions correctly with zero overclaim under all eight degradation conditions, while container-presence baselines overclaim on up to 87.5% of them -- and the run surfaced, and led us to close, a gap in what a denial's verdict attests.

arXiv AI Papershace 3 meses

Unsupervised Learning of Cell Instances with Generative Routing Pyramids

Identifying and representing object instances such as cells or nuclei is a common task in microscopy image analysis. Established machine learning workflows typically use supervised detection or segmentation followed by feature extraction or classification, which requires manual annotations and treats instance segmentation and cell representation as separate stages. We describe a new unsupervised method for cell instance segmentation and phenotypic classification from unlabeled microscopy images. Our method is based on reconstructing each image using a coarse-to-fine routing pyramid that associates pixels with spatially sparse latent sources. The resulting pixel-to-latent associations yield instance masks, while the source latents encode cell morphology. We demonstrate competitive performance in instance segmentation across diverse cell morphologies and imaging modalities, as well as generative modeling of cellular phenotypes under perturbations. Source code and checkpoints are available at https://github.com/weigertlab/routing-pyramids.

arXiv AI Papershace 3 meses

When State Becomes an Attack Surface: State-Semantic Injection in LLM-Driven Embodied Agents

Large Language Models (LLMs) have demonstrated capabilities in in-context learning, task decomposition, step-by-step reasoning, and code generation, driving their gradual evolution from text generation models into the core of agents capable of perceiving environments, invoking tools, and executing tasks. Traditional LLM Agents typically obtain information through webpages, documents, databases, or external tools and generate corresponding invocation sequences according to user goals; when this technology is further integrated with robotic systems, large language models begin to undertake functions such as task understanding, high-level planning, and behavioral decision-making. SayCan combines the task reasoning capability of language models with the affordances of robotic skills, while Code as Policies and ProgPrompt generate robot task plans through policy code and programmatic prompting, respectively, and VoxPoser uses language models and vision-language models to construct three-dimensional value maps to guide robotic manipulation {6,7,8,9}. Vision-language-action models such as PaLM-E, RT-2, and GR00T N1 further strengthen the connection among language, visual perception, and robotic actions {10,11,12}. In such LLM-driven embodied agents, the model not only needs to understand user instructions, but also needs to combine scene states, object attributes, spatial relations, and execution feedback to complete task grounding, and then hand the generated action plan to skill libraries, motion planners, or controllers for execution.

arXiv AI Papershace 3 meses

Diagnosing Dense Same-Class Attribute Misbinding in Large Vision-Language Models

Large vision-language models can recognize the objects and attributes in a crowded scene yet assign an attribute to the wrong same-class instance. Generic visual-question-answering accuracy marks the response as wrong, while object-hallucination metrics may regard both the object and attribute as image-supported; neither reveals the transfer. This study formalizes this blind spot as Dense Same-Class Attribute Misbinding (DSCAM) and presents InstaBind-Lite, a controlled benchmark that makes it directly measurable. Its 524 images contain 529 curated groups of 3-6 same-class entities, 1773 boxed instances, ordered neighbors, distinguishable color-like attributes, and four complementary question levels, yielding 9580 deterministically evaluated questions. Unlike existing protocols, source-instance annotations separate unsupported generation and recognition failure from an attribute copied from another visible entity. Binding-specific metrics further quantify transfer frequency, adjacency, ordinal distance, and intervention effects. Across five open-source and two commercial/API models, the open-source systems average 19.84% Misbinding Rate and the API systems 7.55%; these errors are hidden by aggregate accuracy. Among identifiable transfers, 80.70% and 81.51%, respectively, originate from adjacent instances. Localization and instance-first interventions help selected models but are not universal remedies. InstaBind-Lite therefore turns previously undifferentiated wrong answers into source-identifiable failure categories and tests a reliability dimension that conventional benchmarks cannot determine: whether a model knows not only what is visible, but which instance owns each attribute.

arXiv AI Papershace 3 meses

Cross-Sign Language Transfer Learning Using Domain Adaptation with Multi-scale Temporal Alignment

Sign language serves as a vital means of communication for individuals with hearing impairments, yet recognition resources for the over 100 distinct sign languages are severely lacking. In response, we present our work on sign language recognition using transfer learning and the domain adaptation method TA3N, which utilizes the Temporal Relational Network (TRN) module for aligning multi-scale temporal relations. Our findings highlight the superior performance of Domain Adaptation to neural network-based transfer learning, particularly in improving recognition of American Sign Language (ASL). Our research also identifies the effectiveness of aligning shorter-term temporal features between source and target domains. In addition to using RGB, we conducted experiments using Optical Flow mode for the sign language samples, ultimately determining that RGB outperforms Optical Flow in the majority of cases. Our work aims to improve accessibility and communication for individuals who rely on sign language as their primary mode of communication.

arXiv AI Papershace 3 meses

When Agents Coordinate: Measuring Coordination in Multi-Agent AI Coding

We study how teams of AI coding agents coordinate while solving programming tasks. Current evaluations usually report whether the agents complete the task and how much the run costs, leaving the coordination inside the team largely unmeasured. We introduce an instrument to measure this coordination. Each run is represented as a temporal network in which agents and files are nodes, and messages, file writes, and file reads are timestamped directed edges with an associated cost. We apply this instrument to 1902 runs, each evaluated with a fixed test suite, across configurations that vary the team size, the team structure, and the file policy. The resulting networks show how coordination changes as teams grow and as the work changes. Direct messaging initially increases close to quadratically with the number of agents, with much of this growth coming from an early round of introductions. As the teams grow further, this increase levels off in the largest teams we study, where agents increasingly communicate through broadcast messages. The task also shapes the network that emerges. Work built around a shared specification produces dense, highly connected teams, while pipeline tasks produce sparse networks organised around local interfaces. Shared files can replace repeated 1-to-1 communication, cutting output tokens by about 42% at eight agents on message-heavy work, while adding overhead when files already carry the coordination. Naming one agent as coordinator creates no communication hub and provides no reliable improvement in success. We also observe an unprompted tendency for agents to seek out hidden grading material. We repeat the key experimental conditions in a sealed environment, replacing the hidden material with marked placeholder files. Across 244 additional runs, agents still reach for it in four fifths of runs, while the coordinator and file-channel findings reproduce.