# Research Papers — 2026-08 · bundle page 103 of 240

> Full-text markdown of papers #5101–5150 of 11995 published in 2026-08, newest first. AI-readable mirrors of the full 11995-paper 2026-08 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-08/page/103
[← Previous bundle](https://aipod.dev/papers/archive/2026-08/page/102.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-08/page/104.md)

### The Curious Case of Exploding DecPOMDPs: Containing the Fire through Policy Counting

Authors: Nazlı Nur Karabulut, Tanya Braun
Published: 2026-08-18
Categories: cs.AI
arXiv: https://arxiv.org/abs/2608.17749v2

Decentralised partially observable Markov decision processes (DecPOMDPs) provide a general framework for modelling multi-agent decision making under uncertainty. However, DecPOMDPs are known to suffer from exponential complexity in the number of agents. One way to combat this intractability in agent numbers is to look at partitions of agents that exhibit a form of symmetry among agents, allowing for a compact encoding by counting. However, a challenge arises as the policy space explodes, even though the model complexity and evaluation cost reduce to a polynomial dependence. In this paper, we redirect our focus from counting agents to counting policies, which actually enables tractability in agent numbers for so called policy-counted DecPOMDPs. Further, we present policy-counted dynamic programming using the compact representation to solve policy-counted DecPOMDPs efficiently.

---

### TINA+: Probing Residual Visual Knowledge in Unlearned Diffusion Models via Diffusion-Consistent Text-Free Inversion

Authors: Qianlong Xiang, Miao Zhang, Kun Wang, Haoyu Zhang, Junhui Hou, Liqiang Nie
Published: 2026-08-18
Categories: cs.CV
arXiv: https://arxiv.org/abs/2608.17747v1

Although text-to-image diffusion models exhibit remarkable generative power, concept erasure techniques are essential for preventing harmful content. Existing adversarial probes evaluate these methods by testing whether erased concepts can still be recovered. However, existing erasure and probe methods remain largely text-centric, focusing on whether the text-to-image mapping is severed while overlooking whether the corresponding visual knowledge remains. To investigate this question from a visual perspective, we leverage diffusion inversion to probe whether a generative trajectory can reconstruct visual instances of an erased concept. Under a null-text condition, standard inversion avoids the textual pathway but amplifies approximation errors, hindering faithful trajectory recovery. To address this challenge, we introduce TINA+, a diffusion-consistent Text-free INversion Attack equipped with optimization-based inversion. We also find that unconstrained diffusion inversion may discover spurious trajectories, even allowing a randomly initialized diffusion model to reconstruct the target concept. Such trajectories may falsely indicate residual visual knowledge. TINA+ therefore introduces Diffusion-Consistent Trajectory Regularization to suppress this failure mode. By penalizing trajectories that fall far below the expected marginal energy evolution of diffusion, TINA+ suppresses spurious inversion paths while preserving its ability to recover erased concepts. Experiments across twelve erasure methods, four concept-erasure tasks, and different model architectures demonstrate that TINA+ reliably probes residual visual knowledge through diffusion-consistent visual trajectories. These results provide stronger evidence that current methods often obscure concepts by severing text-image links rather than eliminating the underlying visual knowledge.

---

### Thinking in a Low-Resource Language: What SFT Builds, What RL Fixes, What Accuracy Cannot See

Authors: Ayoub Kirouane, Christos Petrocheilos
Published: 2026-08-18
Categories: cs.CL, cs.LG, cs.RO, stat.ML
arXiv: https://arxiv.org/abs/2608.17744v1

Take three frontier mixture-of-experts models (Alibaba, OpenAI, NVIDIA; 3.6-4.0B active parameters each) and fine-tune them to reason in a low-resource language. On accuracy benchmarks almost nothing happens, and the benchmark itself is noise at this scale: changing only the random seed moves the score by 7.7 points, more than every data and recipe effect we measured. That null is our first result. The real changes live where accuracy cannot see. Base models never think in Greek: 0 of 1,000 reasoning traces, even when the question is Greek, so the model answers correctly while reasoning in a form its user cannot read, audit, or correct. After supervised fine-tuning (SFT), every released checkpoint reasons in the language of the question on ~98% of items, one family at 3x fewer tokens, with judged grammaticality improving on all four models and general ability within a few points of each base: nothing was forgotten, and fluency was gained. We propose six behavioural dimensions that make such changes measurable, each gated to reject any metric that correlates with output length, and we report how our own instruments lied: six failures, each caught by a control. What SFT cannot do is fix its own defects: a quarter of answers skip the requested format, answers leak into the reasoning channel, and an explicit "think in English" is obeyed under half the time. Reinforcement learning with verifiable rewards, pre-registered before training, fixes the first two outright (fallback 24% to 2.5%, leak 3.5% to 0.0%, both against a flat random-reward control) and moves the third (+9.1pp), while the Greek reasoning habit survives an accuracy-only gradient untouched. We release five checkpoints. The instruments, the controls and the pre-registration travel to any low-resource language; Greek is the case that let us measure them.

---

### Neuro-symbolic learning over OWL 2 DL via consequence-based compilation to differentiable circuits

Authors: Olga Mashkova, Asaad Mohammedsaleh, Fernando Zhapa-Camacho, Robert Hoehndorf
Published: 2026-08-18
Categories: cs.AI
arXiv: https://arxiv.org/abs/2608.17741v1

OWL 2 DL ontologies, grounded in the description logic $\mathcal{SROIQ}$, express large knowledge bases in biomedicine and the Semantic Web. Neuro-symbolic (NeSy) learners over description logics either embed the ontology in a continuous space, abandoning classical entailment, or restrict to the Horn fragment $\mathcal{EL}^{++}$, which has a single canonical model. We present Baobab, which compiles a $\mathcal{SROIQ}$ ontology with a finite ABox into a Sentential Decision Diagram (SDD): it saturates a propositional core under a consequence-based calculus and instantiates the remaining $\mathcal{SROIQ}$ features (nominals, number restrictions, and the role axioms) over the active domain. The SDD's evidence-conditioned weighted model count then trains a perception network to recognize real images under partial ABox supervision: on an ontology that exercises every distinctive $\mathcal{SROIQ}$ feature, a CNN learns to read MNIST digits coupled by a successor relation and recovers latent ontology concepts that an independent perception leaves at chance. When the supervision admits several ontology-consistent completions, an independent perception collapses onto one, a reasoning shortcut: we show that a mixture indexed by the query's justifications can represent the calibrated posterior no independent perception can, and that seeding it from the circuit's enumerated completions attains the Bayes-optimal posterior on a real-image MNIST task where single-WMC and learned mixtures (the BEARS-ensemble hypothesis class) do not: to our knowledge the first to characterize and mitigate reasoning shortcuts in a non-Horn description logic. Soundness of the compiler and the representation result are machine-checked in Lean 4. Code is available at https://github.com/bio-ontology-research-group/baobab.

---

### Evaluating the Diversity of AI-Generated Content with Diversity Profiles

Authors: Xiuyuan Hu, Xuege Hou, Guoqing Liu, Yang Zhao, Jieran Li, Dongbiao Sun, José Miguel Hernández-Lobato, Hao Zhang, Xue Liu
Published: 2026-08-18
Categories: cs.AI
arXiv: https://arxiv.org/abs/2608.17731v1

Diversity is a fundamental criterion for evaluating generative artificial intelligence (AI) systems, yet its measurement remains inherently ambiguous. Existing approaches typically represent generated samples in an embedding space, compute pairwise distances or similarities, and aggregate them into a single scalar score. Such scalar summaries are convenient, but they often encode different inductive biases and may yield contradictory rankings of the same sample sets. In this paper, we argue that diversity evaluation for AI-generated content is intrinsically under-specified when reduced to a single number. We first review representative diversity metrics, and then diagnose their limitations from two complementary perspectives: an axiomatic analysis showing that no representative scalar metric satisfies all desirable properties simultaneously, and an empirical analysis showing that high-dimensional representation spaces can induce concentrated, modality-dependent distance distributions. To address these issues, we propose diversity profiles: curve-valued, condition-aware summaries that evaluate a parameterized diversity family across a range of thresholds, scales, exponents, or orders under a specified representation and distance or kernel function. Diversity profiles reveal whether a comparison is robust across resolutions or instead depends on an arbitrary parameter choice. We instantiate profiles for several representative metric families and demonstrate their practical use in generative AI evaluation. Overall, diversity profiles provide a more transparent and resolution-aware framework for comparing the diversity of AI-generated content.

---

### Evaluation of AI-based Visual Crack Detection in Steel Bridges Using Probability of Detection

Authors: Andrii Kompanets, Finn Michael Sherry, Remco Duits, Davide Leonetti, H. H. Snijder
Published: 2026-08-18
Categories: cs.CV
arXiv: https://arxiv.org/abs/2608.17726v1

Bridge structures are regularly inspected for structural damage such as cracks and corrosion in order to ensure public safety and reduce maintenance costs. Much research has been done on automating this process using computer vision methods, which are often evaluated and compared using metrics such as intersection over union, mean average precision, etc. However, predicting the actual effectiveness of an inspection method within the field of structural engineering from these metrics remains challenging. To enable the systematic use of these increasingly popular methods in engineering practice, evaluating the performance of these methods in a way that is compatible with standard engineering approaches is therefore an urgent necessity. We present a new statistical evaluation framework to allow the comparison of computer vision methods with conventional visual inspection for crack detection in steel bridges. The framework is based on probability of detection curves and can account for the influence of image resolution. We apply this evaluation method to the real-world ``Cracks in Steel Bridges'' dataset, which contains annotated images of cracks in bridge structures. The quantification of the probability of detection and its uncertainty enables a practical assessment of the effect of automated methods for damage detection in structural reliability analyses. In turn, this enables the wide-spread use of automated (AI-based) damage detection in safety critical applications. This evaluation method provides evidence that the proposed computer vision approach approach is robust for the crack detection task and can have a high added value as an addition to conventional visual inspection methods.

---

### VERaiPHY -- Validation & Evaluation for Robust AI in PHYsics

Authors: Gaia Grosso, Ramon Winterhalder, Lydia Brenner, Louis Lyons, Tilman Plehn
Published: 2026-08-18
Categories: hep-ph, astro-ph.CO, hep-ex, physics.data-an, stat.ML
arXiv: https://arxiv.org/abs/2608.17724v1

Modern machine learning is leading to substantial gains in precision, flexibility, and computational efficiency in fundamental physics. Statistical validation, uncertainty quantification, and robustness assessment are less systematically addressed. The VERaiPHY initiative (Validation & Evaluation for Robust AI in PHYsics) is a series of articles developed within the PHYSTAT programme, aimed at establishing statistical standards for the development, evaluation, and deployment of ML techniques. Each article focuses on a specific methodological domain from a statistics perspective and clarifies statistical questions, tests, and the interpretation of results. This opening article establishes the probabilistic, statistical, and machine learning foundations that the later contributions assume, together with the notation used throughout.

---

### Vision-Language Models for Analog Gauge Reading: An Empirical Study of Specialization, Transfer and Reliability

Authors: Abdul Mueez, Aaditya Baranwal, Junior Chaj-Mejia, Guneet Bhatia, Jason T. Voelker, Shruti Vyas
Published: 2026-08-18
Categories: cs.CV
arXiv: https://arxiv.org/abs/2608.17723v1

Analog gauges remain common in industrial environments where manual inspection is costly or hazardous. The engineering application addressed here is direct numerical reading of single-target analog-gauge images, while the artificial-intelligence contribution is a systematic evaluation of specialization, transfer, robustness and reliability for a general-purpose vision-language model (VLM) without an explicit pointer-segmentation and geometric-reading pipeline. The Qwen2.5-VL-7B-Instruct model is evaluated using zero-shot prompting, in-context learning (ICL) and parameter-efficient fine-tuning with Quantized Low-Rank Adaptation (QLoRA) on a public synthetic dataset, a video-derived Pressure Gauge dataset and a proprietary industrial dataset. All fine-tuning experiments use a fixed 20-epoch protocol with the final epoch used for analysis; separate models with and without supplied gauge ranges remove prompt-setting confounds. The primary metric is range-normalized mean percentage error (MPE). The best fine-tuned MPE values are 2.39% on the synthetic dataset, with a 95% bootstrap confidence interval (CI) of 1.43-3.90%; 2.61% on the Pressure Gauge dataset, with a CI of 1.66-3.80%; and 4.43% on the proprietary industrial dataset, with a CI of 2.31-7.14%. Leave-one-dataset-out experiments reveal substantial transfer degradation on held-out synthetic and proprietary data, while robustness tests identify Gaussian blur as the strongest tested corruption. Reliability analysis shows that high-confidence errors remain possible, motivating abstention and independent validation in safety-critical use. These results support QLoRA-specialized VLMs for direct single-gauge reading but not yet a deployment-ready plant-monitoring pipeline.

---

### MemCatalyst: Amplifying Data Auditing on Vision-Language Models via Data Poisoning

Authors: Xukun Luan, Jinyan Liu, Yuhui Gong, Yuanguo Bi, Bing Hu, Xuesong Li, Di Wang
Published: 2026-08-18
Categories: cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2608.17722v1

Vision-Language models (VLMs) achieve outstanding performance largely due to the amount of training data available on the internet. At the same time, data holders (e.g., artists) urgently need to determine whether their data has been used for model training without authorization, which concerns both intellectual property rights and personal privacy. Data auditing, particularly through membership inference (MI), has attracted attention as a direct tool. This work proposes MemCatalyst, a set of data poisoning tools, aiming to amplify the data auditing performance on VLMs. MemCatalyst employs two strategies: Poisoning Text (PT) and Poisoning Image (PI). MemCatalyst forces VLMs to over-learn specific inconsistencies between image features and textual semantics during training, thereby increasing their susceptibility to membership information auditing. Crucially, the transferability of poisoned samples across different VLM architectures is demonstrated to be effective in the black-box setting. Extensive evaluations using five state-of-the-art data audits on two prominent VLMs demonstrate that MemCatalyst markedly enhances MI AUC scores with a minimal budget of poisoned samples, while maintaining a negligible impact on model performance.

---

### What Aggregate Scores Miss: Measuring Item-Level Regressions in Commercial LLM API Migrations

Authors: Xiaonan Xu, Wenjing Wu
Published: 2026-08-18
Categories: cs.SE, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2608.17719v1

Context: Software systems that depend on commercial large language model APIs must migrate to successor versions when vendors deprecate older models. Migration decisions typically rely on aggregate benchmark scores, which compress heterogeneous item-level behaviour into a single net figure. Objective: We measure what that compression conceals. Method: On three pairwise upgrades in the GPT-5.4 to GPT-5.6 Sol product sequence, we query 900 public benchmark items (graduate-level knowledge, olympiad mathematics, instruction following) 50 times per item per model, classify each item as reliably improved, reliably regressed, practically equivalent, or inconclusive under false-discovery-rate control and a practical-significance threshold, and calibrate the results against a label-permutation null. Results: Across all nine migration-benchmark cells, reliable improvements and reliable regressions coexist. Edges with aggregate gains of up to 7.3 percentage points contain up to 8.3% reliably regressed items; edges with aggregate losses contain up to 10.7% reliably improved items. On the instruction-following benchmark, the gap between strict and loose scoring widens by 3.9 percentage points on the latest migration: a 3.9-point regression under strict scoring shrinks to 0.04 points under loose scoring. Conclusion: Migration decisions based on aggregate scores alone miss substantial bidirectional item-level change. The complete response-level archive and per-item scoring outputs are released.

---

### Beyond Suspicious Steps: Ontological Trust in Long-Horizon Agents

Authors: An He, Yao Wang, Haibin Zhang
Published: 2026-08-18
Categories: cs.AI
arXiv: https://arxiv.org/abs/2608.17718v1

Long-horizon agents increasingly operate across many steps, tools, and observa- tions. In this setting, the relevant oversight question is not only whether each action is locally valid, but whether the evolving trajectory still corresponds to the task the user authorized. Drift can accumulate quietly: an agent may call the right tool with plausible arguments at every step, while its prefix moves toward a broader role, an adjacent objective, or evidence the user never supplied. Existing monitors mostly check local compliance, deliver final-trace verdicts, or score generic risk; they do not directly estimate this prefix-level relation. We introduce ontological trust, a task-conditioned property of trajectory prefixes, and instantiate it as RGE, an online monitor that decomposes trust along Role, Goal, and Evidence. RGE uses LLMs only to derive structured task and step representations; trust-state updates, projec- tions, and intervention decisions are deterministic, so the output is a replayable and auditable trust trajectory rather than a single end-to-end judge verdict. We construct a cross-domain trajectory corpus from OSWorld, FinanceBench, and EICU-AC, covering benign executions, prefix-paired drift, and pseudo-consistency failures. On this corpus, RGE outperforms adapted rule-, judge-, and shield-style baselines on prefix-paired drift detection. With the two larger estimator models, it exceeds 93% Drift F1 on every benchmark while keeping benign coverage at or above 95.8%. Pseudo-consistency is harder: detection depends on whether task completion is externally visible, a structural limit we characterize empirically.

---

### Communicating Credit Risk with Large Language Models: Evaluation of Explanations from Standard and Alternative Data-Based Models

Authors: Sahab Zandi, Noah Kostesku, Christophe Mues, María Óskarsdóttir, Cristián Bravo
Published: 2026-08-18
Categories: q-fin.RM, cs.AI
arXiv: https://arxiv.org/abs/2608.17715v1

Credit decisioning is a high-stakes task in which model outputs must be accurate and explainable to support compliant decisions. Although modern credit risk models such as eXtreme Gradient Boosting (XGBoost) and Graph Neural Networks (GNNs) improve predictive performance, their explanations are often too technical for stakeholders creating communication gaps that can shape approvals, denials, and fairness judgments. We examine whether Large Language Models (LLMs) can serve as explanation layers that translate post-hoc explanation artefacts into stakeholder-appropriate risk narratives. Using Freddie Mac single-family loan-level data, we develop three pipelines: standard tabular (XGBoost + SHAP), and two with alternative data, a pure network-based (GNN + GNNExplainer), and a bimodal one (combining tabular and network data). We generate narratives with three LLM configurations: a small fine-tuned LLM (Gemma 3 4B), a large fine-tuned LLM (DeepSeek R1 70B), and a zero-shot commercial LLM (Gemini 2.5). Explanation quality is evaluated through automated checks across all pipelines and a human study of bimodal explanations comparing credit risk professionals and non-professionals on eight decision-relevant dimensions. We have three main findings. First, the pipeline accounts for higher variance in evidence-grounding scores than the language model, meaning that the binding constraint on explanation quality is the evidence representation, not the model used. Second, the explanation narratives reliably name the influential factors but are less reliable when stating the direction of influence, which may be consequential for adverse-action communication. Finally, professionals apply stricter evidentiary standards than non-professionals. We discuss implications for the governance of risk models, including deployment considerations and the value of domain-aligned LLMs in regulated credit settings.

---

### Cross-View Correspondence Is a Measurement Intervention: Two-Sided Validation for Agent Evaluation and Credit Assignment

Authors: Zhen Zhang, Ahmad Hafez, Amr Alanwar
Published: 2026-08-18
Categories: cs.LG
arXiv: https://arxiv.org/abs/2608.17713v1

Agent evaluations and trace-based learning often compare outputs across transformed views through a post-response correspondence treated as neutral preprocessing. We show that this correspondence is a measurement intervention: omitting it can manufacture sensitivity, an over-aggressive map can manufacture invariance, and multiple optimal correspondences can leave mechanism labels and signed learning credit unidentified. We develop a validity theory and audit with three components: two-sided validation of nuisance removal and response preservation, all-optima identification of downstream conclusions, and uncertainty propagation after validity is established. We characterize the linear feasibility boundary for response-preserving nuisance removal, compute sharp ranges over exact-optimum correspondence sets, and give a distribution-free certificate that retains a credit coordinate only when all exact optima agree on its nonzero sign. Across public code and SQL pipelines, two deterministic optimal tracebacks disagree on temporal localization for 55.9% of 1,586 nonzero trajectory pairs; two frozen 800-rollout tool-use audits, including a task-and-seed-disjoint replication, expose exact-optimum reversals of intended turn-level credit, although a clean public quick-start subset shows none. A pre-registered transport gate failed on natural responses; frozen corrected and held-out controls then show that a map calibrated only on benign examples erases every retained harmful response, while two-sided validation selects response-preserving alternatives. Cross-view correspondence must therefore be declared, validated, and propagated into uncertainty before agent evaluation or credit assignment supports a point conclusion.

---

### Accuracy and Robustness of Model Cascades Under Data Perturbations

Authors: Pallavi Mitra, Jai Kushwaha, Felix Biessmann
Published: 2026-08-18
Categories: cs.AI
arXiv: https://arxiv.org/abs/2608.17711v2

Prediction cascades significantly reduce energy consumption of Artificial Intelligence (AI) models while maintaining high predictive performance. The idea is that easy inputs are routed through a lightweight small model, and difficult uncertain cases are deferred to a larger model. While this design can improve computational efficiency on clean data, its effectiveness depends on the reliability of confidence-based routing. Input degradations, such as static corruptions and sequential perturbations, can shift model confidence and routing decisions. In this paper, we study confidence-based cascade frameworks for image classification and investigate how such degradations affect their confidence-based deferral behavior. We select a model cascade at the pareto-optimum of accuracy, routing quality, and energy consumption that achieves competitive predictive performance with an up to 10-fold decrease in CO$_2$ emissions. We study the behavior of that model cascade under input corruptions and analyze how the cascade's routing decisions change when the input distribution shifts. Our analysis identifies three failure modes. Static corruptions either (1) break the routing signal while the large model remains useful, or (2) degrade both models so deferral no longer recovers accuracy. Sequential perturbations reveal a third mode: predictions stabilize but deferral suppresses, yielding stable but unreliable predictions. These findings demonstrate that energy efficient model cascades require evaluation beyond clean accuracy, with explicit attention to routing reliability under distribution shift.

---

### DynaForcing: Overcoming Dynamic Collapse in Self-Forcing Distillation for Streaming Avatar Generation

Authors: Yubo Huang, Sirui Zhao, Xinchen Yao, Zhengye Zhang, Jinyang Huang, Fengqi Cui, Shiwei Wu, Enhong Chen
Published: 2026-08-18
Categories: cs.CV, cs.MM
arXiv: https://arxiv.org/abs/2608.17707v1

Audio-driven avatar generation requires realistic lip-sync, expressive motion, and real-time streaming. Recent work achieves the latter via self-forcing with Distribution Matching Distillation (DMD), but this paradigm suffers from a critical failure that has not been systematically characterized: dynamic collapse, where the student model converges to a near-static optimum with high perceptual quality but severely suppressed temporal dynamics. We trace this to two causes: the reverse KL objective in DMD, which biases toward low-motion modes, and unanchored self-conditioning, which creates a feedback loop that amplifies collapse. This is especially harmful for avatars, where even subtle motion loss breaks lip-sync and expression. To address this, we propose DynaForcing, a training framework with three complementary strategies applied at different levels. Specifically, Hybrid Forcing anchors rollouts to ground-truth dynamics at the data level to break the feedback loop. Dynamics-Aware Reward Regularization introduces explicit motion rewards via the RL interpretation of DMD to counteract the reverse KL bias at the loss level. Reference Perturbation perturbs reference images to decouple identity from static details, forcing the model to rely on audio for motion at the conditioning level. We further introduce computation graph pruning and gradient replay, reducing the GPU footprint of self-forcing by over an order of magnitude. Experiments show that DynaForcing recovers dynamics to teacher-comparable levels (Dyn-Deg: 0.31 -> 0.73, Sync-C: 7.03 -> 7.68) while improving visual quality, resolving the quality-dynamics trade-off throughout training without early stopping.

---

### Monitoring Pasture Restoration from Satellite Image Time Series: Caveats and Opportunities

Authors: Linnea Sartorius, Isak Randahl, Delia Fano Yela, Georg Andersson, Sadegh Jamali, Aleksis Pirinen
Published: 2026-08-18
Categories: cs.CV
arXiv: https://arxiv.org/abs/2608.17704v1

Monitoring nature restoration at scale is an important but difficult ecological problem. Deep learning methods to analyze satellite image time series (SITS) have been widely used for land surface monitoring. In semi-natural grasslands - the habitat type in focus in this work - restoration outcomes develop gradually, yet satellite observations are influenced by weather, acquisition conditions, and processing artefacts, making it difficult to distinguish genuine restoration signals from unrelated temporal variation. In this work, we examine - to the best of our knowledge, for the first time - whether restoration status can be detected directly from satellite image time series by formulating pasture restoration as a binary deep learning classification problem. We evaluate two common SITS deep learning architectures on different Sentinel-2 image combinations, across 1,397 restored Swedish pastures and find that explicitly modeling intra-year variability and per-pasture normalization increases separability, reaching 0.88 accuracy for the best model. We further investigate our results and perform a targeted bias analysis finding that reliable deployment requires temporally balanced labels and evaluation protocols that explicitly test for year-related confounding. We therefore frame our contribution not as a solved restoration-monitoring system, but as a realistic case study of what works, what fails, and what future studies should control for. Code and models are available at https://github.com/aleksispi/ml-nature-resto.

---

### Dijkstra as an Oracle for Online Stochastic Shortest Path Navigation with Provable Guarantees

Authors: Mansur M. Arief, Ali Akarma, Ahmad Alfan Alfian Irfan
Published: 2026-08-18
Categories: cs.RO, cs.AI, math.OC
arXiv: https://arxiv.org/abs/2608.17703v1

Mobile robots that operate in side by side with humans and critical facilities must reach their goals at low cost, despite often unknown true traversal costs of the map apriori and imperfect actuation. Planners that solve the underlying stochastic shortest path problem exactly, such as value iteration, require computation that grows with the diameter of the map, whereas Dijkstra's algorithm is fast but is usually considered inexact once transitions are stochastic. This study shows that Dijkstra's algorithm can remain an exact planning engine under a condition that is much weaker than the causality condition often invoked in the literature, namely nonnegativity of a reduced cost defined on the determinized map. Building on this characterization, an online learner DORA (Dijkstra Oracle Reduced-cost Algorithm) is proposed for robot navigation that calls a shortest path oracle a fixed number of times per episode, never estimates a transition kernel, and adds a logarithmic survival weight when the probability of contact with a dynamic obstacle must stay within a budget. In the numerical experiments involving three other benchmarks that cover grid world navigation, directional drilling, and drone surveillance, the learner matches optimistic value iteration that is given the true transition kernel while performing 4.5 to 19.3 times less planner work, reduces contacts during learning by a factor of seventeen relative to determinize and replan, and keeps the contact rate within budgets that span two orders of magnitude. These results indicate that shortest path search supports safe and efficient online navigation and path planning tasks.

---

### Environment-Invariant Subspace Learning for Generalizable Deepfake Detection

Authors: Shenghao Chen, Hao Jia, Chen Li, Chunjie Ma, Zan Gao, Shengyong Chen
Published: 2026-08-18
Categories: cs.CV
arXiv: https://arxiv.org/abs/2608.17700v1

Cross-distribution generalization remains a critical bottleneck in deepfake detection. While recent efforts leverage the semantic priors of large-scale visual foundation models (VFMs), a noteworthy yet underexplored challenge remains: the susceptibility of these semantic priors to environmental interference from factors such as lighting and style. Crucially, this interference establishes spurious correlations between forgery cues and environmental patterns that severely limit generalization. To address this fundamental challenge, we propose an innovative Environment-Invariant Subspace Learning (EISL) framework. The core contribution of EISL is that it aims to disentangle features into orthogonal forgery-relevant invariant factors and environment-related residual factors via a learnable low-rank projection. To facilitate robust feature disentanglement, we also design an Environmental Intervention module that generates diverse and challenging intervention pairs, simulating out-of-distribution environmental shifts to guide the model toward discovering truly invariant forgery representations. Experiments across cross-dataset, cross-generator, whole-face synthesis, and corruption settings show consistent gains and competitive or leading performance against strong detectors, demonstrating improved robustness to unseen forgery types and environmental variations. This work provides a new perspective and a valuable exploration for understanding and tackling the generalization barriers of VFMs in deepfake detection.

---

### Magnitude-Direction Decoupling for Fast Video Generation with Flow Matching Models

Authors: Haonan Xu, Feiyang Chen, Songkui Chen, Hongpeng Pan, Zhefeng Wang, Xinyu Duan, Baoxing Huai, Yang Yang
Published: 2026-08-18
Categories: cs.CV
arXiv: https://arxiv.org/abs/2608.17695v1

Flow matching models for video generation achieve impressive performance but suffer from high computational overhead due to iterative denoising. In fact, the original model is not necessary for all denoising steps, allowing some steps to use lightweight alternatives for faster sampling. However, directly using caching or lightweight models can deviate from the original denoising trajectory, resulting in suboptimal performance. Through empirical analysis, we find that lightweight models can robustly capture the magnitude components of the original model's output, while caching provides reliable directional guidance. Building on this insight, we propose the Magnitude-Direction Decoupling (MDD) method, which adaptively employs a direction-calibrated lightweight model as a substitute for the original model to accelerate inference and effectively correct deviations in the denoising trajectory. Moreover, MDD further reduces inference costs by reusing magnitude information under classifier-free guidance (CFG). As a result, MDD offers a more reliable and lightweight solution to accelerate sampling. Experiments show that MDD outperforms existing acceleration methods, delivering promising speedups (e.g., up to 2.95x on Wan2.1) while preserving high visual fidelity and content richness.

---

### GADR: Gathering Architecture Decision Records from Meeting Transcriptions

Authors: Lucas Daniel Costa da Silva, Kiev Gama
Published: 2026-08-18
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2608.17694v1

Existing LLM-based approaches to Architecture Decision Record (ADR) generation share a critical and largely unexamined assumption: that input is already reasonably structured. In practice, architectural decisions emerge from informal, noisy meetings where choices are implicit, fragmented, and entangled with off-topic dialogue, precisely the conditions under which single-pass prompting degrades. This paper presents GADR, a multi-agent, self-correcting workflow that extracts architectural decisions from raw meeting transcriptions and generates Nygard-formatted ADR drafts. A feasibility study comprising five real project meeting transcripts, expert review by four senior architects, and evaluation by fifteen students provides initial evidence that the agentic workflow captures most expert-identified decisions and produces drafts participants found clear and useful, outperforming zero-shot and few-shot baselines in stability and structural adherence. The study also addresses the underexplored trade-off of RAG-based enrichment improving ADR depth while simultaneously risking transcript-unfaithful content, raising open questions about traceability in automated architectural documentation that we believe is worth the community's attention.

---

### Mixture-of-Expert Blocks Contain Strong Hallucination Detection Signals

Authors: Joao Fonseca, Rodrigo Rodrigues, Paolo Romano
Published: 2026-08-18
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2608.17687v1

Despite their widespread use, Large Language Models (LLMs) remain limited by a fundamental problem: the generation of plausible but false content, known as hallucinations. Most existing detection methods operate at the answer or sentence level, yet per-token detection is essential for localizing hallucinated spans and enabling fine-grained interventions. In this paper, we explore the use of the Mixture-of-Experts (MoE) paradigm to address this gap. In MoE architectures, a single forward pass activates a sparse subset of experts (i.e., distinct feedforward networks per layer) via a routing mechanism, producing internal signals (e.g., router entropy, expert disagreement, and expert usage patterns) that are unavailable in dense architectures and have not been previously exploited for hallucination detection. To this end, we introduce InnerExpert, the first method to leverage these MoE-specific signals for per-token hallucination detection. InnerExpert combines routing-level and standard transformer signals into compact per-token feature vectors, classified by a lightweight detector trained on labels produced by an LLM-as-a-judge pipeline, which enables continuous model updates without manual annotation. Our results show that InnerExpert outperforms existing methods across five datasets and two MoE architectures, achieving up to 0.91 answer-level and 0.76 token-level AUROC, while requiring only a single forward pass.

---

### Auditing Self-Evolution in Financial Agents: Capability Gains, Security Drift, and Execution-Interface Mismatch

Authors: Jialong Li, Jialing Zhu
Published: 2026-08-18
Categories: cs.AI
arXiv: https://arxiv.org/abs/2608.17684v1

Self-evolving agents turn experience into reusable skills, workflows, or memories, but post-evolution accuracy alone does not show whether learned behavior preserves previously correct behavior or security. We audit SkillOpt, Agent Workflow Memory (AWM), and ReasoningBank in simulated e-banking using matched benign acquisition trajectories, sealed evaluation endpoints, execution-grounded checks, and independent state replay. On Qwen 3.7 Flash, SkillOpt raises benign utility from 0.741 to 0.837 while exposure to injected content rises from 0.820 to 0.943. Conditional attack success after exposure falls from 0.605 to 0.562, yet overall attack success rate (ASR) rises from 0.496 to 0.530 and unauthorized financial state changes rise to 0.685. Across three independently evolved lineages, capability, exposure, and unauthorized-state changes increase in all three, whereas ASR increases in only two. ReasoningBank raises utility to 0.859 without increasing aggregate ASR, although unauthorized state changes remain slightly above Static. AWM reveals a separate evaluation hazard: a literal WebArena text-action envelope disrupts tool execution in our native function-calling executor. In a post-hoc sensitivity test, removing only that envelope restores utility from 0.319 to 0.756, while exposure rises from 0.299 to 0.909 and ASR from 0.195 to 0.575. Auditing self-evolving financial agents therefore requires tracking regressions, attack-surface contact, unauthorized financial-state change, and artifact-executor compatibility, not accuracy alone.

---

### Differentiable Voronoi Ray Tracing Beyond Rasterization Speeds

Authors: Bernardo Taveira, Carl Lindström, Joakim Johnander, Fredrik Kahl
Published: 2026-08-18
Categories: cs.CV
arXiv: https://arxiv.org/abs/2608.17682v1

Real-time novel view synthesis is dominated by rasterized explicit primitives. These projection-based pipelines provide high throughput but require specialized extensions for non-pinhole effects such as distortion, rolling shutter, and depth of field. Ray-based rendering expresses these effects naturally but is generally assumed too slow for competitive real-time rendering. We analyze the factors governing throughput in differentiable Voronoi ray tracing and identify traversal length, per-cell work, and memory locality as principal determinants. Guided by this, we introduce VoroTracing, which co-designs the scene representation, optimization, and GPU execution to reduce these costs. Compact octahedral appearance textures reduce memory traffic, while surface-concentrated opacity promotes early termination. The fixed-budget representation is optimized without pruning or densification and rendered with a GPU implementation designed for coherent traversal. On Mip-NeRF 360, VoroTracing renders at 623 FPS on an RTX 5090, providing $3.2\times$ the throughput of the fastest prior ray-based method and $2.8\times$ that of 3D Gaussian Splatting, while maintaining competitive reconstruction quality. Our renderer supports fisheye, rolling-shutter, motion-blur, and depth-of-field effects through ray generation and sampling, requiring no specialized rasterization. These results show that real-time throughput can be achieved with the flexibility of ray-based rendering. We release our source code, see https://research.zenseact.com/publications/vorotracing

---

### Conformal Prediction for Molecular Properties under Label Shift

Authors: Hyeonsu Lee, Juyeon Kim, Erkhembayar Jadamba, Seungjin Choi, Hyunjin Shin
Published: 2026-08-18
Categories: cs.LG
arXiv: https://arxiv.org/abs/2608.17678v1

Drug discovery and development underpins healthcare but remains costly and failure-prone. A critical bottleneck lies in predicting molecular properties such as solubility, potency, and toxicity, which directly determine whether a candidate can advance from preclinical to clinical trials. Artificial Intelligence (AI) has accelerated this process, yet its reliability is often undermined by distribution shift, as experimental conditions frequently diverge from training data. In addition, conventional point predictions provide only single-value estimates, offering limited guidance for high-stakes experimental design. We address these challenges with a conformal prediction framework tailored to label shift. By weighting conformal scores using marginal label probability ratios, our method produces statistically rigorous prediction intervals without retraining. This enables robust uncertainty quantification even when property distributions drift, directly tackling one of the most pervasive obstacles to applying AI in real-world drug development. By moving beyond accuracy alone to provide actionable confidence measures, our approach enhances the trustworthiness of AI-driven predictions. This further aligns predictive modeling with regulatory demands for transparency and uncertainty reporting and ultimately supports more reliable decision-making in billion-dollar development pipelines.

---

### Benchmarking Automated Security Patch Backporting: How Far Are We?

Authors: Jincheng Yang, Yulong Fu, Chengwei Liu, Lyuye Zhang, Fangyuan Zhang, Bingyang Ren, Yang Liu, Hui Li
Published: 2026-08-18
Categories: cs.SE, cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2608.17671v1

Automated security patch backporting is critical for mitigating N-day vulnerabilities. Recent tools report success rates above 80% on their respective datasets. However, these evaluations are often confined to homogeneous environments, such as one repository or specific project versions. Consequently, it remains unclear how well these tools generalize beyond their originally targeted scenarios. We present Porting Benchmark, a curated dataset of 1,234 security patch backporting cases spanning cross-version, cross-branch, and cross-repository scenarios, paired with a common evaluation framework. Using this benchmark, we evaluate five tools spanning program analysis, LLM prompting, and LLM agents under aligned settings. Our results show that aligned evaluation changes the apparent performance landscape: PortGPT and TSBPort remain comparatively strong on the Replication Dataset, while FixMorph and Mystique degrade substantially under the common protocol. Performance degrades sharply on structurally complex patches: the best commit-level success rate falls from 85.2% on Type-I patches to 24.0% on Type-IV. We identify four root-cause categories (missing target API awareness, cross-version semantic mismatch, non-local dependency propagation failure, and patch construction or localization failure) and derive concrete directions for next-generation tool design. On a 45-case dynamically validated subset with verified test cases and constructed POCs, we further observe that reference-based benchmark scores do not fully capture real-world remediation: exact match sharply under-credits harder target adaptations, while executable validation reveals residual integration failures in the target that static reference agreement misses. Executable-feedback refinement provides limited but measurable recovery on the hardest executable cases.

---

### Picard Proximal Monte Carlo for Parallel Bayesian Imaging with Score-Based Generative Priors

Authors: Deliang Wei, Evan Bell, Wenhan Guo, Yifan Chen, Yu Sun
Published: 2026-08-18
Categories: cs.LG
arXiv: https://arxiv.org/abs/2608.17666v1

Bayesian imaging inverse problems often require sampling from high-dimensional posterior distributions. While recent score-based and diffusion models provide expressive Bayesian priors, their sampling procedures remain inherently sequential and computationally expensive for large-scale imaging applications. We propose PiX-MC, a time-parallel posterior sampling framework based on proximal Langevin dynamics and Picard iteration. The proximal-likelihood formulation exploits the fact that many imaging likelihoods admit efficient, problem-specific proximal operators, while Picard refinement exposes parallelism across discretization nodes and naturally supports multi-GPU implementation. To further improve practical scalability and sampling performance, we develop multi-block and annealed variants of the proposed framework. We establish convergence guarantees under transparent assumptions, accommodating non-log-concave posteriors, imperfect learned score models, multi-block implementations, and annealing schedules. Experiments on a diverse collection of imaging inverse problems demonstrate that PiX-MC substantially reduces wall-clock time while preserving reconstruction quality. On a $512\times512\times80$ sparse-view computed tomography (CT) problem, annealed multi-block PiX-MC achieves up to a $50\times$ runtime speedup over the standard Langevin sampler using eight GPUs.

---

### GraphWake: Group Polarization via Memory-Mediated Polarization Cascade in LLM-Agent Communities

Authors: Haoran Bu, Zejian Chen, Litian Zhang, Xi Zhang
Published: 2026-08-18
Categories: cs.AI
arXiv: https://arxiv.org/abs/2608.17665v1

LLM-driven agents can autonomously exchange opinions on online platforms and form communities. Such agent-operated social platforms raise a new security concern: attackers may manipulate agents to induce group polarization. Existing methods manipulate agent prompts or construct echo chambers, both of which are difficult to realize in practice. We therefore formulate a new threat, Memory-Mediated Polarization Cascade, which uses agent memory as a persistence channel and public discussion as a propagation channel. This threat contains three stages. During exposure and memory retention, the attacker exposes a small set of target agents to arguments that reinforce their respective stated stances. The targets' memory systems then process and retain these arguments. During retrieval and reproduction, a shared stance-neutral discussion cues the targets to retrieve and reproduce their respective retained arguments. During iterative propagation, untreated agents influenced by the reproduced arguments restate and spread them. We instantiate this threat in GraphWake with three components: (i) stance-support argumentation knowledge graphs construct knowledge-based arguments; (ii) axiom-oriented triple selection distills them for reliable retention and reproduction; and (iii) stance-neutral memory cueing triggers concurrent retrieval and reproduction, initiating propagation. Experiments across multiple discussions and memory systems show that GraphWake substantially increases group polarization. These findings reveal a community-level polarization risk.

---

### Is Haar Enough? Exploring Symlets and Coiflets for Wavelet Convolution Layers

Authors: Md Rifat Ur Rahman
Published: 2026-08-18
Categories: cs.CV
arXiv: https://arxiv.org/abs/2608.17662v1

Wavelet convolution layers have recently emerged as an efficient mechanism for enlarging receptive fields through multiresolution analysis, but prior work has fixed the wavelet basis to Haar or Daubechies at a chosen decomposition depth, leaving open whether a different basis can shift the underlying efficiency frontier. We identify and characterize a previously unexplored trade-off in this setting: bases with stronger approximation properties (longer filters) can reduce the decomposition depth required for competitive accuracy, yielding a net reduction in parameters and FLOPs despite higher perlevel transform cost. We formalize this as an F-vs.-L tradeoff (filter length vs. decomposition levels) and study it systematically across Haar, Daubechies, Symlets, and Coiflets under controlled architectures and budgets. On image classification (CIFAR-10, ImageNet-1K) and semantic segmentation (Cityscapes), Coiflet-based wavelet convolutions match Haar at deeper levels with approximately 32% fewer additional parameters and 33% fewer additional FLOPs, providing a concrete and actionable design choice for practitioners building wavelet-based architectures.

---

### MobileWorldSafety: Benchmarking GUI Agent Safety Against Environmental Injection Attacks in Android Apps

Authors: Sujin Chen, Lijun Li, Tianyi Du, Jing Shao
Published: 2026-08-18
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2608.17659v1

LLM-powered GUI agents that autonomously operate smartphones are rapidly transitioning from research prototypes to early real-world deployment. However, because these agents routinely process untrusted environmental content, they are highly vulnerable to environmental injection attacks, which include indirect prompt injections and adversarial instructions. Such attacks can manipulate the behavior of agents without user awareness through diverse channels encountered in everyday mobile use. Despite these risks, existing benchmarks often fail to capture everyday user scenarios, lacking a systematic evaluation of GUI agents under environmental injection attacks on mobile devices. To address this gap, we introduce MobileWorldSafety, a benchmark of 142 risk tasks built on real Android applications. For each task, we define a programmatically verifiable risk indicator over the final system state and evaluate outcomes with a two-stage pipeline: rule-based verification handles unambiguous cases, while an LLM judge adjudicates ambiguous ones. This distinguishes safety failures from capability failures and enables objective and reproducible assessment. Evaluations on six agents, including both general agents and specialized GUI agents, demonstrate that all agents remain highly vulnerable, with attack success rates ranging from 40.4% to 66.9%. These findings indicate that current agents often fail to maintain safety alignment when adversarial content is presented as ordinary mobile context. MobileWorldSafety provides a foundation for quantifying these vulnerabilities and advancing research on robust mobile GUI agents.

---

### Denoised Variance-Based Pruning with Optimal Brain Bias Compensation

Authors: Geon Tack Lee, Jaegul Choo, Kang Eun Jeon
Published: 2026-08-18
Categories: cs.CV
arXiv: https://arxiv.org/abs/2608.17657v1

Vision Transformers (ViTs) achieve state-of-the-art performance but carry massive computational overhead that restricts edge deployment. Although structural pruning has emerged as a key strategy to reduce these costs, existing methods often suffer from severe accuracy degradation or require expensive retraining. Recently, Variance-Based Pruning (VBP) introduced a promising paradigm by selecting neurons based on activation variance; however, it remains limited by statistical noise in finite-sample activation covariance and reliance on bias-only updates that cannot fully account for structural reconstruction error. To address these limitations, we introduce Denoised Variance-Based Pruning with Optimal Brain Bias Compensation (DVBP + OB$^2$C). We leverage random matrix theory to filter noise from the activation covariance spectrum for robust neuron selection and mathematically prove that integrating mean-shift compensation into the Optimal Brain Compression objective reduces the layer-wise Hessian exactly to the activation covariance matrix. This enables an optimal, closed-form update of the remaining weights using the same statistics gathered for selection. Extensive experiments on DeiT, Swin, and ConvNeXt architectures demonstrate that DVBP + OB$^2$C achieves state-of-the-art training-free performance; at 50% MLP pruning, it retains over 90% of the original Top-1 accuracy on Small and Base variants, outperforming VBP by up to 29.46% (ConvNeXt-T) and 7.33% (Swin-S). The code is available at: https://github.com/geontackee/DVBP_OB2C.

---

### Elimination Geometry

Authors: Mian Huang, Xueqin Wang
Published: 2026-08-18
Categories: cs.LG
arXiv: https://arxiv.org/abs/2608.17646v2

This monograph develops elimination geometry (EG), a typed, native-loss, audit-oriented framework for studying when locally optimal objects can be realized by a shared deployment rule. Elimination and compression may erase distinctions required by prediction, inference, control, or representation. EG asks which distinctions are lost, whether the induced defect is visible to the declared task, and whether changing information, architecture, action space, or deployment domain can repair it. EG separates local solvability, global realizability, and finite-sample certifiability. It derives native defects from the original objective and distinguishes architecture obstruction from model approximation, generalization, and implementation error. The monograph synthesizes tools from geometry, optimization, information theory, statistics, and machine learning into interfaces for integrability, representation admissibility, resource constraints, observational overlap, and common deployment. Formal results address regular, coordination, singular, compositional, and resource-limited mechanisms with explicit antecedents and claim boundaries. Applications include sparse model selection, distribution-free prediction, observational treatment policies, routed expert and retrieval systems, and learned score fields. Obstruction-Aware Learning and Inference links structural diagnosis to finite-data authorization, mechanism-matched intervention, and independent validation. Reproducible synthetic and real-data studies illustrate how certificates can guide architecture repair while recording failed gates and unresolved cases. The framework requires the deployment contract, native endpoint, competing explanations, information and compute budgets, and validation rule to be fixed before a persistent performance floor is attributed to architecture.

---

### LLM-Derived Preference Judgments Are Not Self-Consistent

Authors: Matthew T. Ford, Francis Bahk, Jingjing Wang, Adam S. Jovine, Tinghan Ye, David B. Shmoys, Peter I. Frazier
Published: 2026-08-18
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2608.17644v1

Agents increasingly interpret a person's natural-language preferences by querying an LLM for numerical preference judgments, e.g., by asking how much the person would be willing to pay for an item. A growing body of work estimates a utility function from these judgments and then chooses actions based on their estimated utility. This pipeline assumes the judgments are approximately self-consistent: that a single utility function can reproduce them. But are they? To study this question, we measure the self-consistency of cardinal LLM preference judgments. For example, the difference in stated willingness-to-pay between two items should match the stated payment that makes a person indifferent to exchanging them. We develop statistical tests and interpretable measures of how far observed responses depart from the best-fitting self-consistent utility function. Experiments with flight, apartment, and hotel examples across six LLMs reveal large persistent inconsistencies. This suggests that LLM-derived preference judgments cannot be faithfully summarized by a single utility function.

---

### rl-triton: High-Performance Triton GPU Kernels for Reinforcement Learning Credit Assignment

Authors: Lars Simon Zehnder
Published: 2026-08-18
Categories: cs.LG, cs.DC, cs.PF
arXiv: https://arxiv.org/abs/2608.17641v2

We present rl-triton, an open-source library of high-performance GPU kernels for reinforcement learning credit assignment, implemented in Triton. The core contribution is a unified associative scan framework that recasts seven distinct RL estimation algorithms - Generalized Advantage Estimation (GAE), V-Trace, Retrace($λ$), TD($λ$) returns, discounted returns, eligibility traces, and episodic prefix sums - as instances of a single first-order linear recurrence solved in $O(\log T)$ parallel steps. All algorithms share the same associative scan operator, with algorithm-specific fused Triton kernels constructing their recurrence coefficients on-chip. We verify the associative operator algebraically and define the treatment of terminated and truncated episodes explicitly. Benchmarks show a 1.6-5.70$\times$ full-call speedup over a vectorized torch-compile baseline in the massively parallel simulation regime (thousands of environments, short rollouts). The reported range covers all seven algorithms on both GPUs, both with and without per-step truncation handling. For most algorithms, speedups increase at longer sequence lengths, as the baseline requires more scan stages as $\log T$ grows, each adding an intermediate HBM round-trip. The library is available at https://github.com/simonsays1980/rl-triton.

---

### Beyond the Trace: Coupling an Interpretable Reasoning-State Readout to Native MoE Routing

Authors: Kang Chen, Sihan Zhao, Yixin Cao, Yu-Gang Jiang
Published: 2026-08-18
Categories: cs.AI
arXiv: https://arxiv.org/abs/2608.17638v2

What a reasoning model writes is only a partial record of the process that produces it. We introduce a two-level internal readout for mixture-of-experts reasoning. We first distill vocabulary-scale J-space into J64, a 64-axis semantic frame learned from the model's own reasoning states. J64 reveals readable process state that the emitted trace does not show: it separates inference effort from problem-induced strain. It also adds 0.096 to 0.135 held-out AUC over a baseline that reads the same rollout as token occupancy and aggregates it in exactly the same way. We then reconstruct J64 from native expert-routing statistics. The result is R64, a low-overhead proxy: its median per-axis correlation with J64 is 0.69 to 0.86 across three models and two families, and on gpt-oss-20b it preserves 95 to 100% of J64's predictive gain. The readout supports test-time decisions at two temporal resolutions. Over completed candidate sets, J64 and R64 improve single-branch selection, and R64-weighted voting improves plain majority voting in seven of eight settings. During generation, rolling readout windows drive a cumulative stop-and-resample policy whose operating point is fixed on training questions alone. J64 improves accuracy by 1.1 to 5.9 points over a sibling-permuted control, and the routing-only R64 proxy retains 0.9 to 3.2 of those points. Finally, router edits aimed at the mechanism J64 names induce the predicted reasoning behaviors and shift a diagnosed stall from numerical guessing toward exact symbolic execution. Together, J64 makes latent process state readable, while routing makes it deployable and actionable.

---

### MaLViL: Multi-axis Low-rank Vision-LSTM for Medical Image Segmentation

Authors: Afshin Bozorgpour, Sina Ghorbani Kolahi, Moein Heidari, Ilker Hacihaliloglu, Dorit Merhof
Published: 2026-08-18
Categories: cs.CV
arXiv: https://arxiv.org/abs/2608.17635v1

Vision-LSTM (ViL) enables efficient global modeling, but its cost still scales with the number of spatial tokens, so existing segmenters confine ViL to a coarse bottleneck and lose fine anatomical detail. Rasterizing 2D features into a 1D sequence further breaks adjacency across the orthogonal scan axis. We propose MaLViL, a Multi-axis Low-rank Vision-LSTM network that extends ViL across decoder resolutions. Bidirectional low-rank ViL (Bi-LRViL) reasons on a compact orthonormal subspace and preserves detail through an orthogonal residual; scale-aware SaLViL restores cross-axis neighbors before serialization; and a Cross-Directional Mixer (CDM) fuses orthogonal horizontal and vertical traversal paths. Statistics-Guided Skip Modulation (SGSM) further retains boundary cues in encoder skips. On skin-lesion, ultrasound, and multi-organ CT benchmarks, MaLViL achieves competitive or state-of-the-art segmentation accuracy, while reducing ViL operator memory by up to $83\times$ at fine decoder resolutions. Code is available at: https://github.com/xmindflow/malvil.

---

### Graph Surgery and the Do-Operator: A Precise Correspondence for Acyclic Structural Causal Models

Authors: Satpreet Makhija
Published: 2026-08-18
Categories: cs.AI, cs.PL
arXiv: https://arxiv.org/abs/2608.17634v2

The $\operatorname{do}$-operator is described graphically by deleting arrows into its targets and functionally by replacing their mechanisms with constants. To call these operations equivalent is not yet a mathematical statement: one returns a graph and remembers only the targets, whereas the other returns mechanisms and also remembers the imposed values. We make a dependency-level comparison precise for deterministic acyclic structural causal models with finitely many endogenous variables. If $\operatorname{Graph}(F)$ extracts the dependencies of a mechanism family $F$, our main theorem is $\operatorname{Graph}(F^ι)=\operatorname{Surg}(\operatorname{Graph}(F),T_ι)$. Thus replacing target mechanisms removes exactly the dependencies removed by graph surgery. For a model $M=(G,F)$ whose graph may contain unused arrows, we characterize when the same equality holds with $G$ in place of $\operatorname{Graph}(F)$; it holds for every intervention exactly when $G$ records the dependencies of $F$ exactly. We then define the intervened model, characterize its run, show how sequential interventions combine, and prove that an outcome depends only on interventions at its actual dependency ancestors. All principal results are machine-checked in an accompanying Lean 4 development.

---

### DEPT: Document Embedding Preservation Tuning for Unified Query Expansion and Retrieval

Authors: Jingyuan Wang, Richong Zhang, Zhijie Nie, Mingxin Li, Yanzhao Zhang
Published: 2026-08-18
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2608.17632v1

Large language models (LLMs) can both expand underspecified queries and encode text as dense representations, suggesting a unified model for query expansion and retrieval. Existing systems usually rely on prompted expansions, independently trained modules, or staged optimization, leaving generated expansions only indirectly aligned with the retrieval loss that judges them. We train a single decoder-only LLM end to end, where the same model generates the expansion and encodes both the expanded query and candidate documents. This unified setting creates a moving-target problem: retrieval supervision should improve query-side expansion, but the same update also shifts the document embeddings that serve as retrieval targets. We introduce Document Embedding Preservation Tuning (DEPT), which keeps tuned document embeddings close to cached initial embeddings while allowing retrieval gradients to pass through straight-through decoding into the generator. DEPT converts joint query--document movement into query-side adaptation against approximately stable, whitened document embeddings that support index reuse and online hard-negative mining. Experiments with Qwen3-4B-Instruct-2507 and LLaMA-3.2-3B-Instruct on five datasets in BEIR benchmark show that DEPT improves average retrieval quality over training-free, independently trained, and staged unified baselines, while ablations isolate the effects of preservation, whitening, end-to-end expansion training, and online negatives. Code is available at https://github.com/ILSparkle/DEPT.

---

### Iterative Grasp Pose Refinement: A Deep Reinforcement Learning Approach for 2D Vision

Authors: Amir Arsalan Nematollahi, Shayan Ahmadi, Mehdi Tale Masouleh, Ahmad Kalhor
Published: 2026-08-18
Categories: cs.RO, cs.AI, cs.LG, eess.IV
arXiv: https://arxiv.org/abs/2608.17628v1

Developing robots capable of understanding and manipulating objects requires compact, interpretable, and generalizable representations. This work proposes a reinforcement learning-based framework for robotic grasp refinement, integrating keypoint-based object representations with a Deep Q-Network (DQN). Using 2D overhead images captured in a simulated environment, a geometric-based algorithm generates initial grasp candidates, which are iteratively refined by the proposed framework, transforming failed grasps into successful ones. Experiments conducted on 300 objects from the Dex-Net dataset using a UR5 manipulator demonstrate the framework's effectiveness, achieving a 100% success rate on objects previously deemed ungraspable by geometrical methods. The framework's sim-to-real transferability is further validated through physical experiments on a Delta parallel robot, where a refined grasp successfully manipulates an object that was previously ungraspable. The findings underscore the effectiveness of reinforcement learning in addressing challenges in robotic grasping, offering a scalable and adaptable solution for contact-rich manipulation tasks.

---

### Validated Adaptation for Aerial Crowd Monitoring at Mass Gathering Scale: A Deployment Protocol, a Severity Law, and a Diagnostic for Label-Free Drone Crowd Counting, Toward the FIFA World Cup 2034 (Saudi Arabia)

Authors: AlAnoud AllGhayth, AlJawharh AlOtaibi, Jude AlSubaie
Published: 2026-08-18
Categories: cs.AI
arXiv: https://arxiv.org/abs/2608.17625v1

Saudi Arabia will host the 2034 FIFA World Cup and already operates crowd management at Hajj scale. Drone-based counting must hold accuracy on footage unlike anything in its training corpus, without labels, and must warn of dangerous inflow before a crush forms. We deliver a validated answer built on 525 controlled runs, a full-resolution corpus study, five falsification ablations, and a five-condition safety-interlock evaluation. Label-free adaptation recovers 31-49% of shift-induced error across four corruptions and five severities, with the strongest method gaining 41.8 MAE over the frozen source (95% CI (34.1, 49.6), p=7.5x10^-10, d=2.52). We establish a severity law separating methods with a constant absolute margin from the one whose margin grows, and a stability budget identifying which configuration is safe to fly. On a full-resolution corpus carrying a genuine +48 MAE aerial gap (source retrained to 14.6 validation MAE, a 34% improvement), adaptation repairs the dense-scene undercounting that would otherwise under-report a forming crush, and the flux-based risk module fires on real congestion episodes in 2 of 6 full-length clips. We localise the recoverable error: in a regime built to favor a physics-informed conservation prior (300-frame clips at 200ms spacing, five times wider than standard), the adaptation signal is normalisation-driven, not flow-driven; the continuity residual is invariant to the proportional counting errors domain shift produces, confirmed by four on/off ablations correlated at r=0.999 and a 40% input corruption moving accuracy by only 0.05 MAE. A label-free shift gate shows shift magnitude and accuracy damage are rank-independent (Spearman rho=0.20; rho=-0.60 among genuine shifts), quantifying the 58% of headroom a magnitude gate forgoes. We establish unconditional adaptation with tail monitoring as policy, closing with a six-point protocol.

---

### RetiWave-Mamba: A Dual-Stream Network for Retinal Disease Detection based on Multi-scale Context and Frequency-Adaptive Mamba Projection

Authors: Cheng Cheng, Jin Hong
Published: 2026-08-18
Categories: cs.CV
arXiv: https://arxiv.org/abs/2608.17623v1

Retinal diseases are a leading cause of irreversible vision impairment, making early and accurate diagnosis essential for effective treatment. Optical Coherence Tomography (OCT) serves as a critical imaging modality for this purpose, yet its automated analysis is hindered by inherent speckle noise, varying lesion scales, and subtle inter-class similarities. To address these challenges, we propose a novel framework, RetiWave-Mamba, which integrates spatial-frequency domain learning with state-of-the-art state space models. The framework utilizes Discrete Wavelet Transform (DWT) to decompose OCT images into low- and high-frequency streams, enabling decoupled processing of structural context and fine-grained details. For the low-frequency branch, we design a Multi-scale Contextual Localization Module (MCLM), which synergizes multi-scale dilation with spatial attention to expand the global receptive field and precisely localize lesion regions. For the high-frequency branch, we introduce an Attention-Guided High-Resolution Network (AG-HRNet) equipped with an intelligent gating mechanism to suppress noise propagation during multi-scale interactions. Furthermore, a Frequency-Adaptive Mamba Projector (FAMP) is incorporated to capture long-range dependencies within disjoint high-frequency textural features. Extensive experiments on the OCT-C8 dataset demonstrate that our approach achieves a state-of-the-art (SOTA) classification accuracy of 98.25%, surpassing existing methods. These results highlight the efficacy of RetiWave-Mamba in robustly identifying retinal pathologies under noisy conditions, offering a promising tool for clinical diagnosis.

---

### OOD Detection for EEG-based Machine Learning in High-Risk Environments

Authors: Philipp Bomatter, Henry Gouk
Published: 2026-08-18
Categories: cs.LG
arXiv: https://arxiv.org/abs/2608.17620v1

Machine learning models for electroencephalography (EEG) analysis show great promise across a wide range of applications, but their deployment in high-risk domains is hindered by their vulnerability to distribution shifts. Encountering out-of-distribution (OOD) data can lead to catastrophic, overconfident predictive failures. While OOD detection methods can mitigate these risks, they remain heavily under-explored for EEG. Moreover, evaluations in the broader literature typically evaluate OOD detection performance in isolation, ignoring their practical impact on downstream applications. To bridge this gap, we introduce a benchmark for EEG OOD detection, evaluate a broad range of methods, and furthermore evaluate their value in two clinical downstream prediction task. Our results disentangle OOD detection and model uncertainty estimation capabilities, which are frequently conflated in the literature, provide actionable insights about the current state of the art for EEG OOD detection and model uncertainty estimation, and demonstrate how complementary methods for both aspects can be combined to form a robust safety net for the deployment of EEG-based machine learning models in real-world applications.

---

### From Student Risk Prediction to SC2R: Semantics-Constrained Counterfactual Recourse for Educational Decision Support

Authors: Ngoc Luyen Le, Marie-Hélène Abel, Bertrand Laforge
Published: 2026-08-18
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2608.17618v1

Learning analytics models can identify students at risk of poor performance, but they do not directly indicate which interventions are feasible, actionable, and compatible with educational constraints. This paper introduces SC2R, a semantics-constrained counterfactual recourse framework for educational decision support. SC2R combines a calibrated predictive model, integer-programming-based recourse generation over discrete action variables, a lightweight RDF vocabulary for intervention-plan representation, and SHACL validation for enforcing timing, budget, immutability, and availability constraints. The framework is evaluated offline on the OULAD dataset using snapshots constructed relative to each assessment at two decision horizons. Results show that the predictive component provides strong performance, that compact intervention plans can be generated at scale, and that semantic validation reveals infeasible plans that lighter optimization-only settings would otherwise accept. Rather than claiming causal improvement in student outcomes, this work shows that counterfactual recourse becomes more operationally meaningful in education when recommendations are not only model-valid, but also semantically feasible and machine-checkable.

---

### MoNe: Modular Neural Memory for Efficient Long Context Inference

Authors: Wonguk Cho, Kyubyung Chae, Tribhuvanesh Orekondy, Sunghyun Park, Hyoungwoo Park, Jeongho Kim, Arash Behboodi, Kyuwoong Hwang, Sungrack Yun
Published: 2026-08-18
Categories: cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2608.17616v1

We present MoNe, a lightweight modular neural memory that attaches to any frozen pretrained Transformer to enable long-context inference without retraining. MoNe reads context in fixed-size segments via test-time learning of fast-weight neural memory networks with layer-localized gradient updates; at inference, the memory generates keys and values from the query tokens alone, with no context tokens re-read. This two-phase design decouples inference cost from context length, achieving $O(N)$ preprocessing and $O(1)$ query cost with peak GPU memory that does not grow with $N$. At 128K tokens, MoNe reduces both compute and peak GPU memory by approximately 80% compared to ICL with only 6.4% parameter overhead. MoNe generalizes to context lengths far beyond the backbone's native window, achieving strong performance on needle-in-a-haystack and word extraction benchmarks from RULER, where ICL degrades sharply.

---

### PathoArgus: Advancing Evidence-Grounded Long-Context Visual Reasoning across Gigapixel Whole-Slide and Multi-Slide Case Contexts

Authors: Bowen Liu, Qixiang Zhang, Xiaomeng Li
Published: 2026-08-18
Categories: cs.CV
arXiv: https://arxiv.org/abs/2608.17607v1

Whole-slide pathology reasoning requires models to integrate gigapixel-scale visual evidence across complete case-linked slides, yet current question-answering benchmarks primarily measure final answer accuracy--a metric vulnerable to linguistic priors and benchmark regularities, and insufficient to establish that predictions are grounded in the supplied tissue. We introduce PathoArgus-Bench, a benchmark and evaluation protocol that explicitly tests the full evidence chain: availability, accessibility, use, and responsiveness. PathoArgus-Bench comprises 22,078 four-choice questions from 4,913 patients across 15 TCGA projects, covering six pathology capabilities across three levels of evidence demand, and operates under a fixed reader budget that retains only a small fraction of the gigapixel context. To further isolate evidence-grounded reasoning, we contribute ESG (Evidence State Quartets), a controlled set of 483 quartets where the question text is fixed while the target WSI set is moved, replaced, or removed, requiring consistent predictions across all states. Evaluating 20 general-purpose, medical, and pathology-specific systems reveals a stark gap: while GPT-5.6 achieves 57.09% overall accuracy and 57.04% on ESG, it correctly completes only 19 of 483 quartets (3.93% QExact), exposing that row-level accuracy does not translate into reliable evidence grounding. We also introduce PathoArgus, a fixed-budget reader that allocates context via question relevance and spatial coverage, attaining 50.39% overall accuracy yet only 1.86% QExact--demonstrating that improved context access alone does not ensure consistent evidence-based prediction. Our benchmark and diagnostics establish that acquiring useful whole-slide context is necessary but far from sufficient, and call for a shift from answer-centric to evidence-grounded evaluation in computational pathology.

---

### Multi-turn Conversational AI from Text to Multimodal Interaction: Data, Models, Evaluation, and Open Challenges

Authors: Syeda Faiza Ahmed Sara, Zien Sheikh Ali, Hunzalah Hassan Bhatti, Firoj Alam, Shammur Absar Chowdhury
Published: 2026-08-18
Categories: cs.CL, cs.AI, cs.SD
arXiv: https://arxiv.org/abs/2608.17605v2

Conversational AI is moving beyond isolated text prompts toward sustained, multimodal interaction. In real conversations, users clarify goals, revise requests, interrupt responses, switch topics, and introduce new evidence while expecting systems to preserve context across turns. This makes multi-turn dialogue a distinct challenge requiring systems to maintain and update memory, ground responses across modalities, tools, and external knowledge, and adapt across languages and cultures. This study reviews multi-turn conversational AI across text-only dialogue, AudioLLMs and speech-native systems, multimodal and omni-modal systems, and tool-augmented agents. We organize the literature around datasets and benchmarks, modeling paradigms, training strategies, evaluation setups, and cross-cutting challenges. Our analysis shows that support for multiple modalities has advanced faster than the ability to sustain coherent interaction across a session. Despite stronger capabilities to perceive, speak, and act across modalities, current systems still struggle with persistent memory, cross-turn grounding, full-duplex interaction, robust evaluation, and cultural alignment. We conclude with a research agenda for systems that can remember, revise, ground, speak, listen, act, and adapt across turns, modalities, and cultures. (https://github.com/faiza-sfa/multiturn-conversational-ai-survey)

---

### SpurCon: Weighted Supervised Contrastive Learning for Mitigating Spurious Cues in Medical Imaging

Authors: Shenhav Nadir, Meir Yossef Levi, Eyal Gofer, Guy Gilboa
Published: 2026-08-18
Categories: cs.CV
arXiv: https://arxiv.org/abs/2608.17598v1

Despite the rapid progress of deep neural networks in visual recognition, their adoption in high-risk medical applications remains limited due to reliability and robustness concerns. Models may exploit spurious correlations, particularly in medical imaging, where devices or treatment artifacts often co-occur with pathology. In small or imbalanced datasets, such cues further reduce worst-group performance and undermine clinical trust. To solve these issues, two major challenges should be addressed: identifying dataset-specific spurious cues, which typically require domain knowledge, and mitigating reliance on them. To tackle both, we propose SpurCon, a lightweight framework based on a novel supervised contrastive loss formulation that leverages available metadata and predicted spurious labels to enhance robustness. We introduce a fast few-shot procedure, without network training, to estimate spurious labels using a small number of expert-annotated samples. We then propose a weighted supervised contrastive objective, WtSupCon, that reshapes the representation geometry by assigning sample-specific weights that depend on the (pathology, spurious, metadata) combination. For example, the highest weight is assigned to samples that differ only in their spurious label. This yields highly similar representations for images with the same metadata and pathology, differing only in the predicted spurious label. Our method operates on pretrained image encoders (such as BiomedCLIP) and trains only a lightweight projection head. We evaluate SpurCon on a synthetic setting and on Waterbirds, CheXpert, a chest X-ray classification dataset, and ISIC 2020, a skin cancer classification dataset. Our approach delivers the best spurious-mitigation performance, balancing well worst-group and overall accuracy on multiple datasets.

---

### HarnessRisk: A Lifecycle-Oriented Benchmark for Agent Harness Safety

Authors: Yajing Bai, Jinhao Duan, Jie Peng, Xianfeng Wu, Sijia Liu, Song Wang, Tianlong Chen
Published: 2026-08-18
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2608.17597v1

Large language models are increasingly deployed through agent harnesses that manage tools, extensions, persistent state, permissions, and external actions. Existing safety benchmarks mainly target individual attack mechanisms or a limited subset of operational settings, making it difficult to compare how safety failures emerge across different harness responsibilities. We present HarnessRisk, a lifecycle oriented benchmark that organizes agent harness safety into six operational phases including Harness Configuration, Capability Extension, Runtime Operation, State Persistence, Action Control, and Incident Recovery. HarnessRisk contains 128 sandboxed cases, each pairing a benign user objective with an adversarial instruction embedded in an untrusted workflow artifact. We evaluate each trajectory using Utility, Attack Success Rate, Persistence, and Detection. Across three harnesses, six language models, and 14 model and harness configurations, attack success ranges from 12.6% to 80.9%, while Utility remains between 75.0% and 97.6%. Harness Configuration is the most vulnerable phase across all three harnesses, showing that attacks can succeed by altering security sensitive parameters within otherwise authorized workflows. We also find that explicit risk recognition does not reliably lead to safe action, as some configurations detect risks in more than 90% of runs while retaining substantial attack success. These results highlight the need to evaluate agent safety across multiple harness responsibilities and at the level of the deployed model and harness configuration.

---

### tinyDSM: A Framework for Skill Modeling and Development for Resource-Constrained Millirobots

Authors: Markus Kobelrausch, Michael Miedler, Axel Jantsch
Published: 2026-08-18
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2608.17596v2

In this study, we investigate developmental mechanisms that enable small, resource-constrained systems such as cm-sized millirobots to autonomously explore, learn, and adapt their capabilities throughout their lifespan. Reinforcement learning algorithms guide the agent's skill acquisition and adaptation through the interplay of our proposed tiny Developmental Skill Method (tinyDSM), which integrates intrinsic motivation and fitness-based assessment. We strive for minimal hard-wired skills while encouraging the open-ended development of new skills. A key emphasis in our approach is to encode minimal a-priori general knowledge, which serves as a foundational starting point for the system as it further learns system-specific dependencies from the initial knowledge provided. Thus, by design, our approach aims to cover generic application domains. The methodology is based on (a) developmental mechanism with intrinsic motivation, and (b) a cognitive architecture (knowledge, reasoning, learning), while (c) utilizing minimal resources. It uses a hierarchical knowledge graph and kinematic reasoners to model and evaluate simple and advanced motion related skills. In our experiments, we use a resource-constrained millirobot with a volume of 36 cm^3 with a Raspberry Pi Pico 32-bit microcontroller that integrates all described features and capabilities except the camera system in 9 kB. Starting with learning the most elementary motor skills the millirobot autonomously progresses from simple linear and angular movements to complex geometric patterns within 15 minutes. To complement the physical experiments, we perform a simulation-based analysis that enables systematic comparisons across learning algorithms and intrinsic motivation parameters.

---

### Modified Bryson-Frazier Smoothing and Hyperparameter Learning for Temporal Gaussian Process Regression

Authors: Tom Colemont, Brecht Evens, Tjonnie G. F. Li, Frederik De Ceuster
Published: 2026-08-18
Categories: stat.ME, stat.ML
arXiv: https://arxiv.org/abs/2608.17595v1

One-dimensional Gaussian processes with stationary, integrable kernel functions admit exact or arbitrarily accurate state-space representations, enabling linear-time inference through Kalman filtering and Rauch-Tung-Striebel (RTS) smoothing. However, the RTS smoother requires inversion of predicted state covariance matrices, which can become ill-conditioned and may therefore lead to numerical instabilities. In this work, we revisit the modified Bryson-Frazier (MBF) smoother as an alternative to the RTS smoother for Gaussian process regression in its state-space representation. In addition to reducing computational cost and memory requirements, the MBF smoother computes the same posterior distributions as the RTS smoother while avoiding the problematic covariance matrix inversion and the associated numerical instabilities. Furthermore, we demonstrate that the intermediate quantities computed by the MBF smoother can be reused to compute gradients of the negative log marginal likelihood, enabling kernel hyperparameter learning with minimal additional cost. Together, these results establish the MBF smoother as a unified and numerically robust approach to inference and kernel hyperparameter learning for one-dimensional Gaussian process regression.

---

### Communication Reduction via Semantic-Based Encoding in DMPC Using LSTMs

Authors: Torben Schiz, Pedro H. J. Nardelli, Henrik Ebel
Published: 2026-08-18
Categories: eess.SY, cs.DC, cs.LG, cs.MA, cs.RO
arXiv: https://arxiv.org/abs/2608.17592v1

The communication demands of distributed model prediction control (DMPC) can overwhelm even advanced wireless communication technologies as agents must exchange a significant amount of information at least once per time step. To semantically reduce communication demands, this work employs encoder-decoder networks built around long-short term memory (LSTM) cells in a distributed optimization algorithm. Agents publish a reduced representation of a message and receivers reconstruct the original message upon reception. In tests with reduced communication using formations of mobile robots, trained networks retain satisfactory performance and work reliably under conditions overwhelming full communication. As the results show, the usage of LSTMs either allows unprecedented reconstruction accuracy or the usage of different prediction-horizon lengths without the necessity to retrain.

---