Artificial Intelligence · Cross-listed from math.OC
A Two-Stage Learning PINN Approach for Solving the Inverse Problem of the 1D Porous Medium Equation
Noura Al Helwani, Sophie Moufawad and Nabil Nassif
The Porous Medium Equation (PME), given by $u_t = \Delta(u^m)$ for $m > 1$, is a degenerate nonlinear
parabolic partial differential equation that arises in various physical applications such as fluid flow in porous media, heat transfer in
plasmas, and population dynamics. It is known for its nonlinear
diffusion and finite propagation speed. In this paper, we study numerical solutions of the one-dimensional direct and inverse PME using Physics-Informed Neural Networks (PINNs), and compare them with classical numerical methods and available analytical and manufactured solutions. While PINNs provide a flexible framework for solving both forward and inverse problems, we show that the standard inverse formulation suffers from a strong sensitivity to the initial guess, leading to only local convergence. To address this issue, we propose a novel two-stage PINN training framework for the inverse problem, which significantly improves convergence stability and allows reliable recovery of the unknown parameter even for poor initial guesses. Overall, the proposed approach demonstrates that PINNs are a flexible and accurate alternative to classical methods for the 1D PME, and the introduced two-stage training strategy substantially improves their robustness in inverse problems, providing a solid basis for extensions to more complex geometries and higher-dimensional cases.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CY
A Regulatory Placebo? The Systemic Failure of Mandatory GenAI Labeling
Jingyi Chen, Chaofan Bu, Shibo Yan et al. (+1 more)
We examine the worldwide trend of mandatory labeling of generative artificial intelligence(GenAI) as a reactive, symbolic form of legislation triggered by technological panic and institutional responses. From a technical perspective, this study demonstrates that current mandatory labeling not only creates implementation dilemmas but also risks hindering the evolutionary trajectory of AI technology. We then systematically analyze the three dominant theoretical strands of this regime, the value dilution theory, the information authenticity theory, and the proactive regulation theory, and find that they are products of regulators' cognitive limitations in understanding the logic of modern technology. Not only do such formalistic compliance requirements become a regulatory placebo, but they also obscure the genuine legal demands of the technological era. This challenges the current governance paradigm and suggests a shift from identity-label governance to content governance, with an urgent need to address the complex problems associated with GenAI.
Read the full abstract ▾
All authors Jingyi Chen, Chaofan Bu, Shibo Yan, Xuesong Li
Artificial Intelligence
JailbreakSkill: Scaling Automated Red-Teaming with Reusable and Ever-Evolving Skills
Xiaoyu Wen, Jiajia Li, Zhida He et al. (+11 more)
Automated red-teaming has produced a growing collection of attack strategies, yet they typically remain scattered across
prompts and workflows, making them difficult to systematically integrate, reuse, and improve at scale. We introduce JailbreakSkill, a skill-centric framework for scaling automated red-teaming through reusable and continuously evolving attack capabilities. JailbreakSkill packages existing attack strategies into modular,
agent-ready skills that can be directly reused and adaptively selected across tasks and target models. Beyond reuse, it closes the loop between attacking and learning: attack experience is used to diagnose, refine, combine, and discover new skills, which are added back to an ever-growing skill library. This
evolution lifts macro-average ASR by 17.5 percentage points on AdvBench and 13.4 points on HarmBench, including a 48.6-point gain against GPT-5.4 on AdvBench, while yielding novel attack strategies such as reframing a direct request as an unfinished document-completion task. Several evolved skills also generalize to unseen
prompts and target models without further adaptation. Our code is available at https://github.com/BattleWen/JailbreakSkill.
Read the full abstract ▾
All authors Xiaoyu Wen, Jiajia Li, Zhida He, Peng Yu, Chenxu Wang, Han Qi, Ziyuan Zhou, Cheng Jin, Ying Wen, Xingcheng Xu, Shuyue Hu, Tianhang Zheng, Chaochao Lu, Qiaosheng Zhang
Artificial Intelligence · Cross-listed from cs.ET
A Human-LLM Teaming Framework for Privacy Risk Analysis: An Illustration with CBDC-Based Welfare Schemes
Sourya Joyee De and Abdessamad Imine
Central Bank Digital Currency (CBDC)-based welfare schemes may be potentially
privacy invasive as they process significant volumes of beneficiary personal data and lead to
privacy harms such as surveillance, discrimination and stigmatization. Such welfare delivery schemes involve complex digital ecosystems and large number of stakeholders. Consequently, to examine their
privacy risks,
privacy risk assessments require extensive information gathering and synthesis, complex
reasoning, scenario explorations, contextual evaluation and human judgement. Thus, they present ideal scenarios for human-LLM teaming, where effective integration of complementary human and LLM capabilities can yield an outcome far superior to either human-only or LLM-only assessments. In this paper, we propose a first human-LLM teaming framework for the systematic
privacy risk analysis methodology called PRIAM. The framework specifies an iterative collaborative process in which the LLM processes large-scale documentary evidence to produce initial outputs, which are then interpreted and evaluated by human experts who direct their further refinement by the LLM and exercise their judgement to finalize the output. We illustrate the framework on the data characterization activity of PRIAM using a CBDC-based welfare scheme use case. The illustration demonstrates that while LLMs generate the initial data categories and assign initial values to data attributes, human experts evaluate and provide feedback to refine them, distinguishing documented evidence from inferences, identifying information gaps, and flagging unsupported or ambiguous outputs. This framework serves as a foundational contribution towards human-AI teaming for
privacy risk assessments.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
Contrastive Energy Fields for Inference-Time Procedure Planning in Instructional Videos
Mohamed Afham, Christoph Reich, Oliver Hahn et al. (+2 more)
Procedure planning seeks to estimate a sequence of actions to transition from an observed initial state to a given goal state. Current procedure planning approaches directly predict action sequences from latent representations using feed-forward neural networks or
diffusion-based inference. These paradigms treat every action as plausible, lacking the ability to enforce task-specific logical constraints that render certain actions irrelevant or not plausible. We propose CEFITO, a procedure planning approach that learns a predictor to express an action-conditioned representation space. Based on this representation space, we formulate procedure planning as a task-constrained optimization problem. Unlike prior methods, CEFITO explicitly reasons over the action space by omitting irrelevant actions during inference-time planning. This reformulation enables effective procedure planning and achieves state-of-the-art accuracy on two established procedure planning
benchmarks.
Read the full abstract ▾
All authors Mohamed Afham, Christoph Reich, Oliver Hahn, Daniel Cremers, Stefan Roth
Artificial Intelligence
HaReCAP: Habitual-action Grounding for Recursive Large Language Model Agents
Shen Liu, Zhenguo Xu, Shaopu Wang et al. (+2 more)
Long-horizon
embodied tasks require LLM
agents to iteratively decompose high-level goals, revise plans in response to environmental feedback, and ground leaf-level subgoals into valid executable actions. Recursive context-management methods such as ReCAP improve planning stability through multi-level task decomposition and parent-node refinement, but still repeatedly invoke the LLM at leaf nodes to ground atomic subtasks into exact valid actions. We refer to this final grounding step as last-mile grounding redundancy, which accumulates into substantial LLM-call and
token overhead during long-horizon execution. To mitigate this issue, we propose HaReCAP (Habitual-action Grounded ReCAP), a low-intrusion leaf grounding extension for ReCAP. HaReCAP extracts frequent leaf decisions from successful trajectories and compiles them offline into auditable and abstainable one-step leaf-reflex rules. At runtime, it skips the leaf LLM call only when a rule can uniquely determine a legal action in the current valid-action set; otherwise, it falls back to the original ReCAP. This design avoids repeatedly carrying the full recursive context into the LLM for routine leaf action grounding, while preserving the original recursive control flow. We evaluate HaReCAP on Robotouille and ALFWorld with Qwen3.5-27B as the main model. On tasks solved by both ReCAP and HaReCAP, HaReCAP reduces
token consumption by 14.67%, 17.93%, and 20.08% on Robotouille synchronous, Robotouille asynchronous, and ALFWorld, respectively. The results show that HaReCAP can serve as a low-intrusion extension to ReCAP-style recursive context-management frameworks, reducing last-mile grounding redundancy across environments and models on commonly successful trajectories.
Read the full abstract ▾
All authors Shen Liu, Zhenguo Xu, Shaopu Wang, Yike Gao, Chunlei Wang
Artificial Intelligence
Time to Reason: Scalable Neurosymbolic Learning for LTLf via Fuzzy Semantics
Riccardo Andreoni, Andrei Buliga, Alessandro Daniele et al. (+4 more)
Neurosymbolic (NeSy) Artificial Intelligence aims to integrate Deep Learning (DL) architectures with symbolic
reasoning. While initial NeSy approaches have targeted mainly symbolic
reasoning in propositional and first-order logics, recent works have started to address the construction of neurosymbolic frameworks for Temporal Logics, and in particular for LTLf. These approaches have established temporal NeSy as a promising research direction, laying the foundations for learning under temporal constraints. Nonetheless, they leave many questions unanswered. From a theoretical perspective, several differentiable semantics for interpreting LTLf have been proposed but have not yet been formally and systematically defined within a unified framework. Moreover, existing approaches commonly rely on automata to represent temporal knowledge, resulting in limited scalability. Motivated by this research gap, this paper provides the following contributions: (i) formally defining different fuzzy semantics for LTLf, and systematically analysing theoretical properties regarding equivalences and dualities of temporal operators; (ii) showing how these semantics can be directly integrated within a novel NeSy framework, called DiffLTLf, enabling flexible and scalable learning without relying on the usage of automata; and (iii) introducing a novel evaluation protocol of increased complexity of learning tasks w.r.t. existing
benchmarks. Our results show that the choice of fuzzy semantics has a significant impact on predictive performance. Moreover, DiffLTLf achieves performance on par with, and sometimes superior to, state-of-the-art probabilistic approaches while substantially improving scalability. Taken together, these results establish direct fuzzy interpretations as a competitive and scalable alternative to existing temporal NeSy frameworks.
Read the full abstract ▾
All authors Riccardo Andreoni, Andrei Buliga, Alessandro Daniele, Paolo Felli, Chiara Ghidini, Marco Montali, Massimiliano Ronzani
Artificial Intelligence
The Value of a Prompt: An LLM-Relative Kolmogorov-Complexity Approach
Rafael Pass
In a world where valuable artifacts are increasingly created, completed, or processed by LLMs, the central economic question is not only what the LLM can produce, but what value remains in the inputs (i.e., the
prompts) we provide to it. Given a
prompt, hint, critique, problem statement, or partial solution that helps an LLM produce an artifact $z$—a proof, program, design, or scientific hypothesis—how should we measure the value of that input? Intuitively, an input is valuable when it makes the target artifact easier for the model to generate: either by increasing its sampling probability, or by reducing the thinking time needed to find it. We propose a computational Levin–Kolmogorov complexity approach to this problem, by appropriately replacing the universal Turing machine in the classical definitions by the LLM itself. Concretely, we introduce an LLM-relative notion of probabilistic Levin–Kolmogorov complexity $pKt$—treating the model's thinking as the random tape of the program, and charging logarithmically for it in Levin's manner—and define
prompt value as algorithmic mutual information with respect to $pKt$. This captures the intuition above: a
prompt having $b$ bits of value for an artifact $z$ makes $z$ $2^b$ times “easier to obtain”, by multiplying the success probability by $2^b$, by dividing the required computation by $2^b$, or by any corresponding tradeoff between probability and computation. In contrast to the classical notion of algorithmic mutual information, ours is efficiently estimable. We additionally show that, under a natural reproduction experiment, a
prompt value of \(b\) bits means that reproducing \(z\) without the
prompt has median
token cost \(2^b\) times that of reproducing it with the
prompt.
Read the full abstract ▾
Artificial Intelligence
Drive, Pack, Fly: The Travelling Thief Problem with Drone
Kabir Murjani and Abhay Sobhanan
In collection operations, accumulating payload progressively slows the vehicle, imposing a cumulative penalty on routing efficiency. An onboard drone can offset this penalty by retrieving outlying items, thereby shortening the makespan and increasing operational profit. However, travel time remains load-dependent, and each item collected by the ground vehicle shifts the arrival times that govern the drone's launch and rendezvous points. This paper introduces the Travelling Thief Problem with Drone (TTP-D), which maximises the collected profit, net of a time-based rental cost, by jointly optimising item selection, vehicle routing, and flight synchronisation. We formulate a mixed-integer linear program that solves small instances to optimality, and develop both metaheuristics and an
attention-based Deep Reinforcement Learning (DRL) policy for larger instances. We further propose a learner-initialised hybrid solver, in which the DRL policy constructs an initial solution that a short annealing run subsequently refines. On two
benchmark sets, this hybrid recovers most of the metaheuristic baseline's quality at a fraction of its computational budget, although the largest instances still require the baseline at its full budget. Finally, a sensitivity analysis reveals that the rental ratio is the primary driver of profitability, whereas the fleet parameters affect profit only at the margin.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.HC
Visualizing Uncertainty-to-Action Composition for Human Oversight
Chisom Anyabolu, Akshat Dubey and Georges Hattab
Artificial intelligence systems often disclose uncertainty, yet they rarely make clear what response that uncertainty should trigger. Most uncertainty visualizations encode uncertainty in model outputs, leaving users to discern the most appropriate course of action. A second region of the design space–uncertainty in the decision process itself, including how multiple uncertainty conditions compose into an oversight response– remains comparatively underexplored. We address this gap with two coupled contributions. First, we introduce an uncertainty-to-action binding framework that composes multiple uncertainty conditions into a single oversight response under a precedence policy with a contextual safety modifier. That response concerns whether and how an AI-supported decision may proceed, not the substantive domain decision itself. Second, we present ActionCue, a process-transparency visualization that renders that composition explicit. We demonstrate the approach through a three-way comparison with confidence-only and data-level uncertainty displays, using worked cases from healthcare, credit assessment, and disaster
forecasting. Together, the framework specifies how uncertainty conditions are resolved into an oversight response, and the visualization makes that resolution inspectable rather than implicit.
Read the full abstract ▾
Artificial Intelligence
ParaTempo: Efficient Parallel Reasoning via Temporal Confidence
Xuteng Zhang, Wenhao Zeng, Xiaodong Gu et al. (+5 more)
Parallel
reasoning improves the accuracy and robustness of large
reasoning models by exploring multiple solution paths, but its computational cost grows with
reasoning depth and branch count. Existing methods for managing these parallel paths typically rely on final-answer consensus, local
token confidence, or isolated intermediate probes. However, these signals are often delayed, weakly tied to actual
reasoning progress, or too noisy for dynamic, branch-level control. To address these limitations, we introduce ParaTempo, a training-free asynchronous parallel
reasoning framework. ParaTempo is driven by temporal confidence, a branch-local measure of answer-space convergence. Each branch is periodically probed for a tentative answer probability distribution, and temporal confidence quantifies how sharply the recent intermediate probes concentrate on a dominant answer. Once sufficient evidence has accumulated, ParaTempo drives its entire control process from this single signal: low-confidence branches are pruned, branches that persistently commit to their dominant answer are retired early, freed computation is reallocated by forking new branches, and generation stops globally once the confidence-weighted vote concentrates. Without requiring synchronization among
reasoning trajectories, ParaTempo adaptively allocates computation based on branch-level convergence. Experiments on challenging mathematical and scientific
reasoning benchmarks show that ParaTempo reduces average latency by 21.8-32.2% and total
token usage by 18.1-30.3% while maintaining competitive accuracy. Moreover, temporal confidence exhibits stronger temporal stability and predictive power for future branch convergence than
token-level and instantaneous signals.
Read the full abstract ▾
All authors Xuteng Zhang, Wenhao Zeng, Xiaodong Gu, Chao Hu, Haotian Lin, Yuling Shi, Min Wang, Beijun Shen
Artificial Intelligence
Reasoning-supported Robustness Validation of Automotive E/E Components
Jan Novacek, Alexander Viehl, Oliver Bringmann et al. (+1 more)
This article presents an ontology-supported approach to tackle the complexity of the Robustness Validation (RV) process of automotive electrical/electronic (E/E) components. The approach uses formalized knowledge from the RV process and stress, operating, and load profiles, so-called Mission Profiles (MPs). In contrast to the error-prone industrially established manual procedure, we show how component characteristics are formalized in OWL in order to form the foundation of an efficient automated analysis selection and decision support during the RV process. Additionally, a rule-based transformation of component characteristics upon propagation via SWRL is described. The proposed approach is based on the idea of mapping MPs to an OWL representation in order to allow to execute semantic queries against MP data to improve their integration into the RV process. The resulting ontology-supported application framework has been applied to an industrial use-case from automotive power electronics. A generalization of the approach is described and demonstrated by applying it to stress test selection within the AEC Q100 standard. We present experimental results showing that the RV process can be significantly improved in terms of reduced design time and increased exhaustiveness by automating the analyses selection step and the provisioning of all the relevant data to be used.
Read the full abstract ▾
All authors Jan Novacek, Alexander Viehl, Oliver Bringmann, Wolfgang Rosenstiel
Artificial Intelligence · Cross-listed from cs.LG
PertMind: Eliciting Emergent Biological Reasoning in LLM via Reinforcement Learning on Cellular Perturbation Data
Zhenchao Tang, Xiaogang Xu, Jiafei Wu et al. (+16 more)
Large
language models can describe mechanisms, yet scalable post-training still depends on costly, manually curated biological
reasoning traces. Here we show that cellular perturbation atlases can instead become reinforcement-learning environments, where measured gene responses provide computable rewards for biological
reasoning. We introduce PertMind, which combines trusted-trajectory supervised initialization with gene-, pathway-, and format-level reinforcement signals. Although trained only on forward perturbation-response prediction, PertMind improves response inference in unseen cellular contexts while retaining general
language capabilities. It also transfers, without task-specific post-training, to reverse perturbation identification, double-perturbation
reasoning, phenotypic-screen prioritization, and biological-process interpretation. PertMind further generates biological profiles that support competitive gene,
cell, and donor representations across multiscale downstream tasks. These results support the hypothesis that reinforcement on experimental endpoints can concentrate reusable biological strategies already accessible to pretrained models. More broadly, perturbation-derived reinforcement learning offers a scalable route for transforming expanding experimental atlases into training environments for general-purpose biological
reasoning.
Read the full abstract ▾
All authors Zhenchao Tang, Xiaogang Xu, Jiafei Wu, Jiahui Guan, Bo Li, Tianxu Lv, Jiale Zhou, Haohuai He, Zhi Song, Hanbo Huang, Jiehui Huang, Xun Lin, Zhipeng Deng, Zhaoxing Li, Guanxing Chen, Yaokun Li, Mengran Li, Songming Zhang, Zhe Liu
Artificial Intelligence · Cross-listed from cs.SE
Towards Risk-free AI Agent Deployment
Yintong Huo, Rangeet Pan and Abhik Roychoudhury
LLM-based
agents are rapidly moving from research prototypes into the core business processes of organizations, but these
agents pose deployment risks to security, compliance, and functionality. In this article, we argue that risk-free deployment must be grounded in the
agent's trajectory: the recorded sequence of
reasoning steps, tool invocations, and environmental observations. Trajectories are available for any
agent, and many failures are visible only in the trajectory. To make
agents deployable and sustainable, we advocate
agent testing and debugging as a systematic research direction for detecting and mitigating these risks. This article begins with the challenges of testing
agents, including the oracle problem, non-determinism, trajectory validation, and the absence of adequacy metrics. We then turn to debugging
agents, from automated failure attribution to repair and self-
evolution. We distill these directions into a practical deployment-readiness checklist covering the full deployment lifecycle. Finally, we identify open problems, i.e., formal adequacy metrics, root-cause attribution over long-horizon trajectories, and the reliability of self-evolving
agents, that the community must address to enable trustworthy
agent deployment.
Read the full abstract ▾
Artificial Intelligence
A Policy Algebra for Trust-Preserving Agentic AI Execution
Bhaskar Tripathi, Anurag Kumar, Ramendra Kumar et al. (+1 more)
Large
language model-based agentic frameworks primarily optimize capability: whether an
agent can reason, retrieve information, call tools, delegate work, and complete a goal. Enterprise execution requires a stronger property. A successful result is not reliable if it was produced through unauthorized data access, widened delegated authority, unapproved side effects, unrecoverable budget consumption, or incomplete evidence. This paper defines reliable capability as a path property: an
agent is reliably capable only when it completes a task through action events that remain admissible under identity, profile, tool, data,
memory, budget, artifact, approval, and audit constraints. We propose a policy
algebra that defines the reliability envelope within which
agent capability may be exercised. Security profiles and runtime obligations compose through joins, intersections, budget narrowing, approval inheritance, and evidence accumulation; the resulting composition is both trust-preserving and the least restrictive state satisfying all governing inputs. The
algebra also propagates restrictions across multi-
agent calls and introduces cost-aware artifact materialization, which redirects open-ended execution toward a recoverable outcome as budget exposure grows. The evaluation is interpreted as a reliability-capability trade-off rather than a capability
benchmark: the policy-
algebra runtime intervenes on 94.8% of policy-violating events while retaining an 86.9% task-completion rate, eliminates the observed profile-monotonicity and zero-artifact-exhaustion violations, and increases audit completeness to 98.6%. The method provides researchers and practitioners with formal correctness conditions, executable decision semantics, and trace evidence for building
agents that are not only capable, but reliably capable.
Read the full abstract ▾
All authors Bhaskar Tripathi, Anurag Kumar, Ramendra Kumar, Bhavesh Gadhe
Artificial Intelligence
Think Inside the Chunk: RegulaRAG for Regulation-Compliant Scenario Generation using LLMs: A Case Study of UN Regulation No. 152
Vahid Zolfaghari, Nenad Petrovic, AndrÉ Schamschurko et al. (+1 more)
Generating regulation-compliant test scenarios is essential for validating safety-critical automotive systems, yet Large
Language Models (LLMs) struggle to ground outputs in long, hierarchical standards. We present RegulaRAG, a
Retrieval-Augmented Generation (RAG) pipeline that couples SmartChunking, reference-aware enrichment of paragraphs and tables via graph traversal, with Smart Retrieve & Rerank over these enriched units. To test our system, we evaluate on a manually curated
dataset covering all scenarios in UN Regulation No. 152 (AEBS). Our study comprises: (i) a three-step progressive search that identifies near-optimal
retrieval parameters without exhaustive grid search; (ii) head-to-head comparisons against five baseline RAG systems; and (iii) a robustness stress test that scales the source corpus with distractor content. Outputs are evaluated using a customized penalized scoring metric. Across all experiments, RegulaRAG achieves the highest average Meta-Score (82.99), outperforming the next-best system by 43% (NoRAG: 57.94), while operating at 14k-25k
tokens per query versus up to 500k for graphcentric baselines. It maintains strong performance, remaining stable even as the number of regulatory sources grows, whereas competing RAG systems degrade sharply in both quality and robustness.
Read the full abstract ▾
All authors Vahid Zolfaghari, Nenad Petrovic, AndrÉ Schamschurko, Alois Knoll
Artificial Intelligence · Cross-listed from cs.CR
Ventor-QTest: Threat-Model-Driven Verification of Vendor-Hosted LLM APIs
Xiangfan Wu, Zonghao Ying, Huiyu Wu et al. (+4 more)
As large
language models become increasingly widespread, third-party providers that deploy open-weight models have become an important part of the ecosystem.
Auditing the quality of their inference APIs is therefore an open problem. We formalize hosted model routing as a
stochastic process and propose \mbox{Ventor-QTest}, a composite black-box audit that requires no probability information from the target API. Its repeated-request component sends each frozen constrained context to the target multiple times, reconstructs a categorical output distribution from the returned text counts, and reports average fidelity loss (AFL) as a null-bias-corrected, within-window mean coarsened-KL statistic. Its long-sequence component uses independent runs to report extreme fidelity loss (EFL) through the empirical upper tail of a run-level reference-centered-surprisal statistic. Across three logprob-capable route conditions, AFL shows strong linear descriptive agreement with a logprob-derived coarsened-KL comparator. Across seven route snapshots, 20-run sequence probes reveal route-specific EFL variation. AFL and EFL have little detectable route-level association with GPQA-Diamond accuracy. In contrast, pronounced EFL coincides with a decline in Terminal-Bench pass rate as task exposure increases. This pattern may arise because correctness in long-horizon tasks is more sensitive to extreme fidelity loss. These results motivate reporting AFL and EFL jointly, particularly when
auditing long-horizon agentic tasks. The open-source implementation is available at https://github.com/Tencent/AI-Infra-Guard/tree/main/services/api_checker/ventor_qtest.
Read the full abstract ▾
All authors Xiangfan Wu, Zonghao Ying, Huiyu Wu, Xing Zheng, Huangsheng Cheng, Xiaorong Shi, Jing Guo
Artificial Intelligence · Cross-listed from cs.CL
Counting Documents Is Not Counting Text: Unit Bias in Web-PDF Corpus Statistics
Luca Foppiano
PDF corpora advertise their size in
tokens, but every rate they publish (coverage, OCR routing, re-fetch recovery,
language mix) is computed per document, and none decomposes its
token total. Because PDF length is extremely skewed, the two units can describe the same corpus very differently. We ask how the headline statistics of a web-PDF corpus change when each document is weighted by the text it contributes rather than counted once. We used CC-MAIN-2021-31-PDF-UNTRUNCATED (7.9M Common Crawl PDFs, 32.6B
tokens), the one public corpus that pairs the fragments Common Crawl stored with the re-fetched originals. Text mass is highly concentrated: 3.02% of text-bearing documents hold half the
tokens (Gini 0.807). The clearest consequence is Common Crawl's payload cap, which truncated 23.06% of these documents but 63.08% of their text. Reconstructing the truncated fragments and extracting both versions, two widely used text-layer parsers recover only 1.4% and 11.4% of that exposed text, so roughly 55-62% of the corpus's text is unrecoverable from the crawl by such pipelines; under the 5MiB cap adopted in March 2025, 30.19% of
tokens would still be exposed. We recommend that corpus statistics be reported in both units, documents and
tokens.
Read the full abstract ▾
Artificial Intelligence
AstronOS: A Unified Execution Model and Runtime for Long-Horizon Agentic Systems
Zhenhang Nie, Gui Zheng, Xudong Sun et al. (+2 more)
Agentic systems often organize execution and state around a single conversation, model invocation, or
agent instance, even when real work spans many calls and stages. We introduce a unified execution model that maintains a work item's persistent identity and versioned authoritative state across calls. Each step receives input scoped to a specific state version and new material; a result advances state only after validation and recording. We implement selected paths of this model in AstronOS using Cases, Tasks, and Scenario Packs across central and local execution. We compare five complete strategies for carrying an established software-version update plan into a fresh model session: rereading original materials, replaying full history, deterministic text summary, deterministic JSON, and the AstronOS runtime-mediated handoff. Ten controlled tasks are run under all five strategies with three repetitions, yielding 150 included executions. On the single-stage reference family, strategies perform similarly. In the primary three-stage A-C batch, AstronOS passes the frozen scorer in 14 of 15 executions, compared with 0 of 15 for rereading and 2 of 15 for full-history replay; later non-interleaved summary and JSON batches each pass 0 of 15. AstronOS has lower attempt-accounted model-
token cost per passing execution, while requiring more execution-window time per attempt. These results associate the complete AstronOS condition with higher end-to-end pass rates across fresh sessions in this
benchmark, at a measurable time cost.
Read the full abstract ▾
All authors Zhenhang Nie, Gui Zheng, Xudong Sun, Tailong Zhu, Bin Zhang
Artificial Intelligence · Cross-listed from cs.CV
Synthetic Data Augmentation for Satellite-Based Analysis of Battle-Damaged Agricultural Fields in Ukraine
Marta Sumyk, Oleksandr Kosovan and Iryna Voitsitska
Monitoring war-induced damage to agricultural land in Ukraine is important for understanding threats to food security, environmental stability, and post-war recovery. However, the development of computer-
vision systems for satellite-based damage analysis is limited by the scarcity of labeled imagery, especially for damaged agricultural fields. This work investigates synthetic data augmentation as a method for improving classification under limited and imbalanced training data. We train class-conditional Generative
Adversarial Network (GAN) and Denoising
Diffusion Probabilistic Model (DDPM) architectures on real satellite images and use them to generate additional bombed and not-bombed agricultural-field samples. The generated images are used only for training augmentation, while all downstream evaluation is performed on an exclusively real test set. A
Vision Transformer classifier is trained under multiple real and synthetic data configurations to measure the practical utility of each generative approach. The best configuration, based on balanced DDPM augmentation, improves accuracy from 84% to 88%, balanced accuracy from 67% to 81%, macro F1 from 65% to 78%, and recall for the underrepresented not-bombed class from 41% to 69%. These results demonstrate the potential of synthetic satellite imagery for data-scarce geospatial applications in war-affected regions.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
Adaptive Post-Processing Drives Instance-Level Detection in Stroke Lesion Segmentation
Qinghui Liu, Jon André Ottesen, Atle Bjørnerud et al. (+1 more)
Instance-level lesion detection has been an increasingly larger focal point in medical image
segmentation besides the more standard voxel-level overlap. Still, most pipelines are trained and post-processed for voxel overlap alone. In particular, the mismatch is most pronounced for small lesions, where a near-miss prediction—substantial overlap that falls just short of the instance-matching threshold—scores the same as a complete miss. In our ISLES'26 submission, we found that closing this gap mattered far more in post-processing than in architecture design. Our Volume-Conditioned Adaptive Post-Processing (VCAP) scheme adjusts component-size thresholds to each case's predicted lesion burden, improving Lesion-F1 by 0.032 (unbiased cross-fold estimate)—approximately 6 times larger than any architectural change we tested. A resolution-aware
attention architecture (Viola2Plus), designed for small-lesion
segmentation, shows why the distinction matters: it left small-lesion Dice unchanged but raised small-lesion detection rate by 3.7%, a real effect voxel-overlap metrics alone would have missed. Under 5-fold cross-validation on the 1,453-case training set, our post-processed two-architecture ensemble achieves Dice 0.651 and Lesion-F1 0.614, versus 0.644 and 0.573 for the unprocessed single-model baseline.
Read the full abstract ▾
All authors Qinghui Liu, Jon André Ottesen, Atle Bjørnerud, Kyrre Eeg Emblem
Artificial Intelligence · Cross-listed from cs.LG
Multinomial Subset Routing with Sum-Max Rewards and Operational Constraints
Quan Zhou and Yiyan Huang
We study online routing to subsets of experts under aggregate bandit feedback and long-run operational constraints. Expert contributions can be complementary: for each task dimension, the best selected expert determines the contribution, and the total reward aggregates these dimension-wise maxima. At the same time, capacity, budget, and
fairness requirements impose lower and upper bounds on long-run expert activation frequencies. A fixed deterministic subset cannot generally satisfy such heterogeneous requirements, motivating a
stochastic routing policy. We formalize this problem as Multinomial Subset Routing (MSR). The learner maintains a distribution \(q\) over \(K\) experts, samples an expert independently \(M\) times from \(q\), and routes each task to the distinct sampled experts. We propose OMD-Approachability, which combines online mirror descent with Blackwell's approachability to optimize MSR under two-sided operational constraints. We establish \(O(T^{-1/2})\) average reward regret and expected constraint violation. We also quantify the approximation gap induced by a linear surrogate, and evaluate the approach on a real-world crowdsourcing
dataset.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
OceanDepths: A Global Dataset of Paired Subsurface and Surface Ocean Observations
Simon Donike, Ruben Cartuyvels, Antonino Ian Ferola et al. (+3 more)
Despite comprising over 70% of its surface, the world's oceans are critically underobserved compared to the land surface or the atmosphere. Understanding the global ocean requires jointly observing its surface and subsurface structure, yet no standardized, high-resolution
dataset couples satellite surface fields to co-located in situ depth profiles in an AI-ready format. Existing resources either consist of model-reconstructed gridded products rather than observations, cover only a single variable or basin, or operate at resolutions too coarse for mesoscale dynamics. We introduce OceanDepths, the first open, global, regridded AI-ready
dataset that pairs satellite-derived sea surface temperature (SST), sea surface salinity (SSS), and sea surface height (SSH) L4 products with co-located EN4 subsurface temperature and salinity profiles, complemented by matched GLORYS12 ocean reanalysis data to support comparisons or multi-stage learning. The
dataset spans 2000-2024 at 0.1 degrees x 0.1 degrees spatial resolution and at weekly temporal resolution, covering the entire globe's sea surface and with over 9.5 million paired profiles interpolated to 50 standardized depth levels. We provide a configurable system to split the globe in equally sized spatial patches. The 4D multivariate structure, high resolution, long temporal extent, and extreme sparsity of subsurface observations (approximately 0.01% per depth level) make OceanDepths a challenging testbed for novel AI methods. We demonstrate subsurface state reconstruction as an example task with simple baseline models, but also envision OceanDepths to support the development of observation-based forecast methods and other related tasks. Available at: https://huggingface.co/
datasets/ESA-philab/OceanDepths.
Read the full abstract ▾
All authors Simon Donike, Ruben Cartuyvels, Antonino Ian Ferola, Elisa Carli, Diego Fernandez Prieto, Marie-Helene Rio
Artificial Intelligence
What Does Context Compression Cost an Agent? Interaction Costs Unrevealed by Task-Completion Metrics
Shuyu Liu
Task completion is the standard metric for evaluating context compression, yet it is incomplete: compression can increase an
agent's interaction cost by forcing it to reacquire dropped state while leaving completion statistically unchanged. We introduce a controlled runtime measurement protocol for reacquisition cost in a bounded-horizon tool-using
agent. The
agent acts in a deterministic planning environment under a fixed 24-turn horizon. We vary compression severity, compare a dropping operator with a fact-preserving operator, restore dropped state through controlled oracle interventions, and decompose tool calls into
retrieval and execution. We evaluate three models across two task regimes.
Retrieval calls increase in all six model-regime comparisons and account for almost all added interaction; five of six remain significant after Holm correction. At the prespecified 5x comparison point, completion changes are not significant in any
cell. DeepSeek shows a significant completion drop only at 10x compression. GPT-5.5 is the clearest case: completion changes from 80% to 85% (p = 1.0) while
retrieval increases from 21.0 to 63.9 calls (p = .002). Retention interventions further separate state quantity, state type, and content validity. Random selection is comparable to an offline hindsight oracle, while replacing retained D-state with semantically irrelevant content increases
retrieval by 57% (p < .001) without a significant completion change. In a second environment, ALFWorld, sliding compression produces no
retrieval surge, showing that the reacquisition signature is environment-dependent rather than intrinsic to shortening context. Overall, compression can impose hidden interaction costs when execution-relevant state becomes absent and must be reacquired, while completion alone may not expose those costs.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.DC
MELD: A Protocol for Merging Knowledge Across Distributed Agentic Memories
Lauri Lovén, Jaakko Sauvola, Jukka Riekki et al. (+1 more)
Autonomous
agents share a transport and can call each other's tools, but they cannot share what they know: no protocol lets two
agents'
memories reconcile a fact phrased two ways, link related facts held apart, or reconcile contradictory knowledge without silently discarding either claim. We present MELD, a self-managing coherence mechanism for a federation of
agent memories whose run-time model is the knowledge graph itself. Each
brain admits every incoming claim through a five-outcome procedure (insert, merge, relate, conflict, or reject), decided from three signals (scoped claim-key identity,
embedding similarity, and a natural-
language-inference verdict) under context and freshness gates, and acting through exactly one auditable, authenticated Patch, the only object that mutates state. A binding onto standard publish/subscribe transport with a per-claim status CRDT keeps sovereign
brains coherent in claim status without a coordinator: self-healing after partitions and under lossy routing, and self-protecting against silent rewrite by a peer, under a benign-fault model. MELD does not adjudicate truth; a detected contradiction is preserved for later adjudication, never silently resolved. On HotpotQA distractor, distributed merge is recall-non-inferior to a centralized store under a pre-specified equivalence test and recall-superior to naive union at about 11% less live storage; the merge classifier separates at AUC 0.968 with a 0.013 false-merge rate on adjudicated candidate pairs; the status CRDT reconverges in 30/30 real partition-heal trials where last-writer-wins manages 11/30; and semantic routing delivers about 3x fewer messages at matched recall. We evaluate on a real computing continuum spanning an operator-grade 5G edge, national HPC, and a local tier, with empirically calibrated thresholds.
Read the full abstract ▾
All authors Lauri Lovén, Jaakko Sauvola, Jukka Riekki, Sasu Tarkoma
Artificial Intelligence
DriveCache: Action-Aware Caching for Driving World Model Inference
Jianchun Yang, Jian Liang, Xianda Guo et al. (+5 more)
Driving
video generation models support autonomous-driving development by predicting controllable future scenes for simulation, planning evaluation, and offline data generation.
Diffusion-based driving generators repeatedly evaluate large backbones across denoising steps, which limits generation throughput. Existing
diffusion acceleration methods reduce this cost, but general-purpose designs omit driving signals available before generation, such as ego speed and planned trajectories. Experiments across driving motions show that cache tolerance varies with ego translation and rotation, denoising progress, and consecutive reuse length. We propose DriveCache, a training-free, action-aware controller that uses planned motion to allocate reuse across scenes and dynamic programming to place it across denoising steps under a calibrated response budget. A causal drift check refreshes features and replans the remaining schedule when generation departs from calibration. Across three generator configurations, DriveCache improves the overall fidelity-efficiency trade-off over evaluated cache methods. Our code will be publicly available.
Read the full abstract ▾
All authors Jianchun Yang, Jian Liang, Xianda Guo, Pinhan Fu, Yanlun Peng, Conglang Zhang, Wenke Huang, Mang Ye
Artificial Intelligence · Cross-listed from cs.CL
HalluTracer: Pre-Decoding Truthfulness Prediction via Depth-Averaged Probe-Logit
Zhihao Guo, Zonghan Wu, Huan Huo et al. (+6 more)
Internal-state probes enable truthfulness prediction before a large
language model generates an answer. When detectors change both the layers they read and the rules used to combine them, the source of improved prediction becomes difficult to identify. We separate these choices and find that retaining more layers improves prediction even under fixed equal weighting. An exact Fisher-ratio decomposition explains why the additional benefit of linear reweighting is limited on these probe scores: information inlayer-wise differences largely overlaps with that captured by the depth mean. Estimating additional weights can then offset this small benefit when the data used to fit them are limited. These findings motivate our proposed method HalluTracer, which averages layer-wise probe logits to predict truthfulness before decoding. Across six models and four
benchmarks, including TruthfulQA, HalluTracer achieves the highest area under the receiver operating characteristic curve (AUROC) in 23 of 24 model–
benchmark pairs among the compared methods. The results support using evidence from across the network without requiring a correspondingly more flexible aggregation rule, clarifying the distinct roles of layer selection and weighting in pre-decoding detection.
Read the full abstract ▾
All authors Zhihao Guo, Zonghan Wu, Huan Huo, DaYong Ye, Junwei Zhang, Weiran Yao, Zhiwei Liu, Qingsong Wen, Yilei Shao
Artificial Intelligence
AeroCopilotBench: Safety-Gated Evaluation of LLM Agents on Aircraft Emergency Procedures in an Executable Cockpit
Yuchen Yuan, Zhenghuang Wu, Yuangan Li et al. (+2 more)
Aviation knowledge question answering cannot directly assess the operational effectiveness and safety compliance of large
language models throughout aircraft emergency procedures. We introduce AeroCopilotBench and its executable cockpit environment, ACOE, which define state-transition rules, task goals, and trajectory-level safety constraints based on aircraft-specific Pilot's Operating Handbooks (POHs). The
benchmark comprises 12 scenario templates and 73 tasks across two aircraft types, evaluating task completion, safety compliance, execution discipline, and repeatability. Across repeated evaluations of 12 models, the highest safety-gated success rate is 72.6%. Most failed episodes achieve all critical goals but do not satisfy all remaining terminal goals. Across repeated runs, models still omit steps that they execute in other runs of the same task. Analysis of failed trajectories further reveals that some reasons for actions that conflict with the aircraft's POH recur across models. These results expose shortcomings in complete procedure execution, consistency across runs, and aircraft-specific emergency response.
Read the full abstract ▾
All authors Yuchen Yuan, Zhenghuang Wu, Yuangan Li, Liang Ma, Ke Li
Artificial Intelligence · Cross-listed from cs.CV
SIGMA-Lane: Scale-pyramId Gated MAmba for Temporally Consistent Video Lane Detection
Tiancheng Zhang, Mengmeng Wang, Yan Gao et al. (+3 more)
Video lane detection requires predictions that remain stable across frames, yet severe vehicle occlusions can break temporal cues. In streaming recurrent models, corrupted observations may enter the hidden state and produce errors that persist into later frames. Existing occlusion-aware refinements usually provide obstacle masks as auxiliary inputs, so the state-update path is only indirectly protected. We propose SIGMA-Lane, which treats this failure mode as state contamination in State Space Model (SSM)-based temporal modeling. SIGMA-Lane places occlusion-aware gates on the SSM write and residual-fusion paths, controlling how current observations enter temporal
memory and are fused back after temporal propagation. After coordinate-consistent affine
alignment, the model combines two complementary paths: SSM-consistent dual-gating for temporal filtering and Structural Spatial
Retrieval (SSR) for recovering missing lane structure from aligned historical priors. Experiments on VIL-100 and OpenLane-V show improved temporal stability under heavy occlusion, with competitive F1 and mIoU scores.
Read the full abstract ▾
All authors Tiancheng Zhang, Mengmeng Wang, Yan Gao, Xiangjie Kong, Guojiang Shen, Jiaxin Du
Artificial Intelligence · Cross-listed from cs.CL
Step-Level On-Policy Distillation: Interpolating Between On-Policy Distillation and Supervised Fine-Tuning
Changhui Sun, Lanbo Liu, Hang Lei et al. (+11 more)
On-policy
distillation (OPD) aligns a student model with a teacher's logit distribution on student-generated trajectories. This approach has achieved strong empirical gains and can often surpass conventional off-policy
distillation with substantially less data. However, standard
token-level OPD can provide only fragmented corrections along an erroneous student trajectory and cannot unfold a complete and correct repair path. Motivated by this limitation, we propose Step-Level On-Policy
Distillation (SOPD), which combines the long-horizon correction of supervised fine-tuning (SFT) with the on-policy advantage of OPD to provide step-level supervision over complete student-generated trajectories. We show that, at different limits of step length, SOPD reduces to SFT or approximates OPD. Compared with SFT, the teacher responses in SOPD are conditioned on student trajectories and therefore align more closely with student-visited states; compared with OPD, SOPD provides longer-horizon corrections rather than fragmented
token-level guidance. Across both
reasoning and
agent tasks, SOPD substantially outperforms conventional SFT and OPD. For example, on ALFWorld, SOPD improves the average success rate by 13.4 points over Vanilla OPD. We hope this work offers a new perspective for future research on
distillation methods.
Read the full abstract ▾
All authors Changhui Sun, Lanbo Liu, Hang Lei, Tong Ling, Jiahang Xie, Zhiyong Zheng, Yujia Wang, Hao Liu, Feng Xiao, Lu Liu, Yanlong Du, Zifeng Cheng, Ziwei Jiang, Qing Gu