Peer Revenue Past citations are no guarantee of future returns

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science

cs Watch Computer Science (sign in to use)

Monday 17 August

Machine Learning

PertMind: Eliciting Emergent Biological Reasoning in LLM via Reinforcement Learning on Cellular Perturbation Data

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

Computation and Language

D2-ScaleAgent: Dual-Dimensional Scaling for Long Document Understanding

Multi-modal retrieval-augmented generation (RAG) is a key technique for visually rich long document understanding. Existing multi-modal RAG methods are progressively advancing toward multi-agent systems: they first retrieve relevant pages based on a query, and then iteratively understand information within those pages. However, these methods typically rely on fixed workflows and lack the ability to dynamically scale computation at test time, often leading to insufficient evidence. To address this, we propose D2-ScaleAgent, an agentic framework that introduces a dual-dimensional scaling paradigm for retrieval and reasoning. The core of D2-ScaleAgent is a Verifier agent-driven dynamic routing loop based on the intrinsic difficulty of the query, centered around a continuously updated evidence bank that serves as the agent's dynamic working memory: when retrieval needs to be expanded, the agent routes outward (retrieval scaling), decomposing the query into attributes and performing parallel page retrieval, followed by adaptive pruning to ensure comprehensive evidence coverage. When fine-grained reasoning is required, the agent routes inward (reasoning scaling), dynamically selecting sub-agents with varying granularity and count to extract evidence from pages. Finally, D2-ScaleAgent achieves logical closure over the evidence chain. Extensive experiments demonstrate that D2-ScaleAgent is effective on long and visually rich document benchmarks like MMLongBench-Doc, LongDocURL, etc.
Read the full abstract

All authors Hao Zhang, Longrong Yang, Lunhao Duan, Ziyang Wang, Qing-Guo Chen, Shanshan Zhao

Machine Learning

Evolving Executable Pipeline Programs for AutoML with Language Models

Automated machine learning (AutoML) systems search for pipelines within a space of preprocessing operators, learners, and hyper-parameters specified in advance: they can select and tune known components, but cannot produce structure outside that space. We present LACE, an AutoML framework that instead searches over complete executable pipeline programs: an evolutionary loop maintains a population of scikit-learn-compatible Python classes, and a large language model acts as the variation operator. To our knowledge, LACE is the first to formulate general tabular pipeline AutoML this way, evaluated on standardized OpenML tasks under a leakage-controlled protocol that withholds dataset identity from the generator. Because every candidate is ordinary Python, the returned pipeline and the search that produced it can be inspected and edited directly, rather than only through a framework's model objects. On 68 OpenML classification tasks, LACE with GPT-5.4-mini significantly outperforms auto-sklearn, H2O, and a fixed XGBoost baseline, with no detectable difference against AutoGluon, the strongest search-based system evaluated, while covering the full benchmark. Newer tabular foundation models are more accurate on the subset of tasks they support, but apply a fixed pretrained predictor rather than returning an editable task-specific program. LACE's contribution is therefore not raw accuracy but a search space defined by code: complete coverage, pipelines practitioners can reuse directly, and a component set extended by editing the prompt rather than the framework.
Read the full abstract

All authors Sofoklis Kitharidis, Cor J. Veenman, Jan N. van Rijn, Thomas Bäck, Niki van Stein

Systems and Control

Scalable Gaussian Process Regression via Deterministic Trigonometric Features: Uniform Bounds for Safe Model Predictive Control

Learning-based Model Predictive Control (MPC) using Gaussian processes (GPs) is an effective approach for safe control in the presence of model mismatch. High-probability safety guarantees typically require uncertainty bounds that hold uniformly over the entire state–input domain, but existing bounds are available only for full GP regression. Since exact GP inference scales poorly with the number of data points, its deployment is impractical in large-data regimes. We close this gap by developing a scalable GP framework that admits the derivation of uniform uncertainty bounds. We formalize a deterministic trigonometric feature Gaussian process (DTF-GP), a finite-dimensional kernel approximation based on discretized trigonometric features that reduces GP regression to Bayesian linear regression in feature space. We derive a high-probability uniform uncertainty bound for the proposed DTF-GP and provide its closed-form solution for the squared-exponential kernel case. Finally, we integrate the DTF-GP into a learning-based MPC scheme and demonstrate that it provides high-probability safety guarantees and exploration performance comparable to a full GP while improving computational efficiency in large-data regimes.
Read the full abstract

All authors Julius Jagdt, Johanna Menn, Sebastian Trimpe, Melanie N. Zeilinger, Anna Scampicchio

Software Engineering

Towards Risk-free AI Agent Deployment

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

Machine Learning

TRACE-CASH: Trial-History-Conditioned Reinforcement Learning for Adaptive Configuration Exploration in Time-Series CASH

Combined algorithm selection and hyperparameter optimization (CASH) searches a conditional space in which the selected model determines which hyperparameters are active. In time-series forecasting, temporal choices, chronological validation, and costly evaluations further complicate this search. Controlled comparisons of heterogeneous search methods under a shared time-series CASH (TS-CASH) evaluation protocol remain limited. Within this setting, we study TRACECASH, a task-local hybrid sequential optimizer combining grouped actor-critic candidate generation with fixed rules for model coverage, validation-guided exploitation, and exploration after stalled progress. A model actor proposes an initial forecasting model; three model-conditioned actors generate temporal, architectural, and training actions; and a modelspecific decoder constructs the configuration ultimately evaluated. We compare TRACE-CASH with six alternatives spanning random, Bayesian, evolutionary, multi-objective, and language-model-assisted search across 41 dataset-frequency task variants. TRACE-CASH has the lowest mean rank on both MASE and WQL. Descriptively, it also has the lowest window-averaged test-MASE rank in the predefined full and late windows. These results support the complete TRACECASH procedure as competitive among the evaluated methods.
Read the full abstract

Machine Learning

SoftModel: A Neural Model That Grows Its Own Topology – Governed Structural Growth for Continual In-Service Learning

Today, a neural system is almost always used in two phases – trained, then deployed – and in that regime it freezes twice: training ends, and the topology itself was never a degree of freedom. We take the opposite premise as an axiom – total plasticity: no part of a model, including its structure, is ever frozen – and derive the governance a lifelong learner then requires. The design's target regime is continual, in-service learning: a long-lived model on a non-stationary stream, whose stability comes from governance rather than immobility and whose capacity follows demand. The result is a growable soft model: an algebra of structural operators (width, hierarchy, composition, input interface, grown cycles, attention heads), each exact at application, budgeted, and audited, with adoption decided solely by a held-out reality gate that treats parametric and structural change uniformly. A complete from-scratch system realizes the whole account; its factory surface is operated end-to-end by a production LLM. Two conclusions follow from the axiom by construction: stability under lifelong change becomes an audit property of the lifecycle, and structure that follows demand removes the silent cap a fixed topology places on later capability where the capacity floor binds. A third is measured: in the worlds where this was measured, the marginal value of new capacity was unobservable before adoption, so workable growth governance took its ex-post form. The same governance extends to evaluative signals, and the core method is evaluated on standard continual-learning benchmarks, where governed growth preserves the ability to keep learning along long task sequences. A pre-registered experimental program adjudicates the mechanism and value claims on the tested problems and reports its failures at full prominence; the map – positive and negative – is the contribution.
Read the full abstract

Information Retrieval

POI Recommendation with LLM-Augmented Multi-Graph Learning and Contrastive Alignment

Point-of-interest (POI) recommendation models based on graph neural networks achieve strong performance by propagating collaborative signals over user-item interactions, yet they struggle with the cold-start problem, where items with few or no interactions are not represented. In this paper, we propose LLM-augmented Multi-Graph Contrastive Learning (LLM-MGCL), a multi-graph neural network that uses semantic and spatial information about items to extend the LightGCN backbone with two auxiliary item-item graphs: a semantic graph constructed from sentence embeddings of LLM-generated photo summaries and keywords, and a geographic graph derived from Haversine distances between business locations. Item embeddings are propagated over all three graphs in parallel, fused additively, and aligned across views through a bidirectional InfoNCE contrastive objective that connects behavioral, semantic, and spatial representations of the same items. Experiments on the Yelp Multimodal Recommendation Dataset show that LLM-MGCL outperforms classical collaborative filtering, matrix factorization, and non-contrastive graph neural network baselines. It improves Recall@20 by 48.5% and NDCG@20 by 59.0% over LightGCN, while trailing the strongest contrastive baseline, Self-supervised Graph Learning (SGL), slightly in aggregate. A popularity-stratified evaluation shows that LLM-MGCL achieves the highest recall on cold and warm items, whereas SGL remains better on popular items. An ablation study reveals that the cross-view contrastive alignment (CA) is the primary driver of the aggregate gains. Our results suggest that externally grounded, LLM-derived item knowledge can partially compensate for missing collaborative signal and mitigate the item cold-start problem in POI recommendation.
Read the full abstract

All authors Burak Tamer, Wolfram Höpken, Zehui Wang, Thomas Bayer

Logic in Computer Science

SATisfying the High School Identities but not Wilkie's Identity

We settle an open question related to Tarski's High School Algebra problem by showing that no 11-element algebra can satisfy the High School Identities while refuting Wilkie's identity. We encode the search as a SAT instance and independently verify the result. As a byproduct, we obtain a new 12-element countermodel that is not isomorphic to the previously known one.
Read the full abstract

Numerical Analysis

Convergence Analysis of Statistical Inverse Problems on Reproducing Kernel Banach Spaces

Statistical inverse problems have garnered significant attention in recent years due to the growing importance of statistical learning theory and functional analytic approaches in the fields of machine learning and artificial intelligence. In this paper, we investigate the stable approximation of the element $u^{\dagger}$ that satisfies the equation $Au = g$, where $A$ is a linear operator that maps a Banach space into an appropriate function space. The function $g$ is observed only through independently and identically distributed data points that are corrupted by noise and assumed to follow an unknown distribution $\rho$. We employ the Tikhonov regularization scheme, leveraging statistical learning techniques and the framework of reproducing kernel Banach spaces to estimate the solution. We establish convergence and derive the convergence rate of the estimated solution with respect to the true solution as the number of data points increases, with the rate expressed in probabilistic terms. The theoretical findings are further supported by numerical experiments that demonstrate the effectiveness of the proposed approach.
Read the full abstract

Cryptography and Security

Recovering Process Variables from Industrial Network Traffic via Search-Based Optimization

Process variables (PVs) provide the process evidence needed for process-aware security monitoring in industrial cyber-physical systems (CPSs). However, existing supervisory infrastructures expose only the subset of PV values recorded by historians, leaving many additional runtime PV values unobserved. To address this incomplete process visibility, we study the problem of recovering PV fields and their semantics directly from raw industrial network traffic through protocol reverse engineering (PRE). In this setting, existing PRE methods face two practical challenges: PV-carrying communication is mixed with heterogeneous runtime traffic, and PV-carrying payloads are often long and deployment-specific. Mixed runtime traffic obscures the PV-carrying communication paths, while long payloads create a vast segmentation space in which early segmentation errors can propagate and corrupt the recovery of later fields under sequential inference. In this paper, we formulate the recovery of PV fields from raw network traffic as a search-based optimization problem. Our key insight is that non-sequentially identifying correct segmentations in such a vast segmentation space can be cast as an optimization problem and addressed by searching for near-optimal solutions. We propose PVParser to approach this goal. PVParser first reduces the search space by identifying the PV-carrying payloads from network traffic via a periodic pattern detection mechanism. It then employs a modified Monte Carlo Tree Search to explore near-optimal segmentations, reducing error propagation from incorrect early boundary decisions. Experiments on three representative industrial CPS datasets demonstrate that PVParser achieves high accuracy and F1-score in PV-carrying payload localization and PV field inference, outperforming six state-of-the-art PRE approaches by a significant margin.
Read the full abstract

All authors Chuan Sheng, Shan Jiang, Jianming Zhao, Yu Yao

Artificial Intelligence

A Policy Algebra for Trust-Preserving Agentic AI Execution

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

Information Theory

Maximal correlation under cardinality constraints

In this paper, we define and analyze the quantized maximal correlation, an extension of the notion of maximal correlation restricted to functions taking values in sets of bounded cardinality. We derive an upper bound on the quantized maximal correlation by showing that the correlation between any quantized functions of $X$ and $Y$ is related to the MMSE distortion in quantization of a particular linear combination of random variables. Following this, we leverage rate-distortion techniques and anti-concentration inequalities to further bound this MMSE, which results in explicit bounds on the quantized maximal correlation. Unlike the quantized maximal correlation itself, which does not generally tensorize, our bounds on the mean squared error do tensorize, resulting in a dimension-free upper bound on the quantized maximal correlation for product distributions. Our results also lead to improved bounds on the isoperimetric constants of reversible Markov chains and product chains, strengthening classical results such as those by Alon and Milman.
Read the full abstract

All authors Dror Drach, Tomer Berg, Or Ordentlich, Ofer Shayevitz

Numerical Analysis

A weak order 2 Runge-Kutta method for Itô stochastic delay differential equations

We present a Runge-Kutta method of weak order 2 for the numerical time integration of stochastic delay differential equations. This scheme extends the class of second order Runge-Kutta methods introduced by A. Rößler in [SIAM J. Numer. Anal., 47(3):1713-1738, 2009] for stochastic ordinary differential equations. The proposed integrator is applicable to equations with discrete commensurable delays and is particularly efficient for problems involving multiple noise terms. Experimental confirmation of the weak order 2 is provided and MATLAB codes are freely available.
Read the full abstract

Artificial Intelligence

Think Inside the Chunk: RegulaRAG for Regulation-Compliant Scenario Generation using LLMs: A Case Study of UN Regulation No. 152

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

Cryptography and Security

Security Assessment of DeepSeek Harness with A.I.G: Evaluating Resistance to Indirect Prompt Injection

We assess indirect prompt injection in DeepSeek Harness (DSH), using AI-Infra-Guard (A.I.G) to construct tests, deliver controlled taint, execute DSH, collect traces, and judge outcomes. The study covers 14,560 controlled executions over 16 indirect-content channels, text and file carrier modes, 35 payload objectives, one unmodified baseline, and 12 attack methods. The experiment preserves DSH's agent loop, tool registry, model adapter, and session-event path; source tools and sensitive sinks are local fixtures, so attempted actions are recorded without external side effects. We evaluate each trace with a deterministic rule-based judge, \JudgeR{} (RuleJudge), and a semantic LLM-based judge, \JudgeL{} (LLMJudge). The strongest observed attack success rates are 17.0% under \JudgeL{} for fake-completion attack in text mode, 25.5% under \JudgeR{} for hidden Unicode in file mode, and 16.0% under \JudgeR{} for the skills channel in file mode. \JudgeL{} also assigns partial compliance more often than \JudgeR{} (7.3% versus 2.0%). We relate these results to DSH's treatment of tool results, additional contexts, and tool-call policy hooks, then identify controls that should sit between untrusted content and sensitive actions. Our code is available at https://github.com/Tencent/AI-Infra-Guard/tree/main/Research/deepseek-harness-security-assessment .
Read the full abstract

All authors Zonghao Ying, Xiangfan Wu, Huiyu Wu, Xing Zheng, Huangsheng Cheng, Xiaorong Shi, Jing Guo

Cryptography and Security

Ventor-QTest: Threat-Model-Driven Verification of Vendor-Hosted LLM APIs

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

Computation and Language

Counting Documents Is Not Counting Text: Unit Bias in Web-PDF Corpus Statistics

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

Distributed Computing

GPU implementation of a resource-constrained virtual machine

One of the main reasons compute hardware becomes obsolete is software bloat: resource requirements increase for every iteration of a software product. Resource constrained VMs are one way to combat software bloat as they post a hard limit on the resources and so force the programmer to be frugal. In this paper we explore the deployment of one such resource constrained VM, Uxn, on GPU. We show that for competitive performance it is essential to make use of the GPU data parallelism. We present an OpenMP-style parallelism API for Uxntal, the stack-based assembly-style language for the Uxn platform. We demonstrate that exemplar code using our API can run at comparable performance even on an integrated GPU. Specifically, our evaluation results show that using this approach improves performance on the compute-intensive Stencil benchmark with 19x and frame rate on the graphics-intensive Bunnymark benchmark with 7x. In practice, all laptops and desktops and even mobile devices have a GPU and our work shows that they can be used to execute frugal workloads effectively.
Read the full abstract

All authors Simone Li, Vladislav Brusokas, Andrei Ghita, Shuxuan Li, Wim Vanderbauwhede

Computation and Language

Mint-Agent: Introducing Finance-Native Agentic Foundation Models

Financial agents must do more than recall domain knowledge: they must be both reliable, executing precise operations over grounded evidence, and executive, sustaining long-horizon research whose conclusions remain auditable. We present Mint-Agent, a family of finance-native agentic models designed around these two scales of financial intelligence. Mint-Agent is built upon three pillars: data, harness, and algorithm. Our data engine constructs clean, specialized tasks for atomic financial capabilities and long-horizon agentic execution from real-world financial sources. MintHarness enables stable interaction with open-ended environments and maintains auditable evidence trails across extended research trajectories. Our training recipe combines SFT, critical-step OPD, and RLVR to develop separate financial reasoning and agentic execution experts, which are then unified through model merging and multi-teacher on-policy distillation into compact, general-purpose financial agents. This pipeline yields two flagship models, Mint-Cu (9B) and Mint-Ag (27B). Across professional financial benchmarks, our models demonstrate two defining strengths: (1) Reliability: Mint-Ag achieves 98.33% on RFC-Bench, surpassing GPT-5.6-Sol and Claude-Opus-4.8 by 3.66 and 3.00 points; and (2) Executability: Mint-Cu reaches 69.86% on FinSearchComp T2, outperforming Agents-A1-35B and Nex-N2-mini by 22.83 and 12.78 points, while Mint-Ag achieves 76.00% and 60.49% on FinanceAgentBench v1.1 and v2, respectively. These results establish a path toward trustworthy financial intelligence in which domain expertise, long-horizon execution, and auditable evidence are jointly engineered as a unified foundation for frontier agentic models.
Read the full abstract

All authors Mint-Agent Team, Kun Wang, Gavin Zhang, Yaze Geng, Lei Tang, Yaoyang Yi, Zonghan Wu, Yifan Hu, Qingsong Wen, Yilei Shao

Machine Learning

FETERS: Few-Shot Early Time-Series Classification via Effective Ratio Selection

Early time-series classification (ETSC) aims to make accurate predictions from partially observed time series as early as possible. Although various stopping mechanisms and feature learning strategies have been developed for ETSC, most existing methods assume access to sufficient labeled training data, which may be unrealistic in applications with limited annotation. Under limited supervision, learning an additional sample-level stopping module and extracting effective classification features can both become challenging. In this paper, we propose FETERS, a few-shot ETSC framework that selects a dataset-level stopping ratio through class-wise leave-one-out (LOO) evaluation on the support set and uses a penalty-based reward function to manage the accuracy-earliness trade-off, thereby avoiding the need to train an additional stopping module. FETERS further combines Rocket-based features with frozen Chronos representations for classification. Extensive experiments on 69 public datasets spanning 14 domains show that FETERS achieves state-of-the-art (SOTA) performance in the 5-shot setting, with the highest average harmonic mean (HM) and the best HM on 38 datasets, while outperforming the current SOTA method on 44 datasets. FETERS also remains competitive in the full-shot setting, demonstrating its effectiveness in managing the accuracy-earliness trade-off.
Read the full abstract

Computer Vision

Self-Routed Tensor Adapters for Parameter-Efficient Universal Visual Adaptation

Universal visual representations require adaptation mechanisms that adapt across heterogeneous domains without fragmenting knowledge into domain-specific modules. Parameter-efficient fine-tuning adapts frozen visual foundation models efficiently, but standard low-rank adapters use a fixed subspace for all inputs, which can be restrictive when domains differ in style, background, and semantic context. MoE-based adapters improve specialization through multiple expert pathways, but often rely on external routers and large expert banks, adding parameters and separating routing from adaptation. We propose Self-Routed Tensor Adapters, a compact framework for multi-domain visual adaptation. SRTA projects each input into a low-rank space, computes routing weights from this representation using a learnable domain matrix, and uses these weights to blend slices of a shared Tucker core. This produces a sample-specific adaptation matrix without an external gating network, allowing shared visual factors to be reused while supporting domain-aware specialization. To strengthen pathway learning, we introduce a progressive depth-weighted routing objective that supervises routing decisions across adapter layers. Across five heterogeneous multi-domain visual classification benchmarks, SRTA achieves competitive or slightly stronger average accuracy than MoE-style PEFT baselines while using substantially fewer trainable parameters. At rank 64, SRTA uses 2.77M parameters in the 4-domain setting compared with 9.52M for MoLoRA, and 3.00M in the 6-domain setting compared with 14.31M. Overall, SRTA offers an effective accuracy-parameter trade-off for adapting visual foundation models toward universal multi-domain representations. \href{https://github.com/surajyadav-research/SRTA}{GitHub}
Read the full abstract

Data Structures and Algorithms

Incremental Directed Minimum Cut by Dynamizing Gabow's Algorithm

We give the first incremental algorithm for directed global minimum cut. Given a directed graph with $n$ vertices undergoing $m$ edge insertions, our deterministic algorithm explicitly maintains a global minimum cut or certifies that its value is at least $k$ in $O(km\log n)$ total update time. Prior work required either that $k\le2$ or that the graph is undirected. Our algorithm is a strict incremental extension of Gabow's state-of-the-art static algorithm (JCSS 1995), with no asymptotic loss in running time over the entire insertion sequence.
Read the full abstract

Artificial Intelligence

AstronOS: A Unified Execution Model and Runtime for Long-Horizon Agentic Systems

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

Computer Vision

Synthetic Data Augmentation for Satellite-Based Analysis of Battle-Damaged Agricultural Fields in Ukraine

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

Computation and Language

Unadapted Multilingual ASR on a Garrusi Kurdish Evaluation Set: A Common-Reference Staged Normalization Analysis

Evaluating speech recognition for a Kurdish variety written in a Latin field orthography, using a model that outputs Arabic script, creates a measurement problem before a modelling one: direct scoring treats writing-system differences as recognition errors. Jointly normalizing reference and hypothesis avoids this, but also changes reference tokenization, mixing agreement gains with a change in the scoring denominator. I evaluate MMS-1B-all with the Central Kurdish (ckb) adapter, used as released without adaptation, on 1,722 Garrusi questionnaire segments from five speakers (9,763 reference word tokens; 117.9 minutes). I use a common-reference design: the reference is folded once and fixed at 9,763 tokens, while only the hypothesis representation varies. The raw Arabic-script hypothesis scores 111.70% WER and 100.92% CER, with zero exact word matches. Latin transliteration gives 102.36% WER and 57.89% CER; folding it into the reference's reduced orthography gives 97.85% and 51.20%. Thus RAW-to-FOLDED reduces measured WER by 13.85 points and CER by 49.72 points; folding alone accounts for 4.51 and 6.69 points. Substantial error remains: 14.53% of reference tokens are exact matches, edits are substitution-dominated, and per-segment WER is higher for shorter segments. A Southern Kurdish fine-tuned system (aranemini/southern-kurdish-asr), scored under the same design, performs worse on every speaker (1,703 segments), with 109.56% WER and 55.85% CER. However, 12,330 output characters fall outside the folding table, so these rates must be recomputed against the corrected fixed reference. The MMS output also contains 613 unconverted or unmapped characters, showing that part of the residual error reflects scoring-pipeline limits rather than recognition alone. I will release the fixed reference and segment-level results, subject to source-corpus sharing terms, to support independent checking.
Read the full abstract

Computer Vision

Adaptive Post-Processing Drives Instance-Level Detection in Stroke Lesion Segmentation

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

Machine Learning

Multinomial Subset Routing with Sum-Max Rewards and Operational Constraints

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

Machine Learning

OceanDepths: A Global Dataset of Paired Subsurface and Surface Ocean Observations

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

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