arXiv:2602.18481v2 Announce Type: replace-cross
Abstract: The rapid advancement of Large Language Models (LLMs) has led to a surge of financial benchmarks, evolving from static knowledge evaluation toward interactive trading simulations. However, existing frameworks for evaluating real-time trading largely overlook a critical failure mode: the severe behavioral instability of LLMs in sequential decision-making under financial uncertainty. Through extensive experiments, we show that when deployed as trading agents, LLMs exhibit extreme run-to-run variance, generate inconsistent action sequences even under deterministic decoding, and frequently produce irrational action flipping across adjacent time steps. We attribute these behaviors to the stateless autoregressive nature of LLMs, which lack persistent memory of prior actions, together with their sensitivity to continuous-to-discrete action mappings in portfolio allocation tasks. These deficiencies fundamentally undermine the reliability and reproducibility of many existing online and offline trading benchmarks. To address these limitations, we propose AlphaForgeBench, a principled evaluation framework that redefines LLMs as quantitative researchers rather than stochastic trading agents. Instead of producing discrete trading actions, AlphaForgeBench requires models to generate executable alpha factors and compose factor-based trading strategies grounded in financial knowledge. This paradigm decouples reasoning from execution mechanics, enabling deterministic and reproducible evaluation while remaining aligned with real-world quantitative research workflows. Extensive experiments across multiple state-of-the-art LLMs demonstrate that AlphaForgeBench eliminates execution-induced instability and provides a rigorous benchmark for evaluating financial reasoning, strategy formulation, and alpha discovery. Webpage at https://finbrain-lab-hkustgz.github.io/AlphaForgeBench
Science Journals
arXiv:2602.14862v2 Announce Type: replace-cross
Abstract: Temperature scaling is a simple method that allows to control the uncertainty of probabilistic models. It is mostly used in two contexts: improving the calibration of classifiers and tuning the stochasticity of large language models (LLMs). In both cases, temperature scaling is the most popular method for the job. Despite its popularity, a rigorous theoretical analysis of the properties of temperature scaling has remained elusive. We investigate here some of these properties. For classification, we show that increasing the temperature increases the uncertainty in the model in a very general sense (and in particular increases its entropy). However, for LLMs, we challenge the common claim that increasing temperature increases diversity. Furthermore, we introduce two new characterisations of temperature scaling. The first one is geometric: the tempered model is shown to be the information projection of the original model onto the set of models with a given entropy. The second characterisation clarifies the role of temperature scaling as a submodel of more general linear scalers such as matrix scaling and Dirichlet calibration: we show that temperature scaling is the only linear scaler that does not change the hard predictions of the model.
arXiv:2601.01496v2 Announce Type: replace
Abstract: In this paper, we settle the problem of learning optimal linear contracts from data in the offline setting, where agent types are drawn from an unknown distribution and the principal's goal is to design a contract that maximizes her expected utility. Specifically, our analysis shows that the simple Empirical Utility Maximization (EUM) algorithm yields an $\varepsilon$-approximation of the optimal linear contract with probability at least $1-\delta$, using just $O(\ln(1/\delta) / \varepsilon^2)$ samples. This result improves upon previously known bounds and matches a lower bound from D\"utting et al. 2025 up to constant factors, thereby proving its optimality. Furthermore, our result establishes the stronger guarantee of uniform convergence: the empirical utility of every linear contract is an $\varepsilon$-approximation of its true expectation with probability at least $1-\delta$, using the same optimal $O(\ln(1/\delta) / \varepsilon^2)$ sample complexity.
arXiv:2512.00814v3 Announce Type: replace
Abstract: Post-training has become effective for high-level generation, but its role in low-level vision remains underexplored. Existing image restoration methods often rely on fixed pixel-wise fitting to ground-truth images, which can lead to over-smoothing and weak generalization. We propose IRPO, a GRPO-based post-training framework for deterministic restoration models. IRPO is built around two axes: data formulation and reward modeling. For data formulation, we select the 30% underperforming samples from the pre-training stage, which improves both accuracy and training efficiency. For reward modeling, we combine fidelity-oriented and quality-aware feedback with three components: a General Reward for structural fidelity, an Expert Reward that uses a Vision-Language Model as a coarse visual-quality judge, and a Restoration Reward for task-specific low-level cues. Experiments on six in-domain and five out-of-domain (OOD) benchmarks show that IRPO improves the AdaIR baseline by 0.93 dB on in-domain tasks and 3.43 dB on OOD settings. Our code can be shown in https://github.com/HaoxuanXU1024/IRPO.
arXiv:2605.28405v1 Announce Type: new
Abstract: Despite widespread discussion of AGI, there is no clear framework for measuring progress toward it. This ambiguity fuels subjective claims, makes it difficult to track progress, and risks hindering responsible governance. As a starting point to address this gap, we present a framework for understanding system capabilities in relation to human cognitive abilities. Drawing from decades of research in psychology, neuroscience, and cognitive science, we introduce a Cognitive Taxonomy that deconstructs general intelligence into 10 key cognitive faculties. We then propose a rigorous evaluation protocol in which a system's performance is measured across a suite of targeted, held-out cognitive tasks, generating a 'cognitive profile' that can be used to understand a system's strengths and weaknesses. We hope this framework will provide a practical roadmap and an initial step toward more rigorous, empirical evaluation of AGI.
arXiv:2605.27449v1 Announce Type: new
Abstract: In the field of multimodal fact checking, the accuracy of retrieving evidence from different modalities has a significant impact on the downstream claim verification process. Existing general multimodal retrieval methods are often constructed based on semantics, resulting in the retrieved evidence being similar but not relevant to the claim. This paper proposes a \textbf{D}ynamic \textbf{A}daptive \textbf{C}ontrastive \textbf{L}earning method for evidence \textbf{R}etrieval called DACLR to address these issues. DACLR first uses a Multimodal Large Language Model (MLLM) to uniformly convert multimodal evidence and claims into text modalities, and extracts the features of these information at event level. Then, it conducts evidence retrieval through a two-stage retrieval method of recall-rerank. DACLR enhances the model's event perception ability of the retrieval stage by optimizing the contrastive loss and mining hard negative samples. Specifically, DACLR designs three loss functions at two levels (semantic and event) based on the InfoNCE loss.Corresponding to these, three sets of hard negative sample candidates are set up. The model dynamically adjusts the ratio based on the accuracy supervision signal of intra-batch samples, allowing the model to learn the correlation between claims and positive samples at the event level without forgetting the semantic retrieval ability. Extensive comparison and ablation experiments demonstrates the effectiveness of DACLR and its internal optimization methods. Further research also prove the advantages of DACLR in the field of multimodal evidence retrieval.
arXiv:2605.27456v1 Announce Type: new
Abstract: Geometric deep learning organises neural architectures around the symmetries of their data domain, with the choice of symmetry group serving as a geometric prior that determines what representations can be learned. Metric-Aware Principal Component Analysis (MAPCA) parameterises principal component analysis by a positive-definite metric matrix, with a canonical subfamily interpolating between standard PCA and output whitening and a diagonal-metric point recovering Invariant PCA (IPCA). This paper positions MAPCA within the geometric deep learning framework. The metric is read as the geometric prior; the orthogonal group preserving it is the symmetry group it induces; MAPCA solutions are equivariant under this group with the resulting spectrum invariant; and MAPCA's defining constraint is the linear analogue of the Schur-type weight constraints used in equivariant networks. Across six axes - domain, symmetry group, equivariance, invariance, architectural primitive, and geometric prior - we construct a precise dictionary between MAPCA and geometric deep learning. The technical anchor is a uniqueness theorem characterising IPCA as the unique linear data-derived metric in the MAPCA family that is equivariant under arbitrary diagonal rescaling and projects onto the fixed-point set of the action, equivalent under normalisation to the variance-maximisation criterion in its precise form. The paper closes with three bridges: kernel PCA as the nonlinear extension, spectral graph methods as MAPCA on graphs, and a deep MAPCA construction extending the positioning into deep equivariant networks
arXiv:2510.17620v2 Announce Type: replace
Abstract: Large language models may encode sensitive information or outdated knowledge that needs to be removed, to ensure responsible and compliant model responses. Unlearning has emerged as an efficient alternative to full retraining, aiming to remove specific knowledge while preserving overall model utility. Existing evaluations of unlearning methods focus on (1) the extent of forgetting of the target knowledge (forget set) and (2) maintaining performance on the retain set (i.e., utility). However, these evaluations overlook an important usability aspect: users may still want the model to leverage the removed information if it is re-introduced in the prompt. In a systematic evaluation of six state-of-the-art unlearning methods, we find that they consistently impair such contextual utility. To address this, we augment unlearning objectives with a plug-in term that preserves the model's ability to use forgotten knowledge when it is present in context. Extensive experiments demonstrate that our approach restores contextual utility to near original levels while still maintaining effective forgetting and retain-set utility.
arXiv:2605.27466v1 Announce Type: new
Abstract: Multi-agent systems built on large language models (LLMs) require many coordination choices that are difficult to fix a priori: which skill protocol to invoke, which agent role should perform a subtask, which model to bind to each role, how roles should interact, when to use retrieval or verification, and when to omit a step entirely. These choices interact with task regime and operational constraints, so static pipelines and one-off model comparisons provide only a limited view of the design space. This paper introduces AgensFlow, an open-source framework that treats multi-agent coordination as an online policy-learning problem under partial observability. The framework makes coordination decisions observable and learnable from repeated trajectories, rather than treating skill, role, model, topology, and evaluation choices as fixed pipeline design.
AgensFlow is evaluated on two corpora: distributed-systems incident tasks and security-advisory tasks. The evaluation shows three main results: learned routing reaches a higher-quality operating point than a fixed pipeline baseline on coordination-heavy classes; skip:X isolates topology compression as a meaningful part of the substrate; and warm-started policy graphs can reduce exploration cost while preserving plateau quality. Overall, the results support that learned, auditable routing can improve coordination-heavy multi-agent workflows over static wiring.
arXiv:2605.27475v1 Announce Type: new
Abstract: Decentralized learning enhances privacy, scalability, and fault tolerance by distributing data and computation across nodes. A popular approach is Federated learning, which relies on a central aggregator, yet faces challenges such as server vulnerabilities, scalability issues, privacy risks and most importantly, the single point of failure. Alternatively Gossip Learning and Epidemic Learning offer fully decentralization through peer-to-peer exchanges of model updates, ensuring robustness and privacy, at the price of slower model convergence. In this work, we introduce a novel decentralized learning framework called HEAL. HEAL is the first cross-layer decentralized learning framework that exploits an optimized self-organizing and self-healing underlying P2P overlay combining the strengths of Federated Learning, Gossip and Epidemic Learning. Leveraging the recently proposed Elevator algorithm, HEAL promotes dynamically chosen nodes to act as aggregators. Through simulations, we demonstrate that HEAL has similar performances to that of Federated Learning in crash-free settings, while being fully decentralized and fault-tolerant. In crash and churn prone environments HEAL outperforms Gossip and Epidemic Learning.
arXiv:2509.23019v5 Announce Type: replace
Abstract: Watermarking offers a promising solution for detecting LLM-generated content, yet its robustness under realistic query-free (black-box) evasion remains an open challenge. Existing query-free attacks often achieve limited success or severely distort semantic meaning. We bridge this gap by theoretically analyzing rewriting-based evasion, demonstrating that reducing the average conditional probability of sampling green tokens by a small margin causes the detection probability to decay exponentially. Guided by this insight, we propose the \emph{Bias-Inversion Rewriting Attack} (BIRA), a practical query-free method that applies a negative logit bias to a proxy suppression set identified via token surprisal. Empirically, BIRA achieves state-of-the-art evasion rates ($>99\%$) across diverse watermarking schemes while preserving semantic fidelity substantially better than prior baselines. Our findings reveal a fundamental vulnerability in current watermarking methods and highlight the need for rigorous stress tests. Our code is available at \href{https://github.com/ml-postech/LLM-Watermark-Evasion-via-Bias-Inversion}{here}.
arXiv:2605.28290v1 Announce Type: new
Abstract: We study bandit learning in matching markets, where players and arms constitute the two market sides, and the players' utilities are linear in the arm contexts. In each round, new arms arrive with observable contexts. Then, the algorithm matches them to players, aiming to minimize each player's regret against a stable matching benchmark. This contextual structure creates significant complexity: subtle context shifts can slightly alter one player's utility while completely reconfiguring the underlying benchmark, causing large regret spikes for others. We address this in two settings: stochastic contexts, drawn from a latent distribution, and adversarial contexts, which may be arbitrary. For the stochastic case, we introduce a novel minimum preference gap to capture learning difficulty and provide a fully adaptive algorithm with an instance-dependent poly-logarithmic regret upper bound. We also establish matching instance-independent regret upper and lower bounds under a mild distributional assumption. For the adversarial setting, we propose a tractable regret notion that remains valid under arbitrary contexts and achieves an instance-independent sublinear regret bound via an adaptive algorithm.
arXiv:2604.08059v5 Announce Type: replace
Abstract: Software systems built from versioned AI components increasingly need lifecycle-time governance: when a capability module evolves into a new version, the hosting system must decide whether the new version may be activated safely, under what deployment conditions it should run, how it must be monitored, and when it should be rolled back. Existing software-deployment patterns (canary release, blue-green, feature flags, and MLOps pipelines) address parts of this loop but were designed for stateless web services rather than for stateful, policy-constrained runtimes that drive AI components in the field. We formulate governed capability evolution as a first-class software-lifecycle problem for AI-component-based systems and propose a staged upgrade framework in which every new capability version is treated as a governed deployment candidate rather than an immediately executable replacement. The framework introduces four upgrade compatibility checks (interface, policy, behavioral, recovery) and organizes them into a seven-stage pipeline (candidate validation, sandbox evaluation, shadow deployment, gated activation, online monitoring, rollback, audit). We implement a reference prototype on a PyBullet manipulation testbed with ROS 2 middleware and evaluate it over 6 rounds of capability upgrade with 15 random seeds. Naive upgrade achieves 72.9% task success but drives unsafe activation to 60% by the final round; governed upgrade retains comparable success (67.4%) while maintaining zero unsafe activations across all rounds (Wilcoxon p=0.003). Shadow deployment reveals 40% of upgrade regressions invisible to sandbox evaluation alone, and rollback succeeds in 79.8% of post-activation drift scenarios.
arXiv:2604.13018v2 Announce Type: replace
Abstract: Agentic systems increasingly automate pieces of AI research. Yet turning underspecified research objectives into runnable, experimentally validated ML systems remains a central bottleneck. We study this operational setting as \emph{long-horizon ML research engineering}: converting a research specification into a runnable ML system through repeated implementation, experimentation, and refinement. The central challenge is to sustain cumulative project progress across heterogeneous stages under delayed, confounded feedback. We introduce AiScientist, a multi-agent system built around thin control over thick state: a lightweight hierarchical research team coordinates through a File-as-Bus workspace that preserves decision-relevant artifacts across roles and invocations. On PaperBench, AiScientist improves over the strongest matched baselines by 9.92 and 11.15 points with Gemini-3-Flash and GLM-5, respectively. On MLE-Bench Lite, it reaches 81.82 Any Medal\% under both backbones, improving over the strongest matched baselines by 4.55 and 16.67 points, and exceeding a Codex/GPT-5.5 xhigh frontier harness reference by 13.64 Any Medal points. Ablations and process analyses show that durable project state is central to later-round refinement: removing File-as-Bus lowers PaperBench score by 6.41 points and MLE-Bench Lite Any Medal\% by 31.82 points. These results suggest that long-horizon AI research is not only a problem of stronger local reasoning, but a systems problem of maintaining cumulative, inspectable project progress.
arXiv:2605.05248v4 Announce Type: replace
Abstract: AI systems increasingly synthesize executable structure at runtime: LLMs generate programs, agents construct workflows,self-improving systems modify their own behavior. In classical homoiconic and staged languages, the transition from code representation to execution is unrestricted. eval is a language primitive, not a governed operation. We argue that in governed intelligent systems, this transition is an authority amplification: it converts symbolic structure into executable authority and must be mediated like any other effect. We present governed metaprogramming, a language design where program representations (machine forms) are first-class values, form manipulation is pure computation, and materialization (the transition from form to executable machine) is a governed effect subject to structural inspection. The governance system analyzes the proposed program's capability requirements, policy compliance, and resource estimates before permitting execution. We formalize two judgments: pure form evaluation (which emits no directives) and governed materialization (which emits exactly one governed directive). We prove three properties: purity of form manipulation, the no-bypass theorem, and boundary preservation. We implement the design in mashinTalk, a DSL for AI workflows compiling to BEAM byte code, and report on integration with 454 existing machine-checked Rocq theorems. The central contribution is reclassifying eval from a language primitive into a governed effect.
arXiv:2605.23327v2 Announce Type: replace
Abstract: Lane detection stands as a crucial perception task in autonomous driving and advanced driver assistance systems. However, existing methods still degrade in complex real scenarios due to two major limitations. First, classification confidence only characterizes the categorical existence of lane priors and has no strong correlation with geometric quality. If threshold filtering and NMS are conducted merely based on this confidence, the model tends to retain lane priors with high confidence while eliminating those with lower confidence but superior geometric representation. Secondly, the regression modules in existing methods weaken correlations among sampling points, hindering fine-grained optimization of distant, high-curvature and complex-topology lanes and causing underfitting. To address these issues, we propose Geometric Fidelity and Spatial Refinement (GFSR), a framework consisting of LaneIoU-guided Confidence Calibration (LCC) and Adaptive Gated Location Refinement (AGLR). Specifically, LCC adopts LaneIoU as soft supervision to explicitly estimate the geometric fidelity of lane priors, which is further fused with classification confidence to construct the Collaborative Reliability Index (CRI). This index guides lane prior filtering, effectively retaining those with high classification confidence and favorable geometric quality. Meanwhile, cooperating with regression heads in each refinement stage, AGLR predicts sampling point lateral offsets and adopts a gating mechanism to adaptively regulate correction magnitude, strengthen inter-point correlations and boost model adaptability as well as robustness toward complex lane scenarios. Extensive experiments on CULane and CurveLanes demonstrate that our GFSR achieves state-of-the-art performance on CULane, with F1_50 and F1_75 scores of 81.46% and 65.01%, and reaches 87.35% F1_50 on CurveLanes.
arXiv:2604.06550v2 Announce Type: replace
Abstract: OpenClaw's ClawHub marketplace hosts tens of thousands of community-contributed agent skills (49,592 in our 2026-04-04 snapshot), and recent audits report that 13-26% contain security vulnerabilities. Regex scanners miss obfuscated payloads; formal static analyzers cannot read the natural-language SKILL.md instructions that hide prompt injection and social engineering. Neither approach covers both modalities.
SkillSieve is a three-layer detection framework that applies deeper analysis only where needed. Layer 1 runs regex, AST, and metadata checks through a recall-tuned heuristic scorer, filtering 86% of the volume. Layer 2 routes suspicious skills to an LLM, splitting the analysis into four parallel sub-tasks with structured outputs. Layer 3 puts high-risk skills before a jury of three LLMs that vote independently and debate when they disagree.
We evaluate on 49,592 real ClawHub skills and adversarial samples across five evasion techniques, running the pipeline on a 440 USD ARM single-board computer. On a 390-skill labeled benchmark, SkillSieve achieves F1 = 0.920 (precision 0.912, recall 0.929) at 0.006 USD per skill. An optional XGBoost fast-path cuts 32% of Layer-2/3 LLM calls with a 1.6-point F1 reduction, while preserving full-pipeline recall (0.929). For cross-ecosystem generalization, we adapt the framework to Feishu/Lark and scan 52 real packages, where Layer 2 corrects Layer 1 false positives from domain-specific idioms, suggesting a low-cost adaptation path to similar enterprise platforms. We deploy SkillSieve as a Feishu chat bot for real-time skill vetting. Code, data, and benchmark are open-sourced.
arXiv:2604.07028v2 Announce Type: replace
Abstract: Strategic interaction in adversarial domains such as law, diplomacy, and negotiation is mediated by language, yet most game-theoretic models abstract away the mechanisms of persuasion that operate through discourse. We present the Strategic Courtroom Framework, a multi-agent simulation environment in which prosecution and defense teams composed of trait-conditioned Large Language Model (LLM) agents engage in iterative, round-based legal argumentation. Agents are instantiated using nine interpretable traits organized into four archetypes, enabling systematic control over rhetorical style and strategic orientation.
We evaluate the framework across 10 synthetic legal cases and 84 three-trait team configurations, totaling over 7{,}000 simulated trials using DeepSeek-R1 and Gemini~2.5~Pro. Our results show that heterogeneous teams with complementary traits consistently outperform homogeneous configurations, that moderate interaction depth yields more stable verdicts, and that certain traits (notably quantitative and charismatic) contribute disproportionately to persuasive success. We further introduce a reinforcement-learning-based Trait Orchestrator that dynamically generates defense traits conditioned on the case and opposing team, discovering strategies that outperform static, human-designed trait combinations.
Together, these findings demonstrate how language can be treated as a first-class strategic action space and provide a foundation for building autonomous agents capable of adaptive persuasion in multi-agent environments.
arXiv:2604.07190v2 Announce Type: replace
Abstract: We present a comprehensive adoption snapshot of the leading open language models and who is building them, focusing on the ~1.5K mainline open models from the likes of Alibaba's Qwen, DeepSeek, Meta's Llama, that are the foundation of an ecosystem crucial to researchers, entrepreneurs, and policy advisors. We document a clear trend where Chinese models overtook their counterparts built in the U.S. in the summer of 2025 and subsequently widened the gap over their western counterparts. We study a mix of Hugging Face downloads and model derivatives, inference market share, performance metrics and more to make a comprehensive picture of the ecosystem.
arXiv:2510.17790v3 Announce Type: replace
Abstract: Computer-use agents face a fundamental limitation. They rely exclusively on primitive GUI actions (click, type, scroll), creating brittle execution chains prone to cascading failures. While API-driven agents harness rich capabilities through structured interfaces and tools, computer-use agents remain constrained to low-level visual interactions. We present UltraCUA, a foundation model that transcends this limitation through hybrid action-seamlessly unifying primitive GUI operations with high-level tool execution. Our innovation rests on four critical advances. First, an automated pipeline extracts and scales tool capabilities from software documentation and code repositories. Second, a synthetic data engine produces 17,000+ verifiable tasks capturing real-world computer-use complexity. Third, comprehensive hybrid action trajectory collection incorporates both GUI primitives and strategic tool calls. Fourth, a two-stage training methodology combines supervised fine-tuning with online reinforcement learning, enabling intelligent action selection between GUI and API. Evaluation with our 7B and 32B UltraCUA models reveals transformative performance gains. On OSWorld, UltraCUA achieves 22% relative improvement while executing 11% faster than existing approaches, averagely. Cross-domain validation on WindowsAgentArena demonstrates robust generalization with 21.7% success rate, surpassing Windows-trained baselines. The hybrid action paradigm proves essential, reducing error propagation while improving execution efficiency. This work establishes a scalable paradigm bridging primitive GUI interactions and high-level tool intelligence, enabling more resilient and adaptable computer use agents for diverse environments and complex real-world tasks.
arXiv:2605.26954v1 Announce Type: new
Abstract: Safety evaluation of Large Language Models (LLMs) has largely focused on high-resource languages, leaving low-resource languages critically underserved. We present AlbanianLLMSafety, the first publicly available safety evaluation dataset for LLMs in Albanian, a linguistically distinct low-resource language with approximately 7.5 million speakers across Albania, Kosovo, North Macedonia, and the diaspora. The dataset contains 2,951 prompts spanning 11 safety categories, including self-harm, violence, racist content, child exploitation, and radicalization, with an average of 268 prompts per category. Each prompt is provided in Albanian with an English reference translation and a detailed category label. This resource addresses a significant gap in safety evaluation infrastruc-ture for low-resource languages and provides an essential benchmark for developing safer, more inclusive LLMs. The dataset will be provided upon request to support safety evaluation, fine-tuning, red-teaming, and guardrail development for Albanian-speaking communities.
arXiv:2605.27021v1 Announce Type: new
Abstract: This paper studies how to balance onboard and ground computation under intermittent LEO connectivity for optimized inference freshness. As connectivity varies in time, the system switches among the actions of onboard computation, cached semantic transmission, raw-data offloading, and waiting. We define Age of Inference (AoInf) as the performance metric, where the age resets only upon successful task-valid updates. We formulate long-run average AoInf minimization as a finite-state average-cost semi-Markov decision process whose state captures the ground AoInf, orbital contact phase, cache occupancy, and cache age. We then transform the SMDP into an equivalent average-cost MDP and compute the solution via normalized relative value iteration (RVI). Numerical results indicate that the resulting hybrid policy reduces average AoInf relative to onboard-only and offload-only baselines, while requiring less computational resources on the satellite than the former, and fewer communication resources than the latter.
arXiv:2605.26123v1 Announce Type: new
Abstract: The operational reliability of a high performance marine vessel depends critically on the health of its marine propulsion systems, which are increasingly subjected to diverse operational loads and environmental stressors. This paper proposes a robust mathematical framework for non-linear state-space forecasting of marine engine parameters using adaptive-window multi-particle stochastic differential equations. Traditional time-series models such as Vector Autoregressive Integrated Moving Average, often fail to capture the inherent stochasticity and transient dynamics of complex systems due to their reliance on fixed-window linear assumptions. To address this, we develop a dual-layered estimation approach: first, an adaptive lookback mechanism dynamically adjusts the learning window size based on the instantaneous drift magnitude, ensuring responsiveness during non-stationary regimes. Second, a Multi-Particle ensemble is evolved via Euler-Maruyama discretization, where each particle trajectory represents a stochastic realization of the system state. To refine the ensemble mean and mitigate the "noise-chasing" behavior of raw estimators, a Girsanov transform induced change of probability measure is implemented, assigning higher probabilistic weights to particles that align with the physical drift. Theoretical evaluation and empirical benchmarking demonstrate that the proposed adaptive SDE framework significantly outperforms classical statistical baselines in multi-step prediction stability and computational efficiency. The model provides a scalable, "grey-box" solution for real-time risk quantification in systems characterized by high-frequency volatility and non-linear transitions.
arXiv:2605.27066v1 Announce Type: new
Abstract: Understanding how events evolve over time is essential for search engines handling queries about trending news. We present QDET (Query-Driven Event Timeline Summarization), a production system deployed on Baidu Search that constructs focused event timelines to explain specific query events. Unlike traditional topic-centric approaches that aim for comprehensive coverage, QDET identifies and organizes sub-events closely relevant to the query from noisy candidate sets formed by millions of documents retrieved daily. QDET incorporates two key innovations: (1) multi-task supervised fine-tuning with three auxiliary tasks-temporal ordering, causal judgment, and timeline completion-that enable compact models to match the performance of much larger general-purpose models in specialized domains; (2) reinforcement learning-based event concise summarization that enforces strict length constraints while maintaining semantic quality, achieving 88.2% length compliance and outperforming 671B-scale models by 7.7 points in constraint satisfaction. Our fine-tuned 7B parameter model achieves 76.2% F1 score on timeline summarization, slightly surpassing the zero-shot performance of DeepSeek-R1-671B (76.1% F1) while using only 1% of its parameters-demonstrating that domain-specific optimization enables production-ready models with comparable quality at drastically reduced computational costs. Online A/B tests on Baidu Search validate real-world effectiveness, showing 5.5% CTR improvement, 4.6% longer dwell time, and 4.4% deeper exploration compared to single-task baselines. We further demonstrate that timeline understanding transfers to heat prediction, confirming effective knowledge transfer to downstream tasks.
arXiv:2605.26533v1 Announce Type: new
Abstract: Automated industrial inspection requires both precise defect localization and structured maintenance report generation; in current practice these tasks are handled separately, with linguistic interpretation left to human experts. This paper describes a decoupled, edge-deployable pipeline for wind turbine blade inspection built from three components that each handle a distinct sub-task. The Eyes a YOLO26-x-obb oriented bounding-box detector localizes defects at dataset-native resolution. The Bridge a deterministic, parameter-free encoding module maps each detected bounding box to grid-referenced spatial tokens embedded in a structured prompt. The Brain a 4-bit quantized Qwen-2.5-1.5B model adapted with Quantized Low-Rank Adaptation (QLoRA) on 947 synthetically generated maintenance reports generates a structured JSON report from that prompt. Retrieval-Augmented Fine-Tuning (RAFT) further grounds each recommendation in indexed maintenance procedures. Five ablation experiments, scored by BLEU-4, ROUGE-L, Hallucination Rate (HR), and an LLM-as-a-Judge rubric, compare the pipeline against a monolithic vision-language model (VLM) baseline and against partial configurations in which one component is removed. The complete system achieves BLEU-4 0.41, HR=4%, and Expert Score = 8.6/10 compared with 0.07, 65%, and 3.3/10 for the zero-shot VLM baseline. The QLoRA-adapted 1.5B model generates higher-quality reports than a 671B-parameter generalist API model given identical detection evidence, at 47 tokens per second on a single T4-class GPU. The results show that purpose-built decoupled architecture with a small domain-specific training corpus outperforms a generalist end-to-end model on this structured generation task.