Artificial Intelligence · Cross-listed from cs.CV
Deep Learning based Detection of Fishing Vessels and Fishing Monitoring using Nightlight Images
Shantakar Mohanty, Prasun Kumar Gupta and Raian Vargas Maretto
The demand for maritime surveillance has given rise to the need for monitoring fishing vessel activities, particularly in addressing the challenge of "dark vessels" that operate without Automatic Identification System (AIS) transmission. This study presents a novel approach for detecting small-scale fishing vessels using nighttime light (NTL) imagery from the SDGSAT-1 satellite, combined with deep learning techniques to enhance fishing monitoring awareness along the western coast of India. A dual-branch YOLO11 architecture was developed to exploit both the 10-meter panchromatic and 40-meter RGB imagery from SDGSAT-1. The custom model architecture was specifically optimized for small object detection in NTL imagery, featuring parallel convolutional backbones that process both modalities before concatenation for enhanced feature extraction. The dual-branch YOLO11 model demonstrated optimal performance with a precision of 0.99, recall of 0.93, F1-score of 0.96, and mAP@50 of 0.96, significantly outperforming single-branch implementations of YOLOv5s, YOLOv8s, and standard YOLO11s architectures. When applied to the western coast of India, the model detected 31525 vessel instances across the temporal
dataset spanning 2022-23. Cross-matching analysis with AIS data revealed that only 7146 (22.7%) of detected vessels had corresponding AIS transmissions, while 24379 (77.3%) were identified as potential dark vessels. Spatio-temporal analysis showed peak fishing activity during January-April, with a primary activity corridor parallel to the coastline within 50-100 km, corresponding to productive continental shelf areas. This research contributes to maritime surveillance capabilities by highlighting the effectiveness of nighttime lights satellite imagery for fishing vessel detection and provides valuable insights into fishing patterns and potential regulatory compliance issues in Indian waters.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Test-Time Augmentation for LLMs: Where to Inject Diversity at Inference Time
Nikita Kozodoi, Zainab Afolabi and Jack Butler
Aggregating several LLM responses to the same question can improve accuracy, but every method that does so must decide where the responses should differ. Established test-time scaling methods such as self-consistency vary only the
reasoning path, resampling from a fixed input. The input modification offers several further options: the wording of the question can be rephrased, the spelling can be perturbed, and the accompanying images can be transformed. We study Test-Time Augmentation (TTA), which aggregates predictions across transformed versions of the input, and use it to ask where diversity is best injected. Comparing these options across six
benchmarks at a matched number of inference calls, we find that where the diversity comes from matters more than how much of it there is. Meaning-preserving paraphrases of the input yield the largest accuracy gains (+1.80 pp over a single call) and reach peak accuracy with the fewest samples. Yet, they are not the most diverse: character-level noise makes the responses disagree far more often (37.8% versus 27.4%) while gaining less accuracy, and perturbing two modalities at once falls below the single-call baseline. Not all diversity is equally useful: perturbations that keep the meaning intact produce disagreement that aggregation can use, while those that corrupt it produce disagreement that is wrong. Overall, our results suggest that for mid-tier LLMs such as Claude Haiku, varying how a question is phrased is a better use of an inference call than varying the
reasoning path. Our TTA implementation is available at github.com/aws-samples/sample-genai-reflection-for-bedrock.
Read the full abstract ▾
Artificial Intelligence
LLM-Guided Heuristic Design from Simulation Traces: A Case Study in Dynamic Production and AGV Scheduling
Jinbo Li and Chuanhao Li
Simulation-based optimization (SBO) evaluates executable policies under
stochastic dynamics, but most methods treat the simulator as a black box: aggregate scores rank candidates without revealing why they fail or which policy logic should change. We present an LLM-guided heuristic design framework that uses repeated simulation for selection and event-level traces for diagnosis. Each incumbent is assessed through multiple replications, while replaying its lowest-scoring one produces a queryable trace. A manager
agent formulates bottleneck hypotheses from this evidence, and editing
agents implement parallel code-level revisions. After execution checks and repeated evaluation, best-so-far selection retains only improvements. LLM revision occurs between evaluation batches, while a fixed policy controls each simulation run. We evaluate the framework in a discrete-event simulation of dynamic production and automated guided vehicle (AGV) scheduling. Across five independent optimization runs with Gemini-3.1-Pro, final mean scores averaged 77.51 on the simulator's 0-100 scale. In the highest-scoring run, trace-based diagnoses motivated proactive charging, distance-aware AGV assignment, and rebalanced dispatch priorities, raising the best-so-far mean score from 62.49 to 78.61. On 100 matched seeds, the best final policy outscored representative rolling-MILP, rule-based, and metaheuristic policies on every seed and retained its advantage under random faults without re-optimization. After separate re-optimization for a longer horizon and variable order interarrival times, the resulting policies again outscored all baselines. Ablations with two LLM backbones showed that removing either parallel candidate generation or trace-database access reduced final mean scores. These results show that simulation traces can guide targeted code-level policy improvement in complex simulation-based scheduling.
Read the full abstract ▾
Artificial Intelligence
Control-Oriented Scenario Tree Construction through Reinforcement Learning
Fabio Pavirani, Bert Claessens, Pierre Pinson et al. (+1 more)
Multistage
stochastic model predictive control (MPC) handles uncertainty by optimizing over a scenario tree, a finite branching approximation of future outcomes constructed from sampled forecasts. To build such a tree, conventional methods focus on matching the underlying probability distribution—e.g., via Wasserstein-based scenario reduction—but improved distributional accuracy does not necessarily yield better control performance. We propose a control-oriented approach that learns scenario tree construction directly from its impact on downstream decisions. Fixing the tree
topology, we formulate tree construction as a sequential assignment of sampled scenarios to leaves. This assignment is parameterized by an
attention-based policy over the scenario set and trained using reinforcement learning, with closed-loop control profit as the objective. Training is stabilized by an asymmetric critic that leverages realized future trajectories. We evaluate the method on a risk-averse battery arbitrage problem. Across a range of forecast set sizes, the learned construction consistently achieves the highest profit, outperforming classical forward and backward reduction methods and certainty-equivalent (single-trajectory forecast) control. The learned policy also exhibits greater robustness on challenging instances, consistently demonstrating better tail-risk characteristics. Analysis of the resulting trees indicates that our method constructs compact, selectively branching structures that capture high-impact events while keeping most trajectories nearly deterministic. These findings highlight that the value of a scenario tree depends critically on the decisions it supports, and provide an effective framework to train scenario tree constructors merely based on the closed-loop control optimization signal.
Read the full abstract ▾
All authors Fabio Pavirani, Bert Claessens, Pierre Pinson, Chris Develder
Artificial Intelligence · Cross-listed from cs.SD
RAG-Audio: Retrieval-Augmented Generation for Faithful Brain-to-Audio Reconstruction
Ambuj Mehrish and Sebastiano Vascon
Brain-to-audio reconstruction is limited by prior domination: when a pretrained generator is conditioned on a weak neural signal, it produces realistic but stimulus-inaccurate audio. We introduce RAG-Audio, which decodes fMRI into a semantic audio
embedding, retrieves a matching real-audio exemplar, and initializes the frozen generator's sampling trajectory from that exemplar while retaining the decoded
embedding as conditioning. On
Brain2Music, RAG-Audio improves 10-way stimulus identification from $0.14$–$0.18$ for direct generation, near the $0.10$ chance level, to $0.40$–$0.43$, comparable to
retrieval. It also reduces Fréchet Audio Distance by roughly an order of magnitude, from $13.49$ to $1.25$ for AudioLDM. RAG-Audio approaches nearest-neighbor
retrieval in identification while remaining generative; its higher FAD is expected because
retrieval directly replays real audio. An autoregressive negative control, which lacks an initializable latent trajectory, shows no comparable gain, attributing the improvement to trajectory initialization. These results suggest that
retrieval-guided initialization can mitigate prior domination in
brain-to-audio generation.
Read the full abstract ▾
Artificial Intelligence
GeoPhysAdapter: Scale-Matched Geophysical Adaptation for Cross-Domain Landslide Mapping with Vision Foundation Models
Zhihang Liu, Mei-Po Kwan, Jinlin Wu et al. (+1 more)
Newly triggered landslides rarely carry immediate annotations, so cross-domain transferability determines the value of landslide mapping for emergency response and regional risk assessment.
Vision foundation models have strengthened representational transfer, yet on unseen regions, events, and data sources they still generate high-confidence false alarms. Terrain, material, and rainfall triggering can constrain such errors, but their supports are local, regional, and event-scale, so that resampling onto a 10~m grid misaligns them with the
segmentation decision unit and compounds the uncertain geographic context problem (UGCoP). We propose GeoPhysAdapter, which anchors on a frozen
vision foundation model, restricts terrain, material, and triggering to dense spatial guidance, regional modulation, and event-timing forcing, and applies bounded adaptation at two decision units, the pixel and the candidate landslide body, reverting exactly to the visual prediction where support is insufficient. On an event-isolated PILD
dataset of four public sources, 55 global landslide events, and 7,890 test samples, 70.3% of cross-domain false-positive mass lies in near-pure spurious bodies of median equivalent diameter 207m, matching coarse-prior support rather than the pixel. Pixel-level adaptation removes a net 507,817 erroneous pixels and reduces error by 7.76%, whereas raising the decision unit to the candidate body, under identical samples, anchor, and baseline, increases error reduction to 23.99%, approximately 3.1 times the pixel-level effect, improves IoU by 0.031 (14.2% relative), and corrects 9.92 pixels per pixel harmed. The data and code are publicly available at: https://github.com/Liu-Zhihang/geophysadapter.
Read the full abstract ▾
All authors Zhihang Liu, Mei-Po Kwan, Jinlin Wu, Hao Li
Artificial Intelligence
CoRE: Consensus Rewards via Equilibrium for Test-Time Reinforcement Learning
Ambuj Mehrish and Sebastiano Vascon
On unlabeled test data, reinforcement learning lacks a ground-truth reward; test-time RL methods derive one from the model's own roll-outs, rewarding those that match the majority vote over $N$ sampled answers. That vote discards a correct answer whenever it is a minority and scores every majority-matching roll-out identically. We replace it with CoRE (Consensus Rewards via
Equilibrium): the $N$ roll-outs form a graph whose edges combine answer agreement,
reasoning similarity, and generation confidence, and replicator dynamics extract its dominant set, yielding a refined pseudo-label, a graded per-roll-out reward, and a per-question cohesiveness gate. CoRE strictly generalizes voting: majority voting is recovered as a special case; a block-value analysis gives a sharp threshold for when consensus recovers a correct minority against a larger wrong plurality; and confidence calibration provably lowers that threshold multiplicatively. Across seven backbones and five
benchmarks (42 model–
benchmark cells, three seeds each), CoRE improves the untrained base by $+21.7$ points on average versus $+20.4$ for majority-vote TTRL, wins wherever agreement is contestable with margins over the vote of up to $+7.5$ points, and reaches the voting baseline's plateau accuracy in $54$–$70$% fewer steps. Consensus, not counting: treating the roll-out group as a graph rather than a ballot box turns a brittle vote into a calibrated, graded, self-supervised reward at no extra roll-out cost.
Read the full abstract ▾
Artificial Intelligence
ASPaeroFlow: Decomposition Heuristics for Joint Air Traffic Flow & Capacity Management
Alexander Beiser, Markus Hecher, Nysret Musliu et al. (+2 more)
While mathematical models act as vital decision support systems for operational Air Traffic Flow and Capacity Management (ATFCM), existing approaches isolate Air Traffic Flow Management (ATFM) from Dynamic Airspace Configuration (DAC). This separation introduces an unresolved circular dependency between fixed-demand and fixed-capacity assumptions. Although joint optimization resolves this gap, the enlarged search space renders exact models computationally intractable for medium- to large-scale instances. To bridge this gap, we propose ASPaeroFlow: a heuristic for the joint ATFCM; it combines instance-space decomposition heuristics with a local exact approach using Answer Set Programming. We
benchmark ASPaeroFlow from small to industry-sized instances and compare it with exact and alternative approaches. The results indicate that (1) the heuristic provides a computational middle ground between exact methods and operational baselines; (2) simultaneous optimization can outperform sequential optimization on joint ATFCM; and (3) an ablation study indicates that DAC has a larger impact on solution quality than flow measures.
Read the full abstract ▾
All authors Alexander Beiser, Markus Hecher, Nysret Musliu, Georg Trausmuth, Stefan Woltran
Artificial Intelligence
Linearized 2-Simplicial Attention
Aritra Das, Dhruman Gupta and Debayan Gupta
We present a linearized form of 2-simplicial
attention by rewriting the trilinear score as an inner product between a composite query and a key, so that the sum over one
token axis takes the same form as ordinary softmax
attention. We then approximate this sum with positive random features and store the entire past in a fixed-size state, while the second axis stays explicit over a short window of recent
tokens. This enables us to achieve linear cost in sequence length combined with a global reach that windowed 2-simplicial
attention lacks. We implement it with custom Triton kernels and combine it with Kimi Delta
Attention to build a model with no softmax
attention at all. Under matched compute, this model achieves the highest mean downstream accuracy among the compared architectures, and at 16k context it improves mean accuracy over a KDA hybrid while lowering LAMBADA perplexity from 715.6 to 602.6.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.RO
WorldSimProbe: Diagnosing Simulator Faithfulness in Action-Conditioned World Models for Embodied Manipulation
Peterson Co, Sicheng Hu, Chunxuan Jiao et al. (+17 more)
Action-conditioned world models (ACWMs) promise to provide
embodied AI with scalable predictive simulators for planning, policy evaluation, and data generation. Realizing this promise requires precise action-conditioned transitions rather than merely plausible outputs. Yet their applicability remains difficult to establish because prevailing evaluations emphasize visual quality, task outcomes, or coarse rollout-level responsiveness without directly testing simulator fidelity. To address this gap, we evaluate ACWMs through the observable capabilities expected of physical simulators. Accordingly, we formalize Observable Simulator Contract, a minimal contract that any action-conditioned physical simulator should satisfy: supplied actions must induce corresponding
agent motion, and environment responses must be grounded in that realized motion. To operationalize this contract, we introduce WorldSimProbe, comprising five controlled suites spanning local control sensitivity, global trajectory variation, source-diverse actions, interaction grounding, and dynamics. Suite-specific evaluators assess simulator-relative calibration, dense action-to-motion correspondence, false-interaction grounding, and primitive-level dynamics. We evaluate six open-source ACWMs on more than 18,000 instances across RoboTwin, ManiSkill, and LIBERO. World-SimProbe reveals systematic action-realization degradation across control variation, structured failures in interaction grounding and dynamics, and
benchmark signals consistent with human judgments and downstream outcomes. Together, this capability-based framework provides a transparent, and standardized paradigm for diagnosing ACWM simulator fidelity beyond coarse, task-directed evaluation.
Read the full abstract ▾
All authors Peterson Co, Sicheng Hu, Chunxuan Jiao, Hongyang Cheng, Yulin Luo, Yijie Xu, Sixiang Chen, Zhongxia Zhao, Zihao Wang, DaFeng Chi, Peidong Liu, YuTong Chen, Henghua Liu, Zhihao Yuan, Huizhu Jia, Yuzheng Zhuang, Tianle Zhang, Liang Lin, Huajie Tan, Shanghang Zhang
Artificial Intelligence
CADEngBench: It Looks Like CAD, but Does It Work? Evaluating Parametric Design, Assembly Reasoning, and Physics Simulation
Harmanjot Singh, Abhra Dubey and Jorge Alejandro Amador Herrera
A CAD model is not engineering-grade merely because it looks correct. It must satisfy design requirements, respond predictably to parameter changes, support controlled edits, match a reference structural response under a declared analysis, and connect to other parts through valid joints. We present CADEngBench, a two-track
benchmark for these capabilities. CADEngBench-P evaluates 300 parametric parts, each used for one zero-to-CAD task and one functional-editing task (600 tasks in total), through boundary-representation (B-Rep) validity, engineering and DFM checks, parameter-family perturbations, functional editing, and matched linear-static FEA in CalculiX. CADEngBench-A evaluates 150 body pairs through ranked joint
retrieval, exact face-and-edge grounding, joint-frame prediction, and kinematic verification. Across eight
multimodal, code-capable models, editing supplied CAD is substantially easier than generating it, while complex edits and matched FEA remain difficult. Assembly predictions often locate the relevant region but fail to recover the recorded joint or mating entities. These results show that CAD evaluation must test engineering behavior rather than appearance alone.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.SD
DAVE: A Decoupled Audio-Visual Enhancement Framework for Real-World Speech Separation
Wei Zhou, Wanyi Ning, Yinshang Guo et al. (+3 more)
Audio-visual
speech enhancement under real-world conditions remains challenging due to unreliable visual inputs and the lack of large-scale training data with realistic acoustic conditions. Existing approaches usually fuse visual features directly into the separation network, making them vulnerable to degraded visual signals. In this paper, we present DAVE, a decoupled audio-visual enhancement framework for real-world
speech separation. Firstly, to address the data scarcity issue, we construct DAVE-Corpus, a large-scale training corpus with 219,411 mixtures generated from public meeting corpora through combinatorial acoustic augmentation. Then, we introduce a progressive multi-objective optimization strategy to jointly improve
speech separation, intelligibility, speaker identity preservation, and perceptual quality. We further develop a certified selective enhancement chain that applies scene routing, GAN-based denoising, and loudness normalization only within the no-reference partition, guaranteeing non-degradation of reference-based metrics. Experimental results on the Real-World Audio-Visual
Speech Enhancement Challenge demonstrate the robustness of DAVE under both real-world mixed scenarios and visual degradation conditions.
Read the full abstract ▾
All authors Wei Zhou, Wanyi Ning, Yinshang Guo, Qianxiao Fang, Haitao Qian, Yingpeng Li
Artificial Intelligence · Cross-listed from cs.CV
UniDFKD: A Unified Semantic Prior Framework for Architecture-Agnostic Data-Free Knowledge Distillation
Xuewan He, Tong Chu, Zihan Cheng et al. (+5 more)
Data-Free Knowledge
Distillation (DFKD) transfers knowledge from a pretrained teacher model to a compact student model by synthesizing semantically informative data, eliminating the need for access to the original training
dataset. Existing DFKD methods rely heavily on architecture-specific statistical priors (e.g., Batch Normalization statistics) to guide data synthesis, however, such architecture-dependent priors are often absent in modern architectures such as
Vision Transformers (ViTs), resulting in degraded semantic quality of the synthesized data and consequently catastrophic performance degradation. In this paper, we propose UniDFKD, a unified data-free knowledge
distillation framework that replaces architecture-specific statistics with explicit, architecture-agnostic semantic priors. UniDFKD governs the entire synthesis-
distillation pipeline along three dimensions: (1) Categorical Semantic Conditioning (CSC) defines what to synthesize by persistently modulating the generator with
language-derived
embeddings to capture semantic diversity; (2) Spatial Semantic Anchoring (SSA) dictates where evidence belongs by anchoring the teacher's spatial attributions to a Gaussian prior; and (3) Spatial Semantic
Distillation (SSD) controls how knowledge is transferred by explicitly aligning teacher-student spatial evidence alongside predictions. Extensive experiments across CNNs and ViTs demonstrate that UniDFKD establishes a new state-of-the-art, outperforming existing methods by an average absolute margin of over 20% in both homogeneous and heterogeneous settings.
Read the full abstract ▾
All authors Xuewan He, Tong Chu, Zihan Cheng, Yuchen Su, Qianxin Xia, Guoming Lu, Jielei Wang, Wen Li
Artificial Intelligence · Cross-listed from cs.LG
VeinCast: Physics-Guided Dynamic Field Graphs with Graph-Conditioned Fusion for Global Medium-Range Weather Forecasting
Zhisheng Chen, Jinhan Li, Yuxuan Li et al. (+6 more)
Global medium-range weather
forecasting requires modeling structured yet state-dependent interactions among heterogeneous atmospheric fields. Existing data-driven models largely learn these interactions implicitly, whereas equation-level physical constraints may inherit approximation and model-form biases. We present VeinCast, a physics-guided dynamic field graph and graph-conditioned fusion framework that jointly forecasts 69 surface and upper-air fields. Within each local window, its Physics-Guided Dynamic Field Graph combines predefined atmospheric relations with state-dependent Top-K residual edges and adapts Earth-window
attention using the resulting graph context. Graph-Conditioned Latent Fusion further employs graph context and source-node centrality to guide field-to-latent aggregation, while bounded feedback preserves field-specific information. On the $1.5^\circ$ ERA5
benchmark, VeinCast demonstrates competitive
forecasting performance across all 69 meteorological fields at lead times of up to 14 days, compared with representative global weather
forecasting models including FuXi, Pangu-Weather, GraphCast, FengWu, and ARROW. Ablations confirm that the two modules provide complementary gains, demonstrating the effectiveness of relational-level physical guidance for data-driven weather
forecasting.
Read the full abstract ▾
All authors Zhisheng Chen, Jinhan Li, Yuxuan Li, Yuan Gao, Hao Wu, Zheng Lu, Jinlong Du, Kun Wang, Bo An
Artificial Intelligence · Cross-listed from eess.SP
GLocFM: A Geometry-Aware Foundation Model for 3D Indoor Wireless Localization
Chenghong Bian, Chaozheng Wen, Hongze Chen et al. (+1 more)
Learning-based wireless localizers often fail to utilize
geometric information about the propagation environment, limiting their ability to exploit non-line-of-sight (NLoS) propagation and generalize across scenes. To bridge this gap, we propose GLocFM, a Geometry-aware Localization Foundation Model, which jointly exploits WiFi measurements and scene geometry represented as a 3D point cloud. We formulate localization as a maximum-likelihood (ML) estimation problem, where the goal is to find a transmitter position that maximizes the likelihood of the wireless observations conditioned on the scene geometry. The likelihood of a candidate transmitter position is calculated by a learned scoring function that matches the observed delay–angle-of-arrival (AoA) spectrum against the spectrum predicted for that candidate. A hierarchical scene encoder extracts propagation-relevant features to produce
geometric priors for LoS and one-bounce reflection paths. For scenarios with imperfect synchronization, we further introduce a time-of-flight (ToF)-robust GLocFM model to handle unknown ToF offsets. GLocFM is trained on a multi-modal synthetic indoor localization
dataset comprising 221 diverse scenes whose associated wireless signals are generated using Sionna RT. On both synthetic and the NeRF$^{2}$
dataset based on real measurements, GLocFM reduces mean 3D localization error relative to one of the state-of-the-art localization baselines by 49.5% and 48.8%, respectively. Ablations across different number of receiver, bandwidths, and array sizes further demonstrate the effectiveness and robustness of the proposed framework.
Read the full abstract ▾
All authors Chenghong Bian, Chaozheng Wen, Hongze Chen, Jun Zhang
Artificial Intelligence
ComboShoppingBench: Evaluating LLM Agents for Budget-Constrained Basket Shopping with Coupons
Adrian Li, Kelong Mao, Yudong Guo et al. (+7 more)
Real-world shopping often requires constructing a basket of complementary items rather than retrieving a single product. Such combo-shopping tasks arise in device setup, meal preparation, event planning, and group takeout ordering, requiring joint
reasoning about item compatibility, availability, store-level requirements, delivery fees, coupons, and budgets. Evaluation is challenging because multiple baskets may satisfy the same request, making exact-match metrics unsuitable, whereas semantic evaluation alone cannot detect infeasible orders, invalid coupon combinations, or incorrect payments. We introduce ComboShoppingBench, an agentic shopping
benchmark for open-ended yet verifiable basket construction in a simulated commerce and takeout environment. During task synthesis, an exploration
agent constructs a feasible and semantically coherent basket of purchasable products; this witness guides the generation of coupons, budget constraints, user queries, and aligned evaluation rubrics. During evaluation, LLM judges assess semantic satisfaction, response quality, and claim faithfulness, while deterministic validation checks product-ID validity, budget compliance, and coupon optimality. Experiments with diverse LLM
agents demonstrate that even strong
agents struggle on ComboShoppingBench, highlighting substantial room for improvement in reliable, constraint-aware combo shopping.
Read the full abstract ▾
All authors Adrian Li, Kelong Mao, Yudong Guo, Heming Xia, Xinwei Yang, Lirui Luo, Jace Wong, Pu Yao, Sulong Xu, Simiu Gu
Artificial Intelligence
MMArch: Benchmarking Multimodal Reasoning Grounded in Architectural Evidence
Chenxu Du, Kang An, Tengyue Wang et al. (+8 more)
Multimodal large
language models (MLLMs) perform strongly on engineering imagery, yet existing
benchmarks mostly test drawing recognition, information extraction, or compliance checking, leaving open whether models can combine distributed visual evidence with engineering principles to reach a conclusion. We introduce MMArch, a
benchmark for architecture and civil engineering spanning ten subdomains and built entirely from figures in peer-reviewed papers. Its $1{,}212$ short-answer items are produced by a decoupled planner–writer pipeline and validated through automated screening, a blind
adversarial audit, and expert review, so that answering requires perceiving the relevant evidence, identifying the governing principle, and applying it, not exploiting textual or single-figure shortcuts. Evaluating $18$ open-weight and proprietary MLLMs against a domain-expert panel, we find a wide gap: the strongest open-source model attains about $30\%$ and the best proprietary system $52\%$, while human experts reach $95\%$, more than forty points ahead. Our error analysis shows that failures concentrate in applying principles and combining evidence across figures rather than in locating it, pointing to substantial headroom for future research. Code and data are available at https://dcx-swjtu.github.io/MMArch/.
Read the full abstract ▾
All authors Chenxu Du, Kang An, Tengyue Wang, Zhongyu Yang, Xinqi Yang, Yuanchi Zhu, Hebao Zhu, Ziliang Wang, Faqiang Qian, Yunli Yang, Qibing Ren
Artificial Intelligence · Cross-listed from cs.SE
Software Engineering for and with GUI Agent
Shengcheng Yu, Yuchen Ling, Junyang Xing et al. (+3 more)
GUI
agents have advanced rapidly, producing a growing body of frameworks,
benchmarks, and applications. However, this growth has outpaced the maturity of the field. GUI
agents remain technically brittle, incompletely engineered, and insufficiently validated for sustained real-world use. They are evolving into closed-loop software systems. Within these systems, model
reasoning is coupled with interface perception, execution feedback, recovery, and human oversight. This
evolution calls for a software engineering perspective that remains largely absent from existing research. We address this gap by reviewing 336 GUI-
agent papers from January 2018 to April 2026. Five research questions examine the research landscape, architectures, evaluation, software lifecycle concerns, and future opportunities. Our findings show that the field has expanded sharply since 2024, while mobile and web settings remain dominant. Architectures increasingly adopt modular perceive-reason-act loops, but recovery, human escalation, safety enforcement, and auditability remain underdeveloped. This architectural imbalance extends to evaluation. Evaluations are becoming more interactive, but they remain centered on task success and are difficult to compare across protocols. More broadly, existing studies provide limited support for testing beyond
benchmarks and for maintaining
agents after release. Observability,
privacy engineering, and systematic human oversight are also underdeveloped. Together, these findings show that capability improvements alone cannot ensure deployment readiness. Future research should connect dependable execution with lifecycle-centered testing and reproducible evaluation. It should also integrate permission and
privacy controls with cost-aware, human-centered governance. This integration is necessary to build dependable, maintainable, secure, and deployable GUI-
agent systems.
Read the full abstract ▾
All authors Shengcheng Yu, Yuchen Ling, Junyang Xing, Quan Zhou, Chunrong Fang, Zhenyu Chen
Artificial Intelligence
P$^{3}$: Joint Program-and-Proof Planning for Verified Code Generation
Zenan Li, Ziran Yang, Peiyang Song et al. (+2 more)
Verified code generation asks a large
language model (LLM) to generate both an executable program and a machine-checkable proof that the program meets a formal specification, promising software that is correct by construction. The de facto workflow decouples the two halves of the problem: first synthesize a program, then attempt to prove it correct. We observe that this sequential pipeline can be both ineffective and inefficient in practice. A program generated without anticipating its proof can be subtly incorrect or structurally difficult to verify, forcing the LLM into brittle repair loops that alternate between patching the code and patching the proof. Inspired by Dijkstra's view that a program and its correctness argument should be developed hand in hand, we propose $P^3$, an LLM-based agentic workflow that first derives a unified program-and-proof plan from the specification, then elaborates the implementation and proof scaffold under this shared plan. To evaluate verified code generation in realistic settings, we further introduce Lean4Commit0, a repository-derived, library-level
benchmark built by extracting core APIs from real-world software repositories and translating their requirements, including relational specifications across APIs, into Lean tasks. Using four frontier LLM backends, we evaluate $P^3$ on Verina, AlgoVeri, and our Lean4Commit0
benchmark, where it achieves the highest solve rate in every
benchmark–model setting. Compared with the stronger baseline, it improves solve rates by 4.6–11.2 percentage points and reduces per-task API cost by up to roughly 40% and wall-clock time by up to roughly 37% on the difficult subset of each
benchmark. A targeted ablation further shows gains of 3.3–8.3 points over implementation-only planning, isolating the benefit of planning the program and proof jointly.
Read the full abstract ▾
All authors Zenan Li, Ziran Yang, Peiyang Song, Zhaoyu Li, Kaiyu Yang
Artificial Intelligence
Entropy-based Code Adversarial Translation for Real-world Repository Migration
Yushun Tang, Yisen Cao, Zhicheng Chen et al. (+4 more)
LLMs have demonstrated strong capabilities in code generation and automated program repair, but migrating an entire repository rarely produces a runnable application because long-horizon translation challenges LLM-based
agents' ability to maintain repository-level migration objectives. In this work, we propose
Entropy-based Code
Adversarial Translation (ECAT), a multi-
agent framework for automated Android-to-HarmonyOS repository migration. ECAT formulates repository migration as
adversarial entropy minimization through a generator-discriminator architecture. The discriminator measures migration quality using a unified metric called Code
Entropy and produces text gradients that specify both file-level generation directives and the skills needed to execute them. Guided by these optimization signals, the generator iteratively updates the repository, and each update is accepted only if it reduces Code
Entropy. Repeated generator–discriminator interactions progressively drive the migration from an initial template toward a functionally complete HarmonyOS repository. Successful low-
entropy trajectories are further distilled into a self-evolving
memory tree, enabling transferable migration knowledge across repositories. We also introduce A2H-RepoBench, the first real-world
benchmark for Android-to-HarmonyOS repository migration, covering applications from tens of thousands to hundreds of thousands of lines of code. Evaluated by node
alignment and an
agent-based functional judge, ECAT achieves 74.7% overall migration quality and consistently outperforms existing
agent-based methods across repositories of different scales.
Read the full abstract ▾
All authors Yushun Tang, Yisen Cao, Zhicheng Chen, Lin Peng, Junkang Mao, Fengyi Song, Yantao Jia
Artificial Intelligence · Cross-listed from cs.LG
SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation
Jefferson Hernandez, Jaywon Koo, Zilin Xiao et al. (+2 more)
Group-based reinforcement learning objectives such as GRPO can allocate learning signal poorly across
prompt difficulty: under binary rewards, group normalization induces a divergent weighting on easy
prompts. We introduce Softmax Advantage Group Estimation (SoftmaxGRPO), a drop-in alternative that replaces z-score-normalized group advantages with temperature-scaled softmax advantages, keeping weights bounded regardless of
prompt difficulty. For binary rewards, we derive the exact finite-group population objective and identify MaxRL as its low-temperature limit. For bounded scalar rewards, we show that the large-group update exactly optimizes a log-moment-generating-function objective, while a universal finite-group scalar objective cannot exist without additional assumptions on the reward distribution. Empirically, SoftmaxGRPO reallocates measured gradient budget away from near-solved
prompts and consistently improves over GRPO under identical rewards. It reaches 51.8% on DeepMath with verifiable rewards and improves a 1.5B instruction-tuned model from 35.0% to 68.0% on Poetry using only lightweight text-similarity rewards.
Read the full abstract ▾
All authors Jefferson Hernandez, Jaywon Koo, Zilin Xiao, Chen Wei, Vicente Ordonez
Artificial Intelligence · Cross-listed from cs.CV
GRASP: Granularity-Aware Region Alignment and Semantic Prototype Learning for Fine-Grained Cross-Modal Understanding in Drone Views
Jiahui Cui, Yan Zhao, Kan Wei et al. (+4 more)
Fine-grained cross-modal understanding in drone views is essential for aerial
vision-
language navigation. However, the inherent wide field of view and overhead perspective of drone scenarios impose dual challenges on
vision-
language understanding. At the macro level, overwhelming background clutter in visual representations leads to Cross-Modal Focus Misalignment, where the model prioritizes global environmental similarities over specific object details. At the micro level, Visual Isomorphism creates ambiguity, where candidates share similar
geometric structures yet differ only in subtle attributes. To address these challenges, we propose the Granularity-Aware Region
Alignment and Semantic Prototype (GRASP) learning framework, enhancing discriminative capability through two synergistic strategies. Specifically, we introduce Region-Focused
Alignment (RFA) to promote object-centric cross-modal
alignment while suppressing background interference. Concurrently, to tackle visual isomorphism, we propose Semantic Perturbation Enhanced Matching (SPEM), which leverages a foreground-purified Semantic Prototype Codebook (SPC) to construct semantically perturbed negatives for fine-grained semantic discrimination. Extensive experiments on the GeoText-1652
benchmark and the unseen ERA
dataset demonstrate that GRASP achieves competitive performance in drone-view fine-grained image-text
retrieval, validating its effectiveness for cross-modal understanding in aerial scenarios. Our code implementation is available at https://github.com/UCAS-JC/GRASP.
Read the full abstract ▾
All authors Jiahui Cui, Yan Zhao, Kan Wei, Enze Zhu, Peirong Zhang, Lei Wang, Yiru Wang
Artificial Intelligence · Cross-listed from cs.HC
Can Coding Agents Solve Repository-Level Issues with Rendered Code? An Exploratory Study of Visual Representations
Weijie Liang, Yuanfeng Song, Xing Chen et al. (+3 more)
Visual modality has recently been explored as a way to compress textual
tokens, including rendering code as images for static code understanding. We study whether this representation can serve as operational context for agentic coding, where an
agent must navigate repositories, edit source files, and verify executable patches. Using SWE-bench Verified, we evaluate rendered code in repository-level repair workflows and introduce controlled
agent settings to separate unguided repository exploration from more structured repair stages. Our results show a mixed picture. Rendered code consistently reduces
prompt-
token cost, but the savings do not increase linearly with the nominal visual compression ratio. It largely preserves end-to-end repair accuracy, but does not overcome the performance limits of the underlying model or
agent architecture, and can become unstable under aggressive compression. Further analysis suggests that visual code is most useful when raw source reading is a major bottleneck; once repository localization is structured, much of the remaining cost comes from patch–test trial-and-error, where visual compression has limited leverage. Overall, our study positions rendered code as a viable but conditional compression mechanism for realistic coding
agents.
Read the full abstract ▾
All authors Weijie Liang, Yuanfeng Song, Xing Chen, Caleb Chen Cao, Sirui Han, Yike Guo
Artificial Intelligence
Privileged Likelihood Is Not Automatically Value: Three Checks for Token Credit in On-Policy Self-Distillation
Xuan-Phi Nguyen, Zeyu Leo Liu, Yang Li et al. (+4 more)
On-policy self-
distillation aims to improve upon reinforcement learning from verifiable rewards (RLVR) by providing
token-level scores derived from privileged information, such as reference solutions or critic feedback. These scores are treated as estimates of
token-level action values, yet they answer a fundamentally different question: how the model's prediction changes when its input context is enriched, rather than how the expected outcome changes when a
token is changed. We examine this gap along three dimensions: (i) whether the
token-level score tracks task success; (ii) whether feedback generated from the same rollout causes the score to reflect agreement with its own description, and whether using feedback from other rollouts in the group mitigates this self-referential effect; and (iii) what behavior the resulting training objective actually reinforces. In experiments on AIME 2025, the implemented score distinguishes correct from incorrect rollouts at approximately chance level (AUC=0.505); using feedback from a different rollout does not consistently improve this discrimination; and all training configurations achieve only 24.2-33.9% Avg@4, compared with 64.2% for outcome-only GRPO. Moreover, the highest-
entropy token decile accounts for 57-71% of the total absolute
token-advantage mass, despite the score being least informative about
reasoning quality in this regime. By contrast, similar experiments on SciKnowEval Biology improves held-out Avg@8 by 28.0%, while its corresponding trajectory scores achieve AUCs of 0.81-0.92. Together, these results suggest that dense credit assignment through
distillation can be effective when its likelihood-based scores are empirically validated as meaningful proxies for outcome-relevant credit. When this
alignment does not hold, however, the resulting supervision can fail to generalize and may substantially underperform outcome-based RL.
Read the full abstract ▾
All authors Xuan-Phi Nguyen, Zeyu Leo Liu, Yang Li, Shrey Pandit, Yiran Zhao, Anurag Koul, Shafiq Joty
Artificial Intelligence · Cross-listed from cs.DB
SafeQL: Search-based Refinement for Safe and Efficient LLM-based Text-to-SQL
Geonho Lee and Min-Soo Kim
Large
language models (LLMs) have advanced Text-to-SQL by enabling natural
language interfaces to databases without task-specific fine-tuning. However, existing LLM-based systems remain unreliable, often generating SQL queries that are invalid under the database schema, referencing non-existent tables, attributes, functions, or values. Such errors persist because interactions with the database management system (DBMS) are typically limited to error messages, leaving it in a largely passive role during query refinement. This paper proposes SafeQL, a search-based refinement paradigm that redefines the role of the DBMS as an active guide in the refinement process. Instead of regenerating entire queries after execution failure, SafeQL interprets DBMS feedback to incrementally repair only the erroneous components. Each refinement step is formulated as a guided search within a safe query space, where candidate queries are progressively validated through DBMS execution, thereby converging to an executable query and preventing repeated regeneration of errors. Experiments on the Bird and Spider
benchmarks show that SafeQL significantly improves execution accuracy and efficiency compared to regeneration-based methods.
Read the full abstract ▾
Artificial Intelligence
Business Truth, not SQL Accuracy: A Rule-Gated 7B Analytics Agent Outperforms a Direct-Prompted 32B Baseline
Morris Lee
LLM analytics
agents are evaluated on SQL syntax accuracy, but production failures look different: questions with two valid business definitions, questions the warehouse cannot answer, deprecated columns after a schema change, and queries that execute successfully while returning the wrong business number. No execution-match metric can score them. This paper introduces WarehouseReliabilityBench, 400 frozen tasks over two synthetic warehouses in which roughly half the correct responses are a clarification, an abstention or a refusal, with pinned denominators and a pre-registered paired bootstrap fixing each claim verb before the numbers existed. QueryProof, a 7B
agent, uses rules derived from a semantic layer and physical catalog to determine its behaviour, and gates every answer on deterministic post-execution checks. On an 80-task synthetic test split evaluated once, QueryProof outperforms a direct-prompted 32B baseline by +0.237 [+0.112, +0.375] Business Truth Rate at 71.0% lower cost per correct answer; against a cost-matched few-shot baseline the accuracy gain holds but the cost difference does not resolve. This compares systems rather than model sizes: the 32B baseline receives none of the scaffolding. False success falls from 0.754 to 0.351 of returned answers, and no wrong number was returned on an answerable task (0 of 24), though 13 answers went to questions requiring clarification or abstention. Removing the routing layer changes little (0.562 against 0.537), so the result does not depend on escalation. Routing tuned on validation over-abstains on test, and the fitted confidence model loses to the heuristic it replaced. Resampling template families rather than tasks widens both accuracy intervals to include zero, so the effect's direction is better supported than its magnitude. The gain tracks the deterministic layer, though no component ablation was run.
Read the full abstract ▾
Artificial Intelligence
SkillSentry: Reliable Skill Execution for LLM Agents via Runtime Assurance
You Lu, Xinyu Huang, Bihuan Chen et al. (+1 more)
LLM
agents are increasingly equipped with skills to perform complex tasks through multi-step
reasoning and tool use. Although skills provide reusable procedural knowledge,
agents may still execute them unreliably. Even when an
agent has demonstrated the capability to complete tasks under the guidance of a skill, it may fail to do so consistently across similar tasks or repeated runs due to deviations from the skill procedure or incorrect execution of individual steps. Such instability limits the practical reliability of LLM
agents. To address this problem, we propose SkillSentry, a skill-oriented runtime assurance framework built upon a new domain-specific
language (DSL) for representing runtime guidance for skill execution. SkillSentry initializes the runtime guidance by combining a skill specification extracted from the corresponding skill document with execution experience mined from historical successful and failed traces. It then wraps around the
agent execution loop to monitor and guide skill execution under the current guidance, while iteratively refining the guidance using newly collected traces. We evaluate SkillSentry on 15 skills across two LLM
agents, each paired with two backbone models, i.e., Claude Code with Claude-Haiku-4.5 and Claude-Opus-4.6, and Codex with GPT-5.2 and GPT-5.4. Our results show that SkillSentry improves the task success rate of LLM
agents by 24.1% across skills, on average, while exhibiting lower variability across repeated runs.
Read the full abstract ▾
All authors You Lu, Xinyu Huang, Bihuan Chen, Xin Peng
Artificial Intelligence · Cross-listed from cs.MA
MoRSE: Task-Oriented Multi-Agent System with Mixture of Role-Subtask Experts
Peiwen Li, Shiyang Zhang, Yangtian Zhang et al. (+3 more)
Large
language model-based multi-
agent systems have recently shown strong potential for complex, long-horizon tasks. However, existing methods mainly rely on coarse
prompt-level differentiation without parameter adaptation for diverse subtasks, resulting in insufficient inter-
agent heterogeneity and limited specialized capability that bottleneck performance on tasks with complex requirements. To address this, we introduce a Task-Oriented Multi-
Agent System with Mixture of Role-Subtask Experts (MoRSE) that distinguishes
agents with (role, subtask)-conditional specialization at both the task structure and parameter levels. To make
agents' responsibility explicit at the task structure level, we formulate a task-oriented multi-
agent system that decomposes each task into a dependency-aware Directed Acyclic Graph of subtasks and assigns each
agent a specific (role, subtask), introducing task-level specialization across collaborating
agents. Additionally, to address the diverse role and subtask parameter adaptation demands, we propose a dynamic Mixture of (role, subtask) LoRA Experts module with a prototype-based semantic router for subtasks, augmenting
agents with parameter-level specialization on a shared LLM substrate cost-effectively. Then, to co-optimize experts and router stably under sparse task rewards, we further propose a hierarchical group-relative policy optimization with two-layer credit assignment that isolates expert updates from the cross-route variance introduced by routing decisions, disentangling expert quality from routing quality. Experiments on code-generation
benchmarks across three backbones demonstrate the effectiveness of our approach, with improvements in both whole-task and step-wise performance, and the gains from trained specialization generalize across held-out task categories and domains.
Read the full abstract ▾
All authors Peiwen Li, Shiyang Zhang, Yangtian Zhang, Sizhuang He, David van Dijk, Rex Ying
Artificial Intelligence
Emotion2Skill: Model-Internal Emotion Signals for Adaptive Skill Selection and Evolution
Bohan Lin, Hejia Geng, Xinyi Xie et al. (+4 more)
Skill-based LLM
agents select reusable procedures from external libraries to solve complex tasks, yet their routing decisions rely primarily on task descriptions, verbal reflections, and experience-derived rules, without explicitly observing the model's internal decision state. Recent interpretability work has identified
emotion representations that influence model behavior, but their use has largely focused on post-hoc analysis and output steering. Their potential to guide
agent-level decisions remains underexplored. We propose
Emotion2Skill, a framework that extracts LLM-internal
emotion vectors and incorporates them into both skill selection and skill
evolution. The framework uses these representations to inform skill choice and tracks their changes to identify problematic invocations, enabling targeted skill refinement beyond coarse outcome feedback. Across two backbones,
Emotion2Skill outperforms seven baselines. On Qwen3-8B, it exceeds Trace2Skill by 3.1 percentage points in WebShop success and 5.7 in ALFWorld average success. Ablations and specificity controls support the utility of context-aligned
emotion signals, while co-activation analysis reveals semantically coherent
emotion–skill associations. The same
emotion vectors also transfer to MATH and MBPP without re-extraction. These results establish LLM-internal
emotion representations as an effective decision-level signal for orchestrating
agent skill systems, extending their utility beyond interpretability and output steering. Code is available at https://github.com/BoHan-LIN04/
Emotion2Skill
Read the full abstract ▾
All authors Bohan Lin, Hejia Geng, Xinyi Xie, Heng Zhou, Qinghua Xing, Chen Zhang, Yudong Zhang
Artificial Intelligence
An Explainable GNN Framework for Component-Level Anomaly Diagnosis
Sena Ozgunay, Louise Travé-Massuyès, Jean-Michel Loubes et al. (+1 more)
Industrial processes are complex systems composed of multiple interacting sensors that generate multivariate time series (MTS). Detecting anomalies in such systems is critical for reliability and safety, yet understanding their origin is equally important. Existing Graph Neural Network (GNN)based methods for anomaly detection primarily focus on sensor-level deviations and either attribute anomalies directly to the deviating sensors. When diagnosis is attempted, generally, the most deviated sensor is identified as a root cause of a system fault. However, in many industrial systems, anomalies do not arise from faulty sensors but from disruptions in the influences governing the system dynamics. We propose an explainable GNN-based anomaly detection framework that shifts the perspective from sensor-level anomalies to component-level diagnosis, hypothesizing that anomalous measurements are symptoms of altered inter-sensor influences. Experiments show that the method effectively identifies and prioritizes the true faulty components, providing interpretable insights into system failures.
Read the full abstract ▾
All authors Sena Ozgunay, Louise Travé-Massuyès, Jean-Michel Loubes, Raul Sena Ferreira