Artificial Intelligence · Cross-listed from cs.LO
The More the Merrier: Combining Properties for ABox Abduction under Repair Semantics in ELbot
Anselm Haak, Patrick Koopmann, Yasir Mahmood et al. (+1 more)
Abduction is a central approach to explain missing entailments from a knowledge base by providing a hypothesis, that would, if added to the knowledge base, make the missing entailment become true. Abduction under repair semantics has recently been investigated in detail, where several desirable properties and optimality criteria were considered, such as signature-restrictions and minimality in size and of introduced conflicts. Naturally, hypotheses that satisfy more than one of these properties or combine a property with an optimality criterion would be even more desirable for applications. So far, such hypotheses have not been investigated in the literature. In the present paper, we consider the ABox abduction problem for hypotheses satisfying more than one property or additional optimality criteria, for EL_bot under brave and AR semantics. Our main observation is that often requiring additional properties for hypotheses does not lead to an increase of complexity.
Read the full abstract ▾
All authors Anselm Haak, Patrick Koopmann, Yasir Mahmood, Anni-Yasmin Turhan
Artificial Intelligence · Cross-listed from cs.CL
Language Models as Interfaces, Not Oracles: A Hybrid LLM-ML System for Pediatric Appendicitis
Soheyl Bateni and Maryam Abdolali
Large
language models (LLMs) can make clinical decision support more accessible by interpreting free-text documentation, but their direct use as diagnostic engines is limited by sensitivity to
prompts, information order, and plausible but incorrect outputs. Structured machine-learning models offer more stable risk prediction, yet they require tabular inputs that are difficult to integrate with narrative clinical workflows. We present ClaMPAPP (Clinical
Language-assisted Machine-learning Pipeline for Appendicitis), a hybrid system that uses an LLM as an interface rather than as the final decision-maker. ClaMPAPP extracts schema-constrained clinical features from note-like narratives, applies deterministic plausibility checks, and passes validated features to an XGBoost classifier trained on clinical, laboratory, and ultrasound variables. We evaluated ClaMPAPP on two independent pediatric appendicitis cohorts from German hospitals and compared it with end-to-end LLM baselines, including open-source and proprietary models. To preserve ground truth while testing free-text input, narratives were generated from structured electronic health records through template rendering and constrained LLM rewriting, with additional sentence-order permutation to assess positional robustness. ClaMPAPP achieved the strongest overall diagnostic performance in both internal and external validation while minimizing missed appendicitis cases, the key safety concern in acute triage. End-to-end LLMs showed unstable sensitivity-specificity trade-offs and greater degradation under narrative reordering. These results support an LLM-as-interface, ML-as-predictor design that separates natural-
language usability from predictive inference and provides a more auditable pathway for clinical decision support.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Compute Efficiency and Serial Runtime Tradeoffs for Stochastic Momentum Methods
Depen Morwani, Alexandru Meterez, Pranav Nair et al. (+1 more)
Stochastic momentum methods such as heavy ball (HB), Nesterov momentum, and variants of Accelerated SGD (ASGD) [Kidambi et al., 2018] are widely used in modern training, but their
stochastic benefits depend on two distinct quantities: serial runtime, the number of iterations needed to reach a target accuracy, and compute efficiency (CE), the inverse total gradient-query or FLOP cost. Larger batches reduce serial runtime without hurting CE only when the contraction gap grows linearly with batch size. We study
stochastic HB and ASGD for consistent linear regression with Gaussian
covariates and prove finite-dimensional, discrete-time lower bounds on their batch-size tradeoffs. Our first result shows that HB does not improve the CE frontier over SGD for arbitrary spectra; rather, it preserves SGD-level CE over a larger batch-size window, allowing larger batches to reduce serial runtime until HB reaches its deterministic accelerated scale. This window can be a factor $\sqrt{\kappa}$ larger than the SGD critical batch size. For ASGD, the picture is more spectrum-dependent: for rapidly decaying power-law spectra, ASGD improves small-batch CE over HB/SGD, but as batch size grows it trades this CE advantage for improved serial runtime. Synthetic linear-regression experiments verify these qualitative regimes, including near-overlap of ASGD and HB for slowly decaying spectra and the predicted CE–serial tradeoff for rapidly decaying spectra.
Read the full abstract ▾
All authors Depen Morwani, Alexandru Meterez, Pranav Nair, Sham Kakade
Artificial Intelligence · Cross-listed from cs.RO
Hardware- and Vision-in-the-Loop Validation of Deep Monocular Pose Estimation for Autonomous Maritime UAV Flight
Maneesha Wickramasuriya, Beomyeol Yu, Jaden Shin et al. (+3 more)
Autonomous
UAV operations on ships require reliable
vision-based relative pose estimation, yet at-sea validation is costly, weather-dependent, and risky. This paper presents a hardware-validated
vision-in-the-loop framework that enables fully autonomous indoor flight while emulating photorealistic maritime environments. Rendered maritime views are processed onboard by a deep
transformer-based
monocular pose
estimator. Delayed
vision measurements are fused with high-rate IMU data using a delayed Kalman filter to provide consistent state estimates for
geometric control. The system captures critical embedded effects, including perception latency, asynchronous updates, and computational constraints, that are absent in pure simulation. Autonomous takeoff, trajectory tracking, and landing experiments demonstrate stable closed-loop flight. The results establish a safe and hardware-realistic intermediate stage for developing maritime
UAV autonomy prior to shipboard deployment.
Read the full abstract ▾
All authors Maneesha Wickramasuriya, Beomyeol Yu, Jaden Shin, Mason Huslig, Taeyoung Lee, Murray Snyder
Artificial Intelligence · Cross-listed from cs.HC
A Clinician-Centered Pipeline for Annotation and Evaluation in Ultrasound AI Studies
Fangyijie Wang, Jianjun Yu, Wentao Shi et al. (+4 more)
Clinician-centered evaluation is critical for validating medical AI systems, especially in ultrasound imaging where quantitative metrics do not always capture clinical usability. Existing medical image platforms primarily focus on
dataset labeling. They lack integrated support for blinded model comparison and reproducible evaluation workflows. We present a clinician-centered pipeline for remote annotation and evaluation in ultrasound AI studies. The proposed pipeline uses a centralized server and lightweight browser interfaces to enable clinicians to perform annotation, blinded ranking, and review without local
dataset downloads. The pipeline also supports multi-rater participation, centralized result aggregation, and automated statistical analysis. We validate the pipeline in a fetal ultrasound
segmentation study with six raters spanning expert, generalist, and non-expert experience levels. The system automatically generated Spearman correlation, Kendall's $\tau$, and top-1 selection statistics. Results indicated moderate to strong agreement across experts and other groups. The blinded evaluation results showed a tendency for later active learning models to be preferred. These outcomes suggest that the pipeline can support clinician-centered annotation and reproducible human-\ac{AI} evaluation studies in ultrasound imaging. The proposed pipeline is available on \href{https://github.com/13204942/SonoRate}{GitHub}.
Read the full abstract ▾
All authors Fangyijie Wang, Jianjun Yu, Wentao Shi, Haixia Huang, Ran Shi, Guénolé Silvestre, Kathleen M. Curran
Artificial Intelligence
User as Engram: Internalizing Per-User Memory as Local Parametric Edits
Bojie Li
Personal
memory in a
language model is two problems: content and
reasoning skill. The
brain keeps the two apart (a sparse, local engram in the hippocampus for each episode, a slow neocortex for the shared skills that interpret it), so a new fact need not overwrite everything else. Most personalization today keeps a user's facts outside the weights, in a natural-
language memory file or a
retrieval index. When facts are written into the model instead, the standard recipe is the per-user LoRA adapter, which does the opposite of the
brain, folding content and skill into one global weight delta. Writing a user's facts as a LoRA contaminates text unrelated to them; writing the same facts as local Engram rows leaves it mathematically untouched, resulting in a roughly 33,000x smaller
memory footprint. We therefore propose User as Engram: store a user's content as
surgical edits to the hash-keyed
memory table of an Engram model, and carry the
reasoning skill in one shared adapter. This layered design matches per-user LoRA's direct recall while delivering 5.6x higher indirect-
reasoning accuracy on average, and never makes a single user worse at
reasoning than the untouched base. The edit is a glass box: writing a fact switches on its lookup at exactly the trigger, adds the value the answer needs, leaves every other position unchanged to the last bit, and fails if written into the wrong layer. Because different users' facts land in disjoint hash slots, their edits compose: many users live in one shared table at once, stacking additively and losslessly, where a per-user LoRA, a single global weight delta, admits only one. Upon
retrieval, a per-user Engram table does not grow with the population the retriever must search, so past ~100 facts it overtakes a
retrieval pipeline on a 2.5x larger model.
Read the full abstract ▾
Artificial Intelligence
Beyond Safe Data: Pretraining-Stage Alignment with Regular Safety Reflection
Jinhan Li, Kexian Tang, Yihan Xu et al. (+2 more)
To achieve deeper safety
alignment for large
language models (LLMs), recent efforts have studied how to push safety interventions earlier into the pretraining stage, primarily by filtering unsafe data or rewriting it into safer forms. We argue that pretraining-stage
alignment should go beyond making the data safe: LLMs may generalize unsafe behaviors from seemingly benign pretraining data. To this end, we propose Safety Reflection Pretraining, a pretraining-stage
alignment method which regularly inserts short safety reflections between sentences in pretraining corpora. This integrates self-monitoring directly into
language modeling, establishing a foundational capability that is subsequently reinforced by compatible post-training. Our experiments with 1.7B models pretrained on FineWeb-Edu show that Safety Reflection Pretraining improves safety classification accuracy and substantially reduces the success rates of inference-stage and fine-tuning attacks. Complementary to our real-world experiments, we also introduce a fully controlled synthetic environment, MedSafetyWorld, with a clear definition of safety and a
reasoning structure under which we find that models can easily generalize unsafe behaviors from safe data. Ablations in MedSafetyWorld further demonstrate a clear advantage of Safety Reflection Pretraining over data filtering and rewriting in preventing models from acting on unsafe behaviors. Taken together, our findings suggest that pretraining
alignment should not only make the training data safe, but also shape the behaviors that models are likely to acquire from safe data.
Read the full abstract ▾
All authors Jinhan Li, Kexian Tang, Yihan Xu, Zhuorui Ye, Kaifeng Lyu
Artificial Intelligence · Cross-listed from cs.LG
Data-Aware Model Merging in the Essential Subspace for Multi-Task Knowledge Aggregation
Longhua Li, Lei Qi, Qi Tian et al. (+1 more)
Model merging enables training-free multi-task learning by aggregating knowledge from models fine-tuned from a shared checkpoint, but their task updates can interfere. Using proxy data, we find that task updates induce output shifts whose energy concentrates in a few dominant directions, while many low-energy directions can accumulate across tasks and impair performance. We call the span of the dominant directions the essential subspace. This observation motivates a data-aware framework to preserve essential task knowledge while reducing interference. Essential Subspace Decomposition (ESD) identifies each task's essential subspace from activation shifts measured on proxy data and represents its update compactly while preserving functional behavior. Essential Subspace Merging (ESM) weights each task-update direction by its corresponding output-shift
eigenvalue, thereby prioritizing core task knowledge; it then orthogonalizes the weighted directions across tasks to reduce interference. ESM++ extends this merged model by dynamically integrating low-rank task-specific residual experts for adaptive knowledge aggregation. Experiments across diverse task sets and model scales show that ESM and ESM++ effectively aggregate task knowledge while mitigating inter-task interference. Code is available at https://github.com/kiddo127/ESM.
Read the full abstract ▾
All authors Longhua Li, Lei Qi, Qi Tian, Xin Geng
Artificial Intelligence · Cross-listed from cond-mat.mtrl-sci
AdsMind: A Physics-Grounded Multi-Agent System for Self-Correcting Discovery of Adsorption Configurations on Heterogeneous Catalyst Surfaces
Zongmin Zhang, Yuyang Lou, Bowen Zhang et al. (+6 more)
Identifying the lowest-energy surface-adsorbate configuration is critical for modeling heterogeneous catalysis, yet exhaustive exploration with ab initio calculations is computationally prohibitive. Machine-learning force fields (MLFFs) accelerate structural relaxation but leave the search over the vast configurational space a major bottleneck, and open-loop large
language model (LLM)
agents lack a physics-grounded feedback mechanism to correct erroneous initial guesses. We propose AdsMind (Adsorption configuration discovery with Machine intelligence and relaxation feedback), a closed-loop multi-
agent framework that enables autonomous error correction through MLFF relaxation feedback. Across four LLM backends, AdsMind achieves consistently high search reliability, with success rates of 100% and 98.8% on the
benchmarks AA20 and OCD-GMAE62. Relative to its single-pass (1-Shot) ablation it reduces cross-backend energy dispersion, and it uses only 4.11 and 4.67 MLFF relaxations per case, respectively – an approximately 14-fold reduction over heuristic enumeration baselines. Density functional theory (DFT) validation using VASP/PBE on six representative AA20 systems shows that the reported open-loop Adsorb-
Agent outputs exhibit qualitative adsorption-energy sign errors for molecular adsorbates, whereas AdsMind preserves the correct sign in all tested cases with closer quantitative agreement. AdsMind thus delivers reliability, self-reflection, and interpretability simultaneously, supporting more DFT-informed autonomous chemistry workflows.
Read the full abstract ▾
All authors Zongmin Zhang, Yuyang Lou, Bowen Zhang, Junwu Chen, Ryo Kuroki, Xuan Vu Nguyen, Edvin Fako, Lixue Cheng, Philippe Schwaller
Artificial Intelligence · Cross-listed from cs.LG
OrthoReg: Orthogonal Regularization for Hybrid Symbolic-Neural Dynamical Systems
Till Richter and Niki Kilbertus
Dynamical systems are fundamental to modeling the natural world, yet modeling them involves a persistent trade-off: manually prescribed mechanistic models are interpretable by design but often overly simplistic and misspecified; in contrast, flexible data-driven neural methods lack physical insight. Hybrid modeling aims for the best of both worlds by combining a prescribed or symbolic, physics-based component with a flexible neural network. A critical challenge, however, is that the neural component may relearn mechanistic parts, yielding redundant and uninterpretable models, especially when the symbolic structure itself is discovered from data. Existing methods based on standard $L^2$ regularization rely on a projection argument that breaks when the symbolic component is learned through sparse discovery, allowing the neural augmentation to overlap with symbolic structure. We introduce OrthoReg (Orthogonal Regularization), which directly penalizes overlap between the symbolic and neural components, preventing symbolic structure from being absorbed by the neural residual. This yields a complementary decomposition: the symbolic part captures what the library can express, and the neural part captures what remains. On
benchmark dynamical systems with partial library mismatch, OrthoReg improves symbolic recovery and out-of-distribution behavior.
Read the full abstract ▾
Artificial Intelligence
Human-AI Coevolution Dynamics: A Formal Theory of Social Intelligence Emergence Through Long-Term Interaction
Jingyi Zhou, Senlin Luo and Haofan Chen
Current conversational AI systems have made significant progress in
language generation, personalization, and long-context interaction. However, most existing methods model social behavior through isolated components such as
emotion modeling,
memory retrieval, or persona conditioning, lacking a unified framework to explain the emergence of stable social relationships and social intelligence in long-term human-AI interaction.To address this, we propose the Human-AI Coevolution Dynamics Framework (HACD-H), a formal model of human-AI interaction as a self-organizing social cognitive system. HACD-H integrates emotional adaptation, relational organization, social
memory, and personality consistency into a unified dynamical framework and introduces principles including multi-timescale social cognition, relational attractors, trust basins, developmental phase transitions, and social cognitive energy dynamics.We construct a conversational
dataset with approximately 14,700 interaction turns and develop a theory-driven empirical evaluation framework. Results reveal a hierarchy of temporal persistence in social cognition, stable relational attractors, phase-transition-like developmental patterns, and a structured social cognitive energy landscape. Social intelligence shows a significant negative correlation with social cognitive energy (r = -0.391, p < 0.001), and interaction trajectories exhibit progressive energy reduction over time.These findings suggest that social intelligence emerges from long-term social cognitive coevolution rather than isolated conversational capabilities. HACD-H provides a unified theoretical foundation for modeling adaptive human-AI social interaction and developing socially intelligent AI systems.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.MA
A Technical Taxonomy of LLM Agent Communication Protocols
Linus Sander, Habtom Kahsay Gidey, Alexander Lenz et al. (+1 more)
As large
language models (LLMs) advance and multi-
agent systems aim to overcome the limits of standalone
agents, robust communication protocols are becoming essential infrastructure for distributed
agent networks. Nonetheless, the fragmented protocol landscape presents a significant interoperability challenge. This study develops a technical taxonomy to classify and analyze LLM
agent communication protocols. Following an established iterative method, we defined the taxonomy's purpose, meta-characteristic, and ending conditions, then performed five iterations, three empirical-to-conceptual and two conceptual-to-empirical, on nine actively maintained open-source protocols with demonstrable adoption. The taxonomy comprises five dimensions: counterparty, payload, interaction state, discovery mechanism, and schema flexibility. Classification reveals recurring architectural patterns: all sampled
agent-to-
agent protocols combine hybrid payloads with session-state persistence; most protocols support multiple predefined schemas, and two negotiate schemas at runtime, indicating a trend toward schema flexibility; decentralized discovery remains rare. Analysis suggests short-term convergence pressure toward protocols unifying
agent-to-
agent and
agent-to-context (tool and data) communication. Long-term, however, no single protocol is likely to maximize versatility, efficiency, and portability simultaneously. The field will more likely evolve toward a
federated, layered protocol stack. The framework guides protocol selection and highlights open research gaps such as
privacy and policy enforcement.}
Read the full abstract ▾
All authors Linus Sander, Habtom Kahsay Gidey, Alexander Lenz, Alois Knoll
Artificial Intelligence · Cross-listed from cs.LG
Pareto Q-Learning with Reward Machines
Arnaud Lequen, Clément Legrand-Lixon and Léo Saulières
We present Pareto Q-Learning with Reward Machines (PQLRM), a multi-objective reinforcement learning
algorithm for tasks whose reward structure is specified by a set of reward machines (RMs). PQLRM combines Pareto Q-Learning (PQL), which maintains sets of vector-valued Q-estimates to approximate the Pareto front, with enhancements from Q-Learning with Reward Machines (QRM), which exploits the factored automaton structure of the reward signal. This yields a multi-policy
algorithm that remains sample-efficient under non-Markovian, RM-encoded rewards. Experimental trials show that PQLRM converges faster than a naive PQL baseline applied to the cross-product MDP and can synthesize Pareto-optimal policies that QRM cannot.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from physics.optics
Equivariant Graph Neural Networks Improve Optical Spectra Prediction for Materials Screening
Kasper Helverskov Petersen, François R J Cornet, Martin Ovesen et al. (+3 more)
Scalable prediction of optical spectra is a critical component of high-throughput materials screening for optoelectronic applications such as
solar cells. Existing surrogate models are trained on spectra computed from lower levels of theory or rely on rotation-invariant scalar features, limiting their
geometric expressiveness. We explore the use of equivariant graph neural networks for optical spectra prediction, adapting GotenNet to this task and evaluating it on multiple
datasets including a recently published collection of 10,533 structures with spectra computed at the level of the random phase approximation (RPA). The proposed model outperforms the current state of the art, with the largest gains in the 0-8 eV range and on predicting the static real permittivity, both of particular relevance for thin-film optics.
Read the full abstract ▾
All authors Kasper Helverskov Petersen, François R J Cornet, Martin Ovesen, Mikkel Jordahn, Kristian S. Thygesen, Mikkel N. Schmidt
Artificial Intelligence
Analysing drivers and interdependencies in European electricity markets using XAI
Antoine Pesenti and Aidan O'Sullivan
Electricity
markets are inherently complex systems characterised by strong nonlinearities, high-dimensional interactions, and increasing interdependence across regions. While deep neural networks (DNNs) have demonstrated strong predictive capabilities for electricity prices, their lack of interpretability limits their usefulness for understanding the underlying drivers of price formation. This paper addresses this gap by combining DNN models with explainable artificial intelligence (XAI) techniques to analyse the determinants of electricity prices across 39 European bidding zones. We employ SHAP (SHapley Additive exPlanations) to quantify feature contributions and apply and extend SSHAP, an aggregation framework to improve interpretability in high-dimensional settings. The analysis identifies that renewable energy sources, particularly
solar, play a disproportionately important role in price formation despite their lower share in total power generation. Gas prices remain a dominant and consistent driver across electricity
markets, while interconnections significantly shape price dynamics, highlighting the strong interdependence of European electricity systems. In addition, a synthetic EU-wide electricity
market is constructed to explore the counterfactual scenario of a fully integrated
market with a single price.
Read the full abstract ▾
Artificial Intelligence
Towards an Agent-First Web: Redesigning the Web for AI Agents
Eranga Bandara, Ross Gore, Ravi Mukkamala et al. (+18 more)
The World Wide Web was built on an assumption held for three decades: the primary consumer of web content is a human being. This permeates every layer; its access model presumes human visitors, its economics rest on human
attention, and its content targets human perception. The rapid emergence of AI
agents as intermediaries between humans and web content invalidates this assumption. Yet the web resists
agents through blanket blocking, CAPTCHA-based exclusion, and economic models that treat
agent access as extraction rather than legitimate interaction. This paper proposes a principled redesign across three layers. At the access layer,
agents acting for humans should inherit equivalent access rights, governed by rate limiting and
agent identification metadata in HTTP requests, analogous to browser headers, alongside a dual-layer architecture serving human-readable and
agent-optimized content from the same domain. At the economic layer, we propose an intent-based tier framework grounded in the
agent-as-human-proxy principle: an
agent's economic obligation mirrors that of the human it represents. A
token-based subscription model meters content in
tokens rather than pageviews, alongside a commissioned content economy anchoring AI content production in human intentionality. At the content layer, we identify epistemic recursion, the self-referential loop in which AI-generated content is consumed by
agents to produce further content, progressively detaching web knowledge from human ground truth. We propose the
Agent Text Markup
Language (ATML), a four-level human supervision tier model, and a cryptographic provenance chain to counter this threat. Together these constitute ten design principles for an
agent-first internet, one in which
agents are first-class citizens whose integration requires renegotiating the web's foundational social contract across access, economics, and content.
Read the full abstract ▾
All authors Eranga Bandara, Ross Gore, Ravi Mukkamala, Asanga Gunaratna, Safdar H. Bouk, Xueping Liang, Peter Foytik, Abdul Rahman, Sachini Rajapakse, Isurunima Kularathna, Pramoda Karunarathna, Chalani Rajapakse, Ng Wee Keong, Kasun De Zoysa, Tharaka Hewa, Amin Hass, Wathsala Herath, Aruna Withanage, Nilaan Loganathan, Atmaram Yarlagadda, Sachin Shetty
Artificial Intelligence · Cross-listed from cs.CL
Leadership as Coordination Control: Behavioral Signatures and the Recovery-Advantage Boundary in Multi-Agent LLM Teams
Haewoon Kwak
Team science holds that leadership is contingent: it helps only under specific conditions. We ask the same question of multi-
agent LLM teams: under what measurable conditions does process-level coordination control add value, and do those conditions match what team science predicts? This takes measurement, not just accuracy: we use behavioral signatures (majority lock-in, exploration, recovery from an incorrect round-0 consensus) and per-action ablations, clean because each controller is an explicit action set. We operationalize three classical leadership styles (transactional, transformational, situational) as controllers over a shared action vocabulary (explore, revise, accept, synthesize). A matched controller with the same actions but an arbitrary rule recovers no better than majority voting. Across four task regimes and three open-weight model families, no controller dominates by accuracy. Transactional control matches a shared round-0 vote on all 12 combinations to within 1.3pp, and accuracy gains appear only on the single llama-4-scout social combination, where the round-0 majority is unreliable. Against the stronger flat baseline, only situational still gains (+8pp). A recovery-advantage account, tested with four boundary probes, says a controller beats plain interaction only where the round-0 majority is unreliable, the task is recoverable, and undirected interaction does not already repair it. Because these conditions map onto contingency theory (leadership substitutes, path-goal redundancy, the readiness gap), a largely null accuracy result is what the theory predicts, not a failure of the controllers. We advance this readiness-gap boundary as an explanatory hypothesis rather than an established general principle. Its null side is corroborated across every other combination, including under held-out prediction, while its positive side is observed in a single combination.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
ProductConsistency: Improving Product Identity Preservation in Instruction-Based Image Editing via SFT and RL
Mukund Khanna, Raj Singh Yadav and Kunal Singh
Recent advances in instruction-based image editing have enabled models to perform complex visual edits from natural
language instructions. However, in product-centric scenarios where preserving product features, branding, and textual elements are critical, current open and closed source models often struggle to maintain this fine-grained object identity. This issue is further compounded by the lack of
datasets for instruction-based product image editing with text fidelity constraints, leaving it largely treated as an implicit capability of instruction-based image editing models. In this work, we introduce the ProductConsistency
dataset which is designed to improve product-centric image editing. Our approach includes a supervised fine-tuning (SFT)
dataset of 87k samples for product editing, a reinforcement learning (RL)
dataset with 869 unique product images, and a new
benchmark dataset, the ProductConsistency
Benchmark, to allow rigorous and standardized evaluation of editing models. To guide RL training, we propose a Cyclic Consistency reward that enforces semantic preservation of product identity by using caption similarity between the original product description and captions generated from the edited image. We fine-tune both Qwen-Image-Edit-2511 and Flux.1-Kontext-dev using our
dataset and demonstrate consistent improvements over baseline models in OCR and Perceptual metrics, and MLLM-based evaluations as well, indicating stronger product consistency, text rendering, and overall visual quality; with the Qwen-Image-Edit-2511 model achieving a 5x reduction in the character error rate. The code and pipeline is available at https://anonymous.4open.science/r/ProductConsistency-6FCC/README.md
Read the full abstract ▾
Artificial Intelligence
Semantic Adapter Routing with Fine-Tuning Task Embeddings
Enrico Cassano, Michał Brzozowski, Paolo Mandica et al. (+2 more)
Parameter-efficient fine-tuning (PEFT) has led to model ecosystems in which a single backbone is paired with many task-specialized adapters. Given such a library, routing aims to select the most appropriate adapter for a user query. While existing adapter routers typically require access to adapter weights or supervised training, we develop training-free semantic adapter routing methods using task
embeddings. In ARIADNE, we reframe adapter selection as a classification problem, where PEFT adapters are represented by task
embeddings and an unlabeled query is routed to the nearest adapter in the encoder's latent space. Evaluated on 23 tasks, ARIADNE recovers 97.4% of Oracle task performance and scales to 44 adapters at 89.7% selection accuracy, without touching a single adapter parameter. However, training data needed for ARIADNE may not be available when adapters come from public hubs or third-party providers. To overcome this limitation, we introduce GRACE, which recovers an adapter's fine-tuning data from its output logits alone via a modified contrastive decoding diffing (CDD) procedure. Synthetic data generated from CDD-UM is then used to construct task
embeddings. Across three backbones (Llama-3.2-1B, Qwen2.5-3B, Qwen2.5-32B), GRACE recovers 72–100% of Oracle task accuracy and matches or exceeds ARROW on 48 of 69 task/backbone combinations, while requiring neither training data nor model weights. Overall, we demonstrate that fine-tuning task
embeddings provide an accurate and efficient path to semantic adapter routing.
Read the full abstract ▾
All authors Enrico Cassano, Michał Brzozowski, Paolo Mandica, Zuzanna Dubanowska, Neo Christopher Chung
Artificial Intelligence
RODS: Reward-Driven Online Data Synthesis for Multi-Turn Tool-Use Agents
Ruishan Fang, Siyuan Lu, Chenyi Zhuang et al. (+1 more)
Multi-turn tool-use RL is bottlenecked by the rapid depletion of informative samples in static
datasets. We observe that the gradient signal in GRPO concentrates on tasks with the highest rollout reward variance, a consequence of the Popoviciu upper bound. Consequently, samples near the
agent's capability boundary – where successes and failures are roughly balanced – contribute disproportionately large policy gradients. As training progresses, this boundary continuously shifts, which gradually depletes the pool of informative samples in a static
dataset. We propose RODS (Reward-driven Online Data Synthesis) to resolve this depletion. RODS closes the loop between RL training and data generation by repurposing the progress reward variance as a practical, zero-cost boundary detector that requires no extra inference beyond the rollouts already computed for training. It continuously identifies such boundary samples, synthesizes new multi-turn variants matching their structural complexity (e.g., API
topology and dependency depth) via a skill-aligned resampling pipeline, and manages a dynamic replay buffer that co-evolves with the policy. Starting from 400 human seeds and maintaining an active training pool of ~800 samples, RODS achieves comparable performance to a 17K-sample offline pipeline while requiring roughly 20x fewer trajectories, and improves over fixed-data RL and environment augmentation in our controlled setting.
Read the full abstract ▾
All authors Ruishan Fang, Siyuan Lu, Chenyi Zhuang, Tao Lin
Artificial Intelligence · Cross-listed from cs.SE
Where Did the Variability Go? From Vibe Coding to Product Lines by Regeneration
Xhevahire Tërnava
In vibe coding, an emerging AI-driven paradigm, an LLM generates an entire program from a natural
language prompt, but what happens to the variability that traditional software engineering carefully builds into code? To answer this question, we conducted an exploratory analysis on 10 vibe coded C/C++ projects, which suggests that there is near zero in-artifact variability, i.e., at compile- and runtime. All variability decisions are resolved at a single new binding time, generation time, the moment the LLM produces the source code. Rather than treating this as a defect to fix, we propose Variability by Regeneration (VbR), to our knowledge the first product line approach in which the LLM acts as the derivation engine, generating a dedicated, free of dead code binary for each variant from a declarative specification, while a variant dispatcher transparently routes user requests to the matching binary. We formalise VbR, contrast it with classical SPL derivation, and demonstrate its full pipeline on a wc product family. For SPL engineering, variability in AI-generated software belongs in the specification, not in the code.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
A Hybrid LSTM–Vision Transformer Architecture for Predicting HRRR Forecast Errors
David Aaron Evans, Jay C. Rothenberger, Kara J. Sulia et al. (+2 more)
Forecast errors in high-resolution numerical weather prediction (NWP) systems are often linked to unresolved planetary boundary layer (PBL) processes, convection, terrain-induced circulations, and other vertically structured atmospheric phenomena. Previous work demonstrated that Long Short-Term
Memory (LSTM) networks can successfully predict forecast errors in the High-Resolution Rapid Refresh (HRRR) model using mesonet observations, but we believe performance degradation is linked to periods of complex vertical atmospheric
evolution. To address this limitation, we develop a hybrid LSTM-
Vision Transformer (LSTM-ViT) framework that combines temporal sequence learning from surface observations with atmospheric profiles from the New York State Mesonet profiler network. The LSTM-ViT framework is trained to predict HRRR hourly precipitation, 10 m wind speed, and 2 m temperature forecast errors at individual mesonet stations. Across all three predictors, incorporation of profiler-derived atmospheric structure improves forecast error prediction skill relative to the baseline LSTM architecture, with the largest gains occurring at shorter forecast lead times and during periods of enhanced PBL activity. Improvements are particularly pronounced for precipitation forecast error, where the LSTM-ViT framework achieves approximately a twofold increase in predictive skill relative to the baseline LSTM while better capturing convectively driven error
evolution and reducing degradation associated with PBL processes. These results demonstrate that combining temporal sequence learning with vertically informed
attention mechanisms provides a physically meaningful pathway for improving forecast error prediction in operational NWP systems. Our research offers forecasters enhanced guidance regarding model bias and forecast confidence.
Read the full abstract ▾
All authors David Aaron Evans, Jay C. Rothenberger, Kara J. Sulia, Nick P. Bassill, Chris D. Thorncroft
Artificial Intelligence · Cross-listed from cs.LG
FoMoE: Breaking the Full-Replica Barrier with a Federation of MoEs
Lorenzo Sani, Zeyu Cao, Meghdad Kurmanji et al. (+5 more)
Pre-training Large
Language Models (LLMs) typically demands large-scale infrastructure with tightly coupled hardware accelerators. Mixture-of-Experts (MoEs) architectures partially decouple model capacity from per-
token compute. This efficiency alone does not make MoE training feasible over ordinary Internet links or loosely connected commodity hardware since active expert routing still assumes high-speed datacenter fabrics. Low-communication methods such as DiLoCo and
Photon reduce synchronization frequency across distributed sites, mitigating bandwidth constraints, yet still require full model replicas at every site. This creates a mismatch: modern MoEs have sparse data paths, but their distributed training infrastructure remains communication-dense and
memory-inefficient, limiting attempts to pool geographically distributed compute. In this work, we introduce FoMoE, a system that breaks the full-replica paradigm by partitioning expert layers across workers and skipping non-resident experts during local training. We demonstrate that FoMoE: (I) reduces communication costs by up to 1.42x over efficient baselines and 45.44x over Distributed Data Parallelism (DDP) via partial expert replication in controlled regimes; (II) achieves empirical throughput speedups of up to 1.4x through the skip-
token mechanism; and (III) shows stable routing in the trained regimes and projects the communication/
memory benefits to 100B-scale configurations through system modeling.
Read the full abstract ▾
All authors Lorenzo Sani, Zeyu Cao, Meghdad Kurmanji, Alex Iacob, Andrej Jovanovic, Yan Gao, Wanru Zhao, Nicholas D. Lane
Artificial Intelligence · Cross-listed from cs.DC
Spotlight: Synergizing Seed Exploration and Spot GPUs for DiT RL Post-Training
Ruiqi Lai, Dakai An, Wei Gao et al. (+6 more)
Reinforcement learning (RL) post-training of
Diffusion Transformers (DiTs) is prohibitively expensive, requiring thousands of high-end GPUs. Existing works explore two directions to reduce cost: seed exploration improves training convergence by selecting high-contrast samples, yet adds compute to the critical path; spot GPUs offer 69–77% lower cost, yet sit idle during training because DiT rollouts finish nearly simultaneously, which prevents LLM-style pipelining of rollout with training. Spot preemptions further break Sequence Parallelism (SP) groups, fragmenting GPU
topology. We present Spotlight, the first system that harvests spot GPUs for DiT RL post-training. Spotlight rests on two key insights we devise: (1)~we show that exploration can tolerate stale model weights because exploration that uses the model weights from the previous iteration preserves the relative ranking of random seeds, allowing exploration to run on idle spot GPUs during training. (2)~SP reconfiguration can reuse on-node state, reducing group recovery from minutes to sub-second launches. Built on these insights, Spotlight introduces three techniques: a bandit-based exploration planner that maximizes reward variance within the training time budget, elastic sequence parallelism that reconfigures SP groups on the fly via persistent schedulers and intra-node weight copying, and a preemption-aware pull-based request scheduler that balances load and commits in-flight state upon preemption. We implement Spotlight on the open-source RL platform ROLL and evaluate it on Qwen-Image post-training. Spotlight reaches the same target validation score $4\times$ faster than baselines, reducing total cost by $1.4$-$6.4\times$ while achieving superior image quality on DeepSeek-OCR and Geneval
datasets with resolution $512\times512$ and $1280\times1280$.
Read the full abstract ▾
All authors Ruiqi Lai, Dakai An, Wei Gao, Ju Huang, Siran Yang, Jiamang Wang, Lin Qu, Dmitrii Ustiugov, Wei Wang
Artificial Intelligence · Cross-listed from cs.CR
TRAP: Benchmark for Task-completion and Resistance to Active Privacy-extraction
Moon Ye-Bin, Nam Hyeon-Woo, Baek Seong-Eun et al. (+2 more)
Agents are increasingly deployed in document-intensive workflows where sensitive private information is not an edge case but a routine input, e.g., an
agent booking a flight needs passport numbers. In such settings, the
agent must use private information to complete tasks accurately while never exposing it in its responses, because it cannot verify who is actually at the keyboard. These two obligations are in fundamental tension. A model capable enough to use private information for task completion can, by the same capability, be induced to reveal it. To evaluate the trade-off of task accuracy and
privacy leakage, we introduce Task-completion and Resistance to Active
Privacy-extraction (TRAP). Each scenario includes a document containing private information, a task query that requires the
agent to invoke the correct tool using private fields, and an attack query that attempts to elicit the same information in natural
language. Evaluating 22 models spanning frontier proprietary and open-source models at multiple scales, we find that all model families exhibit non-trivial leakage, and that instruction-following ability correlates with leakage rate. Existing
prompt-based defenses reduce leakage but at significant cost to task accuracy.
Prompt optimization fails to escape this trade-off. We demonstrate that this failure is not incidental. For any softmax-based model, no soft-constraint defense, e.g.,
prompt-based defenses, can jointly achieve high task success with zero leakage probability. Motivated by this impossibility result, we propose structural private field isolation, which replaces private fields with hash keys before they reach the model. This approach largely prevents leakage while keeping task accuracy.
Read the full abstract ▾
All authors Moon Ye-Bin, Nam Hyeon-Woo, Baek Seong-Eun, Yejin Yeo, Tae-Hyun Oh
Artificial Intelligence · Cross-listed from cs.CL
G-IdiomAlign: A Gloss-Pivoted Benchmark for Cross-Lingual Idiom Alignment
Fengying Ye, Yanming Sun, Runzhe Zhan et al. (+3 more)
Idioms are difficult to transfer across
languages due to their non-compositionality and weak surface-form grounding, making literal mappings unreliable. We present G-IdiomAlign, a gloss-pivoted
benchmark where each idiom is anchored by an English gloss from Wiktionary. We further construct a high-confidence reference
alignment set for reproducible evaluation. G-IdiomAlign supports two protocols: (1) a controlled Multiple-Choice Idiom Equivalence with typed distractors for error attribution; and (2) a Gloss-Contrastive Generation contrasting No-gloss and With-gloss inputs to isolate the effect of an explicit semantic pivot. Across diverse LLMs, a bias to literal translation is a dominant failure mode, especially when the target is a low-resource
language. Glosses consistently improve Gloss-Contrastive Generation under an
embedding-based semantic proxy, but performance remains modest, indicating substantial headroom in the open output space. Subsequent analysis on Qwen3-8B further suggests that cross-condition differences are concentrated more in
attention heads than in layers, while better With-gloss generations coincide with stronger gloss anchoring.
Read the full abstract ▾
All authors Fengying Ye, Yanming Sun, Runzhe Zhan, Zheqi Zhang, Lidia S. Chao, Derek F. Wong
Artificial Intelligence
ThinkDeception: A Progressive Reinforcement Learning Framework for Interpretable Multimodal Deception Detection
Jinhao Song, Shan Liang, Yiqun Yue et al. (+2 more)
Multimodal deception detection is critical for identifying fraudulent intentions, yet existing approaches predominantly rely on end to end black–box paradigms. These methods suffer from a severe lack of interpretability failing to provide transparent
reasoning trajectories and struggling to explicitly capture the subtle, cross modal inconsistencies inherent in deceptive behaviors. To transcend these limitations, we propose ThinkDeception, a novel and interpretable
multimodal deception detection framework. As a pioneering effort, it introduces
Multimodal Large
Language Models (MLLMs) into this domain, transforming deception detection from a traditional binary classification task into an explicit cognitive
reasoning process. Facilitated by the first meticulously annotated step–by–step
multimodal Chain of Thought (CoT)
dataset, we develop a foundational model, ThinkDeception Base, empirically validating the critical role of modal inconsistency in decoding deception. Building upon this foundation, our core innovation lies in proposing Visual-Audio Consistency Group Relative Policy Optimization(VAC–GRPO) equipped with a progressive training strategy. Distinct from standard GRPO, we stratify the training data into four progressive difficulty tiers, guiding the model through a psychologically grounded easy–to–hard cognitive transition. By innovatively coupling this dynamic curriculum scheduler with a multi dimensional, process aware reward mechanism and a reflective learning paradigm, we significantly elevate the model's overall
reasoning quality. Extensive experiments on mainstream
benchmarks demonstrate that ThinkDeception establishes a new SOTA, significantly outperforming existing methods in both detection accuracy and rationale quality. Ultimately, this work successfully drives the field of deception detection toward interpretable,
multimodal cognitive
reasoning.
Read the full abstract ▾
All authors Jinhao Song, Shan Liang, Yiqun Yue, Zhuhuayang Zhang, Tianqi Gao
Artificial Intelligence · Cross-listed from cs.CL
Beyond Tokenization: Direct Timestep Embedding and Contrastive Alignment for Time-Series Question Answering
Yafeng Wu, Huu Hiep Nguyen, Thin Nguyen et al. (+1 more)
Recent advances in large
language models (LLMs) have given rise to time-series question answering (TSQA), which formulates time-series analysis as natural-
language question answering. However, directly feeding raw numerical series into LLMs suffers from a tokenization bottleneck: Byte Pair Encoding fragments continuous values into unstable
tokens whose
embeddings lack meaningful metric structure, resulting in the loss of magnitude, scale, and trend information. Prior methods use patch-based encoders that split the series into fixed windows, locking in one granularity that breaks patterns and hides exact timesteps, through a separate module that rarely transfers across
datasets with different lengths or sampling rates. To address this challenge, we propose CADE (Contrastive
Alignment with Direct
Embedding), a novel framework for TSQA built upon two key components: direct timestep
embedding and semantic
alignment. The proposed framework maps each timestep directly into the LLM
embedding space through a point-wise linear encoder and MLP projector, preserving exact index-level access while eliminating the need for patching and padding. To further bridge the semantic gap between time-series and
language representations, we introduce a novel one-directional supervised contrastive loss that aligns time-series
embeddings with frozen class-name text anchors. Experimental results on the public Time-MQA
benchmark demonstrate that our framework consistently improves performance across six TSQA tasks, outperforming both open-source and proprietary LLM baselines.
Read the full abstract ▾
All authors Yafeng Wu, Huu Hiep Nguyen, Thin Nguyen, Hung Le
Artificial Intelligence · Cross-listed from cs.SE
CAPRA: Scaling Feedback on Software Architecture Deliverables with a Multi-Agent LLM System
Marco Becattini, Niccolò Caselli, Matteo Minin et al. (+2 more)
Automated assessment in software engineering education has advanced significantly for code grading and essay scoring. However, reviewing software architecture deliverables, which requires analyzing structural completeness and requirements traceability, has not yet been fully automated. Applying Large
Language Models (LLMs) to this task requires robust architectures to ensure technical feedback is accurate and reliable for students. This paper presents CAPRA (Configurable Architecture Proficiency Report Assessment), a multi-
agent LLM system that analyzes software architecture deliverables to generate personalized, template-compliant LaTeX feedback. As a core design choice, CAPRA coordinates multiple specialized
agents and employs a Python-based microservice for multi-modal document extraction, utilizing PyMuPDF and
vision-enabled LLMs (specifically gpt-4o) to parse text and UML diagrams. To ensure educational reliability and mitigate
hallucinations, CAPRA introduces a deterministic Evidence Anchoring step using fuzzy matching via normalized Levenshtein distance, along with a ConsistencyManager
agent that cross-verifies, deduplicates, and merges findings. System performance is assessed using a structured eight-criterion binary evaluation taxonomy covering: (i) extraction completeness, (ii) feature validation, (iii) issue grounding and severity detection, (iv) recommendation specificity and traceability, and (v) template and tone compliance. A preliminary empirical evaluation on 10 student reports shows that CAPRA satisfied 88.8% of the evaluated criteria under a strict two-rater aggregation rule, achieved moderate inter-rater agreement with human evaluators (kappa = 0.582), and processed each report in slightly over 4 minutes. While these results support the viability of LLM-supported architectural feedback, human oversight remains essential for subjective assessment dimensions.
Read the full abstract ▾
All authors Marco Becattini, Niccolò Caselli, Matteo Minin, Roberto Verdecchia, Enrico Vicario
Artificial Intelligence · Cross-listed from cs.LG
A Controlled Benchmark of Quantum-Latent GAN Augmentation for Brain MRI
Syed Mujtaba Haider and Silvia Figini
Medical image classification is often constrained by limited labeled data, motivating generative augmentation; recently,
quantum generative models have been proposed for this purpose, frequently reporting accuracy gains. However, such claims are typically based on single training runs, do not match the parameter budgets of the
quantum and classical generators, and do not characterize the data regime in which any benefit appears. We present a controlled
benchmark that isolates the contribution of a
quantum generator to
brain-MRI augmentation. Images are encoded into a KL-regularized latent space in which a conditional Wasserstein GAN with gradient penalty is trained using either a variational
quantum generator or a classical generator of near-identical parameter count (1648 vs. 1632). Synthetic samples are decoded and used to augment a pretrained classifier across labeled data fractions from 5% to 100%, evaluated over eight random seeds with paired significance testing (with multiple-comparison correction) and with intraset diversity and latent-distribution analyses. Across all fractions, no augmentation variant significantly outperforms real-data-only training, and the
quantum and classical generators are statistically indistinguishable. Any low-data benefit behaves as regularization rather than faithful data expansion:synthetic samples are off distribution and severely mode collapsed precisely where data is scarce, and the
quantum generator is no more diverse thanits classical counterpart. We release the protocol as a testbed for rigorous evaluation of
quantum generative augmentation in medical imaging.
Read the full abstract ▾