# Research Papers — 2026-05 · bundle page 319 of 326 > Full-text markdown of papers #15901–15950 of 16266 published in 2026-05, newest first. AI-readable mirrors of the full 16266-paper 2026-05 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-05/page/319 [← Previous bundle](https://aipod.dev/papers/archive/2026-05/page/318.md) [Next bundle →](https://aipod.dev/papers/archive/2026-05/page/320.md) ### AgentStop: Terminating Local AI Agents Early to Save Energy in Consumer Devices Authors: Dzung Pham, Kleomenis Katevas, Ali Shahin Shamsabadi, Hamed Haddadi Published: 2026-05-01 Categories: cs.LG, cs.AI, cs.DC arXiv: https://arxiv.org/abs/2605.15206v1 Autonomous agents powered by large language models (LLMs) are increasingly used to automate complex, multi-step tasks such as coding or web-based question answering. While remote, cloud-based agents offer scalability and ease of deployment, they raise privacy concerns, depend on network connectivity, and incur recurring API costs. Deploying agents locally on user devices mitigates these issues by preserving data privacy and eliminating usage-based fees. However, agentic workflows are far more resource-intensive than typical LLM interactions. Iterative reasoning, tool use, and failure retries substantially increase token consumption, often expending significant compute without successfully completing tasks. In this work, we investigate the time, token, and energy overhead of locally deployed LLM-based agents on consumer hardware. Our measurements show that agentic execution increases GPU power draw, temperature, and battery drain compared to single-inference workloads. To address this inefficiency, we introduce AgentStop, a lightweight efficiency supervisor that predicts and preemptively terminates trajectories unlikely to succeed. Leveraging low-cost execution signals, such as token-level log probabilities, AgentStop can reduce wasted energy by 15-20% with minimal impact on task performance (<5% utility drop) for challenging web-based question answering and coding benchmarks. These findings position predictive early termination as a practical mechanism for enabling sustainable, privacy-preserving LLM agents on user devices. Our project code and data are available at https://github.com/brave-experiments/AgentStop. --- ### AgenticAITA: A Proof-Of-Concept About Deliberative Multi-Agent Reasoning for Autonomous Trading Systems Authors: Ivan Letteri Published: 2026-05-01 Categories: q-fin.TR, cs.AI, stat.ME arXiv: https://arxiv.org/abs/2605.12532v1 Conventional algorithmic trading systems are grounded in deterministic heuristics or offline-trained statistical models that cannot adapt to the semantic complexity of rapidly shifting market regimes. This paper introduces AGENTICAITA, an agentic AI framework that replaces the traditional signal then execute paradigm with a fully autonomous deliberative loop in which multiple specialized Large Language Model agents reason, negotiate, and act in concert - without any offline training or human intervention. The framework proposes four architectural contributions: (i) an Adaptive Z-Score Trigger Engine that acts as a cognitive resource allocator, gating LLM inference exclusively on statistically anomalous market conditions; (ii) a Sequential Deliberative Pipeline - the core agentic contribution - in which an Analyst agent, a Risk Manager agent, and an Executor agent form a structured reasoning chain governed by typed JSON contracts and a deterministic hard-gate safety layer; (iii) an Inference Gating Protocol, a mutex-based cognitive resource scheduler that serializes concurrent agent activations and ensures fully reproducible audit trails; and (iv) a Correlation-Break Diversification composite score that operationalizes portfolio-level idiosyncratic signal prioritization within individual agent reasoning. Validated over a five-day autonomous dry-run session under live market conditions, the framework demonstrates operational correctness of the deliberative pipeline, achieving 157 zero-intervention invocations across 76 assets with an 11.5% agentic friction rate that confirms non-trivial inter-agent negotiation. This preliminary proof-of-concept establishes the feasibility of training-free, deterministic safety-constrained multi-agent orchestration in financial decision loops, with statistically robust performance evaluation and execution cost modeling deferred to extended live deployment. --- ### Benchmarking ResNet Backbones in RT-DETR: Impact of Depth and Regularization under environmental conditions Authors: Pamela Barboza, Víctor Castelli, Belén Pereira, Ricardo Grando, Bruna de Vargas, Augusto Calfani Published: 2026-05-01 Categories: cs.CV, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2605.08136v1 Visual perception plays a central role in competitive robotics, where environmental variations can directly affect real-time detection performance. The related literature on transformer-based detectors lack information regarding the impact of backbone scale and environmental settings on model performance. This work presents a comparative evaluation of RT-DETR for detecting round objects under environmental and hyperparameter variations relevant to competitive robotics. Four ResNet backbones (ResNet18, ResNet34, ResNet50, and ResNet101) were compared using dropout rates, analyzing their effect on confidence and accuracy. All models were trained under the same configuration and evaluated under changes in lighting and background contrast. Environmental conditions primarily impact prediction confidence, while inference latency remains largely unaffected and classification accuracy stays consistently high, approaching or above 1.00 in most cases. Two distinct behaviors were observed. Under illumination variation, ResNet50 achieves the best trade-off, combining near-perfect accuracy, confidence values up to approximately 0.869 and latency around 0.058-0.059 ms. Under background variation, ResNet34 provides the most balanced performance, reaching near-perfect accuracy and higher confidence values up to approximately 0.887. These results indicate that the optimal architecture depends on the type of environmental variation, with intermediate-depth models offering the best balance between performance and efficiency. --- ### Dendritic Neural Networks with Equilibrium Propagation Authors: Yoshimasa Kubo Published: 2026-05-01 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.08135v1 Equilibrium propagation (EP) is a biologically plausible alternative to backpropagation (BP), but its effectiveness can degrade in deeper and more challenging learning settings. In parallel, dendritic neural networks have demonstrated improved performance and generalization when trained with BP, suggesting that structured, biologically inspired architectures may enhance learning. In this work, we investigate the integration of dendritic neural networks with equilibrium propagation using an advanced EP framework. We evaluate the proposed dendritic EP model on MNIST, Kuzushiji-MNIST (KMNIST), and Fashion-MNIST (FMNIST), considering both shallow and deeper architectures. Our results show that dendritic EP achieves performance comparable to standard EP on simple tasks, while providing consistent improvements on more challenging datasets and deeper models. In particular, dendritic EP significantly outperforms standard EP on KMNIST and FMNIST, and approaches the performance of dendritic networks trained with backpropagation through time.To further understand these improvements, we analyze the evolution of hidden states during the free phase. We observe that dendritic EP exhibits higher activation magnitudes and more distributed hidden-state activity compared to standard EP, indicating that dendritic structure alters the internal network dynamics. These findings suggest that incorporating dendritic structure can enhance the effectiveness of biologically plausible learning algorithms, especially in regimes where standard EP struggles. Our work highlights the importance of architectural design for improving biologically inspired training methods. --- ### DARE: Diffusion Language Model Activation Reuse for Efficient Inference Authors: Natalia Frumkin, Bokun Wang, Hung-Yueh Chiang, Chi-Chih Chang, Mohamed S. Abdelfattah, Diana Marculescu Published: 2026-05-01 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.08134v1 Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to auto-regressive (AR) models, offering greater expressive capacity and potential for parallel generation and faster inference. However, open-source dLLMs remain immature, lagging behind AR models in both efficiency and quality. We identify an underexplored property of dLLMs: *token-wise redundancy* in bi-directional self-attention. Self-attention activations are highly correlated across tokens, and temporal changes in query representations can predict redundancy in corresponding key, value, and output activations. We introduce DARE, with two complementary mechanisms: DARE-KV, which reuses cached key-value (KV) activations, and DARE-O, which reuses output activations to reduce redundant computation while preserving quality. DARE achieves up to 1.20x per-layer latency reduction and reuses up to 87% of attention activations, with negligible degradation on reasoning and code-generation benchmarks. DARE-KV and DARE-O incur average performance drops of only 2.0% and 1.2%, respectively. Combined with techniques such as prefix caching and Fast-dLLM, DARE provides additive gains without retraining. These results establish token-wise reuse as an effective strategy for improving the efficiency of diffusion-based LLMs while preserving generation fidelity. Code: https://github.com/enyac-group/DARE --- ### VLADriver-RAG: Retrieval-Augmented Vision-Language-Action Models for Autonomous Driving Authors: Rui Zhao, Haofeng Hu, Zhenhai Gao, Jiaqiao Liu, Gao Fei Published: 2026-05-01 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.08133v2 Vision-Language-Action (VLA) models have emerged as a promising paradigm for end-to-end autonomous driving, yet their reliance on implicit parametric knowledge limits generalization in long-tail scenarios. While Retrieval-Augmented Generation (RAG) offers a solution by accessing external expert priors, standard visual retrieval suffers from high latency and semantic ambiguity. To address these challenges, we propose \textbf{VLADriver-RAG}, a framework that grounds planning in explicit, structure-aware historical knowledge. Specifically, we abstract sensory inputs into spatiotemporal semantic graphs via a \textit{Visual-to-Scenario} mechanism, effectively filtering visual noise. To ensure retrieval relevance, we employ a \textit{Scenario-Aligned Embedding Model} that utilizes Graph-DTW metric alignment to prioritize intrinsic topological consistency over superficial visual similarity. These retrieved priors are then fused within a query-based VLA backbone to synthesize precise, disentangled trajectories. Extensive experiments on the Bench2Drive benchmark establish a new state-of-the-art, achieving a Driving Score of 89.12. --- ### Interactive Inverse Reinforcement Learning of Interaction Scenarios via Bi-level Optimization Authors: Yue Mao, Shicheng Liu, Siyuan Xu, Minghui Zhu Published: 2026-05-01 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.08131v1 Inverse reinforcement learning (IRL) learns a reward function and a corresponding policy that best fit the demonstration data of an expert. However, in the current IRL setting, the learner is isolated from the expert and can only passively observe the expert demonstrations. This limits the applicability of IRL to interactive settings, where the learner actively interacts with the expert and needs to infer the expert's reward function from the interactions. To bridge the gap, this paper studies interactive IRL (IIRL) where a learner aims to learn the reward function of an expert and a policy to interact with the expert during its interactions with the expert. We formulate IIRL as a stochastic bi-level optimization problem where the lower level learns a reward function to explain the behaviors of the expert, and the upper level learns a policy to interact with the expert. We develop a double-loop algorithm, Bi-level Interactive Scenarios Inverse Reinforcement Learning (BISIRL), which solves the lower-level problem in the inner loop and the upper-level problem in the outer loop. We formally guarantee that BISIRL converges and validate our algorithm through extensive experiments. --- ### Additive Atomic Forests for Symbolic Function and Antiderivative Discovery Authors: Reda Belaiche Published: 2026-05-01 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.08130v1 We present a framework for the simultaneous symbolic recovery of a function and its antiderivative from data. The framework rests on three ideas. First, a derivative algebra: the observation that the product rule $\frac{d}{dx}(f \cdot g) = f'g + fg'$ and the chain rule, applied to a seed set of elementary functions, generate a self-expanding system of function-derivative pairs -- a living library that grows each time a new function is discovered. Second, two complementary primitives -- EML$\,(e^u - \ln v)$, which is theoretically complete for all elementary functions, and SOL$\,(\sin u - \cos v)$, introduced here, which makes trigonometric atoms available at depth~1 instead of depth~$\sim$8 -- that seed the library with core atoms cheaply. Third, additive atomic forests: finite sums of primitive trees, optionally composed via multiplicative nodes, whose derivatives are fitted to data by continuous optimisation or by exhaustive search over the library. Because differentiation of each atom is determined by construction, the forest simultaneously encodes a symbolic expression $F$ and its derivative $F'$; no symbolic integration step is required. The library is not a fixed object: it self-constructs from a small seed set by recursive application of the product rule, chain rule, and the two primitives, and it can grow as newly discovered functions are folded back in. The larger the library, the richer the expressible class of candidate functions. We give conditional completeness, additive-depth, and analytic simultaneous-recovery results for the framework. Empirically, in our reported runs on 17 classification benchmarks, sparse atom combinations match or exceed XGBoost on 13 datasets while producing interpretable formulas. --- ### Towards Customized Multimodal Role-Play Authors: Chao Tang, Jianzong Wu, Qingyu Shi, Ye Tian, Aixi Zhang, Hao Jiang, Jiangning Zhang, Yunhai Tong Published: 2026-05-01 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.08129v1 Unified multimodal understanding and generation models enable richer human-AI interaction. Yet jointly customizing a character's persona, dialogue style, and visual identity while maintaining output consistency across modalities remains largely unexplored. To mitigate this gap, we introduce a new task, Customized Multimodal Role-Play (CMRP). We construct the RoleScape-20 dataset comprising 20 characters, including training and evaluation data that cover persona, stylistic descriptions, visual/expressive cues, and text-image interactions. Building on a unified model, we devise UniCharacter, a two-stage training framework containing Unified Supervised Finetuning (Unified-SFT) and character-specific group relative policy optimization (Character-GRPO). Given only 10 images plus corresponding interaction examples, the model acquires the target character and exhibits coherent persona, style, and visual identity in both generated text and images. This process takes about 100 GPU hours. Experiments on the RoleScape-20 dataset show that the proposed method substantially outperforms prior approaches. Ablation studies further validate the effectiveness of our cross-modal consistency design and few-shot customization strategy. We argue that CMRP, coupled with unified modeling, provides a basis for next-generation characterful and immersive interactive agents. --- ### Towards Universal Gene Regulatory Network Inference: Unlocking Generalizable Regulatory Knowledge in Single-cell Foundation Models Authors: Jiaxin Qi, Hang Li, Yan Cui, Yuhua Zheng, Jianqiang Huang Published: 2026-05-01 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.08128v1 Gene Regulatory Network (GRN) inference is essential for understanding complex cellular mechanisms, rendered tractable through single-cell transcriptomic data. With the emergence of single-cell Foundation Models (scFMs), enhanced transcriptomic encoding is widely expected to revolutionize GRN inference. However, we observe that their performance remains far from satisfactory. The primary reason is that the standard reconstruction-based pre-training objectives often fail to explicitly capture latent regulatory signals. To bridge this gap, we first introduce a GRN generalization benchmark designed to evaluate regulatory predictions on unseen genes and datasets, which relies on the zero-shot capabilities of scFMs and is inherently challenging for traditional methods. Furthermore, to unlock the regulatory knowledge within the foundation models, we propose two novel methods, Virtual Value Perturbation and Gradient Trajectory, to distill implicit regulatory information from scFMs into highly generalizable inter-gene features. Extensive experiments demonstrate that our approach significantly outperforms existing methods, establishing a new paradigm for leveraging the potential of scFMs in universal GRN inference. --- ### Topology-Driven Anti-Entanglement Control for Soft Robots Authors: Haoyang Le, Shengxuan Wang, Mohan Chen, Shuo Feng Published: 2026-05-01 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2605.05236v2 In the field of precision manufacturing in complex constrained environments, the role of soft robots is increasingly prominent, and the realization of anti-winding control based on multi-intelligent body reinforcement learning has become a research hotspot. One of the core problems at present is to coordinate multiple robots to complete the unwinding operation in a highly constrained environment. The existing distributed training framework faces some observability challenges in high-density barrier and unstable environments, resulting in poor learning results. This paper proposes a topology-driven Multi-Agent Reinforcement Learning (TD-MARL) framework to coordinate multi-robot systems to avoid entanglement. Specifically, the critical network adopts centralized learning, so that each intelligent body can perceive the strategies of other intelligent bodies by sharing the topological state, thus alleviating the training instability caused by complex interactions; eliminating the demand for communication resources between robots through distributed execution, Upgrade system reliability; the integrated topological security layer uses topological invariants to accurately assess and mitigate the risk of entanglement to avoid the strategy from falling into local difficulties. Finally, the full simulation experiments carried out in the real simulation environment show that the method is better than the current advanced deep reinforcement learning (DRL) method in terms of convergence and anti-winding effect. --- ### Topology-Driven Anti-Entanglement Control for Soft Robots Authors: Haoyang Le, Shengxuan Wang, Mohan Chen, Shuo Feng Published: 2026-05-01 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2605.05236v1 In the field of precision manufacturing in complex constrained environments, the role of soft robots is increasingly prominent, and the realization of anti-winding control based on multi-intelligent body reinforcement learning has become a research hotspot. One of the core problems at present is to coordinate multiple robots to complete the unwinding operation in a highly constrained environment. The existing distributed training framework faces some observability challenges in high-density barrier and unstable environments, resulting in poor learning results. This paper proposes a topology-driven Multi-Agent Reinforcement Learning (TD-MARL) framework to coordinate multi-robot systems to avoid entanglement. Specifically, the critical network adopts centralized learning, so that each intelligent body can perceive the strategies of other intelligent bodies by sharing the topological state, thus alleviating the training instability caused by complex interactions; eliminating the demand for communication resources between robots through distributed execution, Upgrade system reliability; the integrated topological security layer uses topological invariants to accurately assess and mitigate the risk of entanglement to avoid the strategy from falling into local difficulties. Finally, the full simulation experiments carried out in the real simulation environment show that the method is better than the current advanced deep reinforcement learning (DRL) method in terms of convergence and anti-winding effect. --- ### Are Multimodal LLMs Ready for Clinical Dermatology? A Real-World Evaluation in Dermatology Authors: Roy Jiang, Hyunjae Kim, Zhenyue Qin, Morten Lee, Margaret MacGibeny, Ailish Hanly, Angela Sadlowski, Shanin Chowdhury, Xuguang Ai, Jeffrey Gehlhausen, Qingyu Chen Published: 2026-05-01 Categories: cs.CV, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2605.04098v1 Multimodal large language models (MLLMs) have demonstrated promise on publicly available dermatology benchmarks. However, benchmark performance may not generalize to real-world dermatologic decision-making. To quantify this benchmark-to-bedside gap, we evaluated four open-weight MLLMs (InternVL-Chat v1.5, LLaVA-Med v1.5, SkinGPT4 and MedGemma-4B-Instruct) and one commercial MLLM (GPT-4.1) across three publicly available dermatology datasets and a retrospective multi-site hospital-based dermatology consultation cohort comprising 5,811 cases and 46,405 clinical images. Models were evaluated on two clinically relevant tasks: differential diagnosis generation and severity-based triage. Diagnostic performance was modest on public datasets and declined substantially in the real-world cohort. On public benchmarks, top-3 diagnostic accuracy reached 26.55% for the best open-weight model and 42.25% for GPT-4.1. On real-world consultation cases using images alone, top-3 diagnostic accuracy fell to 1.50%-13.35% among open-weight models and 24.65% for GPT-4.1. Incorporating clinical context improved performance across all models, increasing top-3 diagnostic accuracy up to 28.75% among open-weight models and 38.93% for GPT-4.1. However, model outputs were highly sensitive to incomplete or erroneous consultation context. For severity-based triage, models achieved moderate sensitivity (above 60%), suggesting potential utility for screening but insufficient reliability for clinical deployment. These findings demonstrate that benchmark performance substantially overestimates the real-world clinical capability of current dermatology MLLMs. --- ### Kernel Affine Hull Machines as Compute-Efficient Encoders for Frozen Semantic Spaces Authors: Mohit Kumar, Somayeh Kargaran, Bernhard A. Moser, Manuela Geiß Published: 2026-05-01 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.02950v2 Transformer-based semantic encoders are effective for retrieval, but in many deployments the recurring bottleneck is online query encoding rather than offline corpus indexing. This paper studies whether, once a strong teacher representation space and corpus index are fixed, repeated neural query encoding can be replaced by a substantially lighter and analytically explicit estimator. We formulate fixed-teacher lexical-to-semantic encoding as a conditional-mean estimation problem in which the target semantic vector is represented as a noisy mixture of semantic prototypes weighted by posterior cluster probabilities. Kernel Affine Hull Machine (KAHM) geometry is used to estimate these posterior weights from inexpensive lexical features in an explicitly identified RKHS hypothesis space, and the semantic prototypes are refined by normalized least-mean-squares updates from noisy teacher embeddings. This yields a backpropagation-free query-side encoder together with an end-to-end error decomposition into posterior-approximation, finite-sample/generalization, and teacher-noise terms. We instantiate the approach on a controlled Austrian-law retrieval benchmark with 5,000 test queries, 84 candidate laws, and 10,762 aligned retrieval units, using law-specific encoders into a frozen Mixedbread embedding space. Among evaluation-matched learned adapters, KAHM achieves the strongest teacher-space reconstruction and the best rank-sensitive retrieval performance at all evaluated cutoffs. At k=20, it obtains MRR@20 = 0.504, Hit@20 = 0.694, and Top-1 Accuracy = 0.411, while reducing online per-query time by 8.53 relative to direct transformer query encoding in the reported CPU setting. The results support KAHMs as compute-efficient encoders for supervised fixed-representation deployment regimes. --- ### Disease Is a Spectral Perturbation Authors: John D. Mayfield, Matthew S. Rosen Published: 2026-05-01 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2605.02949v1 We propose a novel method of understanding disease transformation from a healthy baseline with biomarker-level explainability. By modeling the biomarker covariance matrices of healthy controls and disease states, the perturbation can be individually characterized to accomplish mechanistic explanations of disease trajectories, both at a molecular level and for individual patients. Given a cohort of n patients each measured on p biomarkers, we define the biomarker "Hamiltonian" H = X^T X / n \in R^{p \times p}, where X \in R^{n \times p} is the covariant biomarker matrix. The eigenvectors of H define a set of normal modes of biomarker coordination, and the eigenvalues quantify the energy carried by each mode. In the healthy state, the reference Hamiltonian H_0 governs this structure where disease perturbs H_0 by an additive operator ΔH, thus shifting eigenvalues and rotating eigenvectors in proportion to the severity of pathological disruption. We formalize this framework, derive the spectral change given a disease perturbation, and demonstrate that the projection of a newly diagnosed patient's cumulative biomarker covariance structure onto disease-discriminant eigenmodes constitutes an optimal prognostic statistic for greater precision in disease prognosis. This work serves as a veritable white paper with application across a panoply of disease frameworks from cancer to neurodegenerative disorders. --- ### AsymTalker: Identity-Consistent Long-Term Talking Head Generation via Asymmetric Distillation Authors: Yuxin Lu, Jiayang Sun, Guibo Zhu, Min Cao Published: 2026-05-01 Categories: cs.LG, cs.AI, cs.SD arXiv: https://arxiv.org/abs/2605.02948v3 Diffusion-based talking head generation has achieved remarkable visual quality, yet scaling it to long-term videos remains challenging. The widely adopted chunk-wise paradigm introduces two fundamental failures: (1) temporal-spatial misalignment between static identity references and dynamic audio streams, and (2) cascading identity drift propagated through self-generated continuity references across chunks. To address both issues, we propose AsymTalker, a novel diffusion-based talking head generation method comprising Temporal Reference Encoding (TRE) and Asymmetric Knowledge Distillation (AKD). First, TRE mitigates temporal-spatial misalignment by transforming the static identity image into a temporally coherent latent representation through encoding of a temporally replicated pseudo-video, without introducing additional parameters. Second, AKD resolves the inherent conditioning dilemma in chunk-wise training: using ground-truth references causes train-inference mismatch, while self-generated references entangle supervision with identity drift. Our asymmetric design circumvents this by anchoring the teacher model with ground-truth continuity references to provide drift-free, chunk-level supervision, thereby avoiding the teacher bottleneck. Meanwhile, the student model learns under inference-aligned conditions, conditioned only on self-generated references, and is trained via distribution matching to preserve identity over long horizons. Extensive experiments show AsymTalker achieves state-of-the-art results on HDTF and VFHQ. It guarantees high-fidelity, identity-consistent synthesis over 600-second videos and reaches a real-time inference speed of 66 FPS. --- ### Predicting Euler Characteristics and Constructing Topological Structure Using Machine Learning Techniques Authors: Gyunghun Yu, Seong Min Park, Han Gyu Yoon, Tae Jung Moon, Jun Woo Choi, Hee Young Kwon, Changyeon Won Published: 2026-05-01 Categories: cs.LG, cond-mat.mtrl-sci, cs.AI, physics.comp-ph arXiv: https://arxiv.org/abs/2605.02947v1 This study proposes a novel approach to extract topological properties, specifically the Euler characteristic, from input images using neural networks without relying on large pre-existing datasets but with a single geometric image. Inspired by solid-state physics, where topological properties of magnetic structures are derived from spin field analysis, our model generates a unit vector field from an image, interpreted as a spin configuration. The Euler characteristic is then predicted by computing the skyrmion number of this generated spin configuration. Remarkably, the network learns to construct chiral magnetic textures without access to ground-truth chiral spin configurations, relying instead on only a single, simple geometric image and the straightforward skyrmion number computation. Furthermore, spin configurations generated by independently trained networks can be non-unique due to inherent degrees of freedom. To constrain these degrees of freedom and further refine the spin configuration, we incorporate a magnetic Hamiltonian, comprising exchange interaction, Dzyaloshinskii-Moriya (DM) interaction, and anisotropy, as an additional, physics-informed loss function. We validate the model's efficacy on complex geometrical shapes and demonstrate its applicability to practical tasks. --- ### RouteHijack: Routing-Aware Attack on Mixture-of-Experts LLMs Authors: Zhiyuan Xu, Joseph Gardiner, Sana Belguith, Lichao Wu Published: 2026-05-01 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.02946v1 Safety alignment is critical for the responsible deployment of large language models (LLMs). As Mixture-of-Experts (MoE) architectures are increasingly adopted to scale model capacity, understanding their safety robustness becomes essential. Existing adversarial attacks, however, have notable limitations. Prompt-based jailbreaks rely on heuristic search and transfer poorly, model intervention methods require privileged access to internal representations, and optimization-based input attacks remain output-centric and are fundamentally limited to MoE models due to the non-differentiable routing mechanism. In this paper, we present RouteHijack, a routing-aware jailbreak for MoE LLMs. Our key insight is that safety behavior is concentrated in a small subset of experts, creating an opportunity to steer model behavior by influencing routing decisions through input optimization. Building on this observation, RouteHijack first performs response-driven expert localization to identify safety-critical and harmful experts by contrasting activations under safe refusals and harmful completions. It then constructs adversarial suffixes with a routing-aware objective that suppresses safety experts, promotes harmful experts, and prevents early-stage refusal during generation. At inference time, the optimized suffix is appended to a malicious prompt, requiring only input access. Across seven MoE LLMs, RouteHijack achieves a 69.3\% average attack success rate (ASR), outperforming prior optimization-based attack by $3.2\times$. RouteHijack also transfers zero-shot across five sibling MoE variants, raising average ASR from 27.7\% to 61.2\%, and further generalizes to three MoE-based VLMs, increasing average ASR from 2.47\% to 38.7\%. These findings expose a fundamental vulnerability in sparse expert architectures and highlight the need for defenses beyond output-level alignment. --- ### Exploring Pass-Rate Reward in Reinforcement Learning for Code Generation Authors: Xin-Ye Li, Ren-Biao Liu, Yun-Ji Zhang, Hui Sun, Zheng Xie, Ming Li Published: 2026-05-01 Categories: cs.LG, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2605.02944v1 Reinforcement learning (RL) from unit-test feedback has become a standard post-training recipe for improving large language models (LLMs) on code generation. However, the pass-all-tests binary reward can be sparse, yielding no learning signal on challenging problems where none of the sampled solutions passes all tests. A common remedy is to use the test-case pass rate as a surrogate reward. In this work, we study pass-rate rewards in critic-free RL for code generation (e.g., GRPO and RLOO) and report a consistent pattern across base models and algorithms: despite alleviating reward sparsity, pass-rate rewards do not reliably improve final performance over binary rewards in rigorous controlled experiments. To understand this discrepancy, we analyze reward density and the resulting gradient directions. We find that pass-rate rewards are denser, but the induced gradient updates do not consistently move probability mass toward full-pass solutions. This arises because test-case pass rate is a miscalibrated surrogate for progress toward full correctness, and partial-pass solutions within the same group can induce conflicting gradient directions that cancel out. Overall, our results suggest that, in critic-free RL, pass-rate rewards are insufficient to improve code generation and motivate reward designs that better align optimization with the goal of full correctness. --- ### Healthcare AI GYM for Medical Agents Authors: Minbyul Jeong Published: 2026-05-01 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.02943v1 Clinical reasoning demands multi-step interactions -- gathering patient history, ordering tests, interpreting results, and making safe treatment decisions -- yet a unified training environment provides the breadth of clinical domains and specialized tools to train generalizable medical AI agents through reinforcement learning remains elusive. We present a comprehensive empirical study of multi-turn agentic RL for medical AI, built on \gym{}, a gymnasium-compatible environment spanning 10 clinical domains with 3.6K+ tasks, 135 domain-specific tools, and a knowledge base of 828K medical passages. Our analysis reveals that agentic multi-turn structure degrades into verbose single-turn monologues, characterized by monotonic length explosion and a simultaneous erosion of tool-use frequency. We characterize how this collapse, alongside distillation instability, stems from the misalignment of sparse terminal rewards with sequential clinical trajectories. We find that vanilla GRPO achieves strong final accuracy on some benchmarks but suffers from training instability, evidenced by significant oscillations in response length and prolonged convergence periods. To improve training efficiency and stability, we propose Turn-level Truncated On-Policy Distillation (TT-OPD), a self-distillation framework where a gradient-free EMA teacher leverages outcome-privileged information to provide dense, outcome-aware KL regularization at every conversation turn. TT-OPD achieves the best performance on 10 of 18 benchmarks with an average +3.9~pp improvement over the non-RL baseline with faster early convergence, controlled response length, and sustained multi-turn tool use. --- ### Intersectional Disentangling of Temporal and Acquisition Bias in Fetal Ultrasound Authors: Aya Elgebaly, Joris Fournel, Benjamin Laine Jønch Jurgensen, Kamil Mikolaj, Anders Christensen, Martin Tolsgaard, Claes Ladefoged, Aasa Feragen Published: 2026-05-01 Categories: cs.LG, cs.CV, eess.IV arXiv: https://arxiv.org/abs/2605.02942v3 Fairness studies of medical imaging AI often explain subgroup performance gaps through under-representation in the training data. We show that intersectional analysis can disentangle fairness and performance gaps arising from clinical and acquisition confounders that co-vary with the target. As a case, we study scan-time fetal weight estimation from obstetric ultrasound, analyzing two models: a state-of-the-art deep learning (DL) model and the clinical gold-standard Hadlock formula. Using unsupervised slice discovery, we find that high-error subgroups share extreme in the image-acquisition pixel spacing (PS) and in the scan-to-delivery (STD) interval. Of these, PS is an acquisition parameter that can be optimized, while STD is a potential confounder for both PS and our bias diagnostics. Subgroup inspection alone cannot separate them. We disentangle the factors using a model-agnostic analysis with identical metadata partitions and partial regression. Holding STD fixed, the apparent PS effect collapses to a small residual (standardized coefficient $β=-0.17$), whereas holding PS fixed, STD dominates error ($β=+0.56$). Both models degrade with increasing STD, including the biometric formula, indicating much of the error is intrinsic to the prediction target rather than imaging. The DL model is $\sim$1.5$\times$ more sensitive to STD than Hadlock, though it remains more accurate in every subgroup. We conclude that fairness analyses need to carefully analyze potential confounds, or risk attributing an effect such as temporal or acquisition-related dependency to demographics. --- ### Intersectional Disentangling of Temporal and Acquisition Bias in Fetal Ultrasound Authors: Aya Elgebaly, Joris Fournel, Benjamin Laine Jønch Jurgensen, Kamil Mikolaj, Anders Christensen, Martin Tolsgaard, Claes Ladefoged, Aasa Feragen Published: 2026-05-01 Categories: cs.LG, cs.CV, eess.IV arXiv: https://arxiv.org/abs/2605.02942v2 Fairness studies of medical imaging AI often explain subgroup performance gaps through under-representation in the training data. We show that intersectional analysis can disentangle fairness and performance gaps arising from clinical and acquisition confounders that co-vary with the target. As a case, we study scan-time fetal weight estimation from obstetric ultrasound, analyzing two models: a state-of-the-art deep learning (DL) model and the clinical gold-standard Hadlock formula. Using unsupervised slice discovery, we find that high-error subgroups share extreme in the image-acquisition pixel spacing (PS) and in the scan-to-delivery (STD) interval. Of these, PS is an acquisition parameter that can be optimized, while STD is a potential confounder for both PS and our bias diagnostics. Subgroup inspection alone cannot separate them. We disentangle the factors using a model-agnostic analysis with identical metadata partitions and partial regression. Holding STD fixed, the apparent PS effect collapses to a small residual (standardized coefficient $β=-0.17$), whereas holding PS fixed, STD dominates error ($β=+0.56$). Both models degrade with increasing STD, including the biometric formula, indicating much of the error is intrinsic to the prediction target rather than imaging. The DL model is $\sim$1.5$\times$ more sensitive to STD than Hadlock, though it remains more accurate in every subgroup. We conclude that fairness analyses need to carefully analyze potential confounds, or risk attributing an effect such as temporal or acquisition-related dependency to demographics. --- ### PrismAgent: Illuminating Harm in Memes via a Zero-Shot Interpretable Multi-Agent Framework Authors: Zihan Ding, Ziyuan Yang, Yi Zhang Published: 2026-05-01 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.02940v1 The rapid spread of memes makes harmful content detection increasingly crucial, as effective identification can curb the circulation of misinformation. However, existing methods rely heavily on high-volume annotated data, which leads to substantial training costs and limited generalization. To address these challenges, we propose PrismAgent, a zero-shot, multi-agent, interpretable framework. PrismAgent conceptualizes this task as a criminal case investigation, employing four specialized agents responsible for the analysis, investigation, prosecution, and judgment stages within a structured collaborative workflow. In the first stage, the analyst agent paraphrases each meme under benevolent and malicious assumptions to probe its underlying intent. The investigator agent then retrieves supporting evidence from an unannotated dataset and constructs contextual interpretations for the meme and its variants. Next, the prosecutor agent performs three independent preliminary judgments by pairing the original meme with each of the three interpretations. Finally, the judge agent deliberates across all evidence to render a final verdict. Moreover, PrismAgent's explicit multi-stage reasoning chain makes the model inherently interpretable, as every intermediate step is explicitly explained rather than only producing a final detection result. Extensive experiments on three public datasets show that PrismAgent significantly outperforms existing zero-shot detection methods. --- ### From Static Analysis to Audience Dissemination: A Training-Free Multimodal Controversy Detection Multi-Agent Framework Authors: Zihan Ding, Ziyuan Yang, Yi Zhang Published: 2026-05-01 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.02939v1 Multimodal controversy detection (MCD) identifies controversial content in videos and their associated user comments, to support risk management for social video platforms.Prior research frames MCD as a static representation learning task, where features are directly extracted from videos and their accompanying comments. However, these methods fail to capture the diverse perspectives and evaluations from different audience groups. Inspired by the real-world process of content dissemination among audiences, we propose AuDisAgent, a training-free multi-agent framework that reformulates MCD as a dynamic propagation process.Our framework explicitly models audience dissemination through a structured multi-agent system. First, three specialized Screening Agents (Video Agent, Comment Agent, and Interaction Agent) conduct initial assessments from visual, textual, and cross-modal perspectives, respectively. For samples where the three agents cannot reach a consensus, a Viewing Panel Agent is activated to simulate post-screening discussions among audiences with diverse backgrounds and stances. This mechanism models how different audience groups interpret and react to the same content, uncovering latent controversial content that may emerge during the dissemination process. Finally, an Arbitration Agent renders the final judgment based on the complete reasoning chain from the preceding steps.In addition, to address the "cold-start" scenario where newly released videos have few or no comments, we design a Comment Bootstrapping Strategy that leverages historical public comments from semantically similar videos as the initial comment context. Extensive experiments on a public dataset demonstrate that our framework significantly outperforms existing state-of-the-art (SOTA) methods in both rich-comment and limited-comment scenarios. --- ### PAMNet: Cycle-aware Phase-Amplitude Modulation Network for Multivariate Time Series Forecasting Authors: Yingbo Zhou, Yutong Ye, Zhiwei Ling, Shuhao Li, Rui Qian, Jian Xiong, Li Sun, Dejing Dou Published: 2026-05-01 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.02938v1 Reliable periodic patterns serve as a fundamental basis for accurate multivariate time series forecasting. However, existing methods either implicitly extract periodicity through complex model architectures (e.g., Transformers) with high computational overhead or overlook the intrinsic phase-amplitude coupling when modeling periodic components explicitly. To address these issues, we propose a novel Cycle-aware Phase-Amplitude Modulation Network (PAMNet) that explicitly decomposes periodic patterns into complementary phase and amplitude components. The core innovation lies in its dual-branch modulator, featuring dedicated learnable embeddings for phase positioning and amplitude modulation. The phase branch employs cyclical embeddings to capture phase-dependent mean shifts, while the amplitude branch models intensity variations to adapt to changes in variance. A lightweight modulator with element-wise fusion efficiently combines these components, enabling explicit modeling of their interactions without complex attention mechanisms. Extensive experiments on twelve real-world datasets demonstrate that our method achieves state-of-the-art performance through its novel phase-amplitude decoupling mechanism, offering a new perspective for cyclical modeling in time series forecasting. --- ### Proteo-R1: Reasoning Foundation Models for De Novo Protein Design Authors: Fang Wu, Weihao Xuan, Heli Qi, Hanqun Cao, Heng-Jui Chang, Zeqi Zhou, Haokai Zhao, Ma Jian, Carl Ma, Yu-Chi Cheng, Kuan Pang, Xiangru Tang et al. Published: 2026-05-01 Categories: cs.LG, cs.AI, cs.CE arXiv: https://arxiv.org/abs/2605.02937v2 Deep learning in de novo protein design has achieved atomic-level fidelity. However, existing models remain largely non-deliberative: they directly synthesize molecular geometries without explicitly reasoning about which residues or interactions are functionally essential. As a result, design decisions are entangled with continuous sampling dynamics, limiting interpretability, controllability, and systematic reuse of biochemical knowledge. We introduce Proteo-R1, a reasoning-guided protein design framework that explicitly decouples molecular understanding from geometric generation. Proteo-R1 adopts a dual-expert architecture in which a multimodal large language model (MLLM) serves as an understanding expert, analyzing protein sequences, structures, and textual context to identify key functional residues that govern binding and specificity. These residue-level decisions are then passed as hard constraints to a separate diffusion-based generation expert, which performs conditional co-design while respecting the fixed interaction anchors. This factorization mirrors how human experts approach molecular engineering: first, reasoning about critical interactions, then optimizing geometry subject to those constraints. By operationalizing reasoning as explicit residue-level commitments rather than latent textual guidance, Proteo-R1 achieves stable, interpretable, and modular integration of LLM reasoning with state-of-the-art geometric generative models. Code, data, and demos are available at https://smiles724.github.io/r1/. --- ### Proteo-R1: Reasoning Foundation Models for De Novo Protein Design Authors: Fang Wu, Weihao Xuan, Heli Qi, Hanqun Cao, Heng-Jui Chang, Zeqi Zhou, Haokai Zhao, Ma Jian, Carl Ma, Yu-Chi Cheng, Kuan Pang, Xiangru Tang et al. Published: 2026-05-01 Categories: cs.LG, cs.AI, cs.CE arXiv: https://arxiv.org/abs/2605.02937v1 Deep learning in \emph{de novo} protein design has achieved atomic-level fidelity. However, existing models remain largely non-deliberative: they directly synthesize molecular geometries without explicitly reasoning about which residues or interactions are functionally essential. As a result, design decisions are entangled with continuous sampling dynamics, limiting interpretability, controllability, and systematic reuse of biochemical knowledge. We introduce \textbf{Proteo-R1}, a reasoning-guided protein design framework that explicitly decouples \emph{molecular understanding} from \emph{geometric generation}. Proteo-R1 adopts a dual-expert architecture in which a multimodal large language model (MLLM) serves as an \emph{understanding expert}, analyzing protein sequences, structures, and textual context to identify key functional residues that govern binding and specificity. These residue-level decisions are then passed as hard constraints to a separate diffusion-based \emph{generation expert}, which performs conditional co-design while respecting the fixed interaction anchors. This factorization mirrors how human experts approach molecular engineering: first, reasoning about critical interactions, then optimizing geometry subject to those constraints. By operationalizing reasoning as explicit residue-level commitments rather than latent textual guidance, Proteo-R1 achieves stable, interpretable, and modular integration of LLM reasoning with state-of-the-art geometric generative models. Code, data, and demos are available at https://smiles724.github.io/r1/. --- ### A Universal Space of Brain Dynamics for Unveiling Cognitive Transitions and Individual Differences Authors: Ronghua Zheng, Chengyuan Qian, Weiyang Ding Published: 2026-05-01 Categories: q-bio.QM, cs.AI arXiv: https://arxiv.org/abs/2605.02936v1 Representing dynamical systems through data-driven universal spaces has proven effective; however, achieving this universality for human brain activity remains a significant challenge, further aggravated by diverse cognitive states and individual subjects. Recognizing that spatial properties reflect physical wiring while temporal properties reflect brain function, we develop Universal Brain Dynamics (UBD) to construct a universal space tailored to brain activity and quantify corresponding dynamics using a model-derived Jacobian matrix. Crucially, we validate UBD's universality by accurately predicting functional magnetic resonance imaging (fMRI) signals (Pearson's r > 0.9) across eight states and 963 subjects in the Human Connectome Project (HCP). Through evaluating resting-state fMRI represented within UBD, we gain insight into how infra-slow fluctuation (ISF) underpins brain activity. Furthermore, we reveal a new perspective on structure-function coupling (SFC) by analyzing the temporal sequence of brain dynamics. Extending UBD to task-evoked states, we derive brain dynamics across various cognitive conditions, elucidating the neural mechanisms driving cognitive transitions at a finer granularity. For individual differences, we compare brain dynamics across subjects to identify the neural underpinnings of these variations. Our findings suggest that synergistically integrating spatial and temporal properties of brain activity establishes a universal space for its unfolding, enabling the precise numerical analysis of underlying neural mechanisms across varying conditions. --- ### Quantifying and Predicting Disagreement in Graded Human Ratings Authors: Leixin Zhang, Çağrı Çöltekin Published: 2026-05-01 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.01168v1 It is increasingly recognized that human annotators do not always agree, and such disagreement is inherent in many annotation tasks. However, not all instances in a given task elicit the same degree of opinion divergence. In this paper, we investigate annotation variation patterns in graded human ratings for inappropriate languages, including offensive language, hate speech, and toxic language perception. We examine whether the degree of annotation disagreement can be predicted from textual features. We further propose the Opposition Index, a metric that quantifies perspective opposition among annotators on a given item, and investigate the predictability of instances with potentially opposing human opinions. Our results show a moderate positive correlation between estimated and observed annotation variance. We find that two approaches achieve comparable performance in variance prediction: directly predicting the variance value and estimating it from predicted annotation distributions. Our results on opposition perspective prediction show that items with high opposition index values are more difficult to predict and are often underestimated by models. --- ### Minimizing Collateral Damage in Activation Steering Authors: Tam Nguyen, Tu Anh Nguyen, Sina Alemohammad, Richard G. Baraniuk Published: 2026-05-01 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.01167v1 Activation steering is a method for controlling Large Language Model (LLM) behavior by intervening in its internal representations to increase the alignment with a specific target feature direction. However, standard interventions, such as vector addition, often cause ``collateral damage", defined as unintended changes in the alignment of activations along other non-target feature directions. This damage occurs because standard methods implicitly assume the isotropy of non-target features. In this work, we provide a mathematical formalization of collateral damage and introduce a principled framework that models steering as a constrained optimization problem. Our method finds a new activation that minimizes the expected squared collateral change weighted by the empirical second-moment matrix of activations. This weighting encodes the nonuniform cost of the perturbation in different feature directions, in contrast to isotropic approaches that penalize changes uniformly in all feature directions. By accounting for the empirical second-moment of activations, our approach achieves more precise control while reducing the degradation of model performance on unrelated tasks. --- ### CEZSAR: A Contrastive Embedding Method for Zero-Shot Action Recognition Authors: Valter Estevam, Rayson Laroca, Helio Pedrini, David Menotti Published: 2026-05-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.01165v1 This paper proposes a novel Zero-Shot Action Recognition~(ZSAR) method based on contrastive learning. In ZSAR, we aim to classify examples from classes that were missing during training. Two well-known problems remain in ZSAR: the semantic gap and the domain shift. A semantic gap occurs because label representations come from the textual domain (i.e., language models) and must be associated with visual representations (i.e., CNNs, RNNs, transformer-based). This multimodal nature implies that the semantic properties of the two spaces are not identical. On the other hand, the domain shift arises from differences between the training and test sets and is inherent to ZSAR once the test set is unknown. One of the most promising methods to address both issues is learning joint embedding spaces. Therefore, we propose a new model that encodes videos and sentences in a joint embedding space, trained by aligning videos with their natural-language descriptions. We design an automatic negative sampling procedure to augment the training dataset and generate unpaired data, i.e., visual appearance and unrelated descriptions. Our results are state-of-the-art on the UCF-101 and Kinetics-400 datasets under several split configurations. Our code is available at https://github.com/valterlej/cezsar. --- ### LLMs Should Not Yet Be Credited with Decision Explanation Authors: Wenshuo Wang Published: 2026-05-01 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.01164v1 This position paper argues that LLMs should not yet be credited with decision explanation. This matters because recent work increasingly treats accurate behavioral prediction, plausible rationales, and outcome-conditioned reasoning traces as evidence that LLMs explain why people decide as they do, risking a premature redefinition of what counts as explanatory progress in human decision modeling. We first distinguish three claims with different evidential burdens: decision prediction, rationale generation, and decision explanation. We then argue that the evidence most commonly offered for LLM-based decision accounts directly supports the first two claims, and sometimes explanatory hypothesis generation, but does not distinguish decision explanation from prediction-supportive rationalization. Next, we propose a bridge standard for decision-explanation credit: stronger claims should specify explanatory targets, discriminate against weaker rationalizer alternatives, use target-appropriate process- or intervention-sensitive validation, and bound their scope. We then situate this standard against competing views and related literatures, clarifying why it preserves the value of LLMs as predictors, narrators, and hypothesis generators while resisting premature explanatory credit. We conclude with a principle of credit calibration: LLMs should be credited for the strongest claim their evidence warrants, and no stronger; if adopted, this principle can help turn LLMs from persuasive narrators of decisions into more reliable instruments for discovering, testing, and communicating explanations of human behavior. --- ### Multimodal Data Curation Through Ranked Retrieval Authors: Pratyush Muthukumar, Harshil Kotamreddy, Sarah Amiraslani, Tomo Kanazawa, Ramani Akkati, Shaan Jain, Andrew Mathau Published: 2026-05-01 Categories: cs.IR, cs.LG arXiv: https://arxiv.org/abs/2605.01163v1 Shared embedding spaces are widely used for multimodal search and data curation. In practice, two problems often limit how well this works. First, embeddings can reflect modality more than meaning, so examples cluster by input type even when the underlying content matches. Second, the paired supervision used to train these spaces is often noisy. When we blend many heterogeneous, human-labeled datasets, these issues reinforce each other and degrade cross-modal retrieval. We present a framework that improves alignment by acting on both the training pairs and the embedding model. Symmetric Nucleus Subsampling (SNS) refines training pairs by trimming raw inputs and annotations to the portions that best support each other. Expert Embedding Engine (EEE) combines complementary embedding experts using a learned projection network, together with a bias-aware objective that reduces modality-driven separation in the embedding space. We demonstrate that this approach collapses the modality gap by over 90% on average vs base embedding experts and is a strong data curator, with datablends from our method outperforming stratified sampling and traditional curation baselines in downstream model performance. --- ### The Productivity-Reliability Paradox: Specification-Driven Governance for AI-Augmented Software Development Authors: Sabry E. Farrag Published: 2026-05-01 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2605.01160v1 Since 2022, AI-powered coding assistants have produced contradictory evidence: controlled studies report 20-56% productivity gains on well-scoped tasks, while the most rigorous RCT documents a 19% slowdown for experienced developers, and telemetry across 10,000+ developers shows 98% more pull requests but 91% longer review times with flat delivery metrics. This paper argues these findings constitute the Productivity-Reliability Paradox (PRP): a systematic phenomenon emerging from non-deterministic code generators and insufficient specification discipline. Through a multivocal literature review of 67 sources (2022-2026), this paper: (1) formally defines the PRP with three moderating variables (task abstraction, codebase maturity, developer experience) and two amplifying mechanisms (code review bottleneck, context window constraint); (2) proposes the AI-Augmented Methodology Taxonomy (AAMT), classifying six methodologies under three AI integration tiers; (3) introduces the Specification Governance Model (SGM), grounded in Transaction Cost Economics, with a practical governance decision guide; and (4) evaluates Spec Kit and TDAD as SGM instantiations via a four-month pilot study. Specification discipline, not model capability, is the binding constraint on AI-assisted software dependability. --- ### Multi-Perspective Transformers in ARC-AGI-2 Challenge Authors: Caleb Talley, Vedant Tibrewal, Seun Adekunle, Weiwen Dong, Xinyu Wu, Fariha Sheikh Published: 2026-05-01 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.01154v1 ARC-AGI-2 is a benchmark of human-intuitive visual puzzles that measures a machine's ability to generalize from limited examples, interpret symbolic meaning, and flexibly apply rules in varying contexts. In this paper, we discuss our approach to solving the ARC-AGI-2 puzzles with TinyLM, with additional fine-tuning at test time, including Test-Time-Training (TTT) and Products of Experts (POE). Our model achieves 96.1% accuracy on the training set and 21.7% accuracy on the evaluation set. --- ### Arithmetic in the Wild: Llama uses Base-10 Addition to Reason About Cyclic Concepts Authors: Sheridan Feucht, Tal Haklay, Usha Bhalla, Daniel Wurgaft, Can Rager, Raphaël Sarfati, Jack Merullo, Thomas McGrath, Owen Lewis, Ekdeep Singh Lubana, Thomas Fel, Atticus Geiger Published: 2026-05-01 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2605.01148v1 Does structure in representations imply structure in computation? We study how Llama-3.1-8B reasons over cyclic concepts (e.g., "what month is six months after August?"). Even though Llama-3.1-8B's representations for these concepts are circularly structured, we find that instead of directly computing modular addition in the period of the cyclic concept (e.g., 12 for months), the model re-uses a generic addition mechanism across tasks that operates independently of concept-specific geometry. First, it computes the sum of its two inputs using base-10 addition (six + August=14). Then, it maps this sum back to cyclic concept space (14->February). We show that Llama-3.1-8B uses task-agnostic Fourier features to compute these sums--in fact, these features have periods that respect standard base-10 addition, e.g., 2, 5, and 10, rather than the cyclic concept period (e.g., 12 for months). Furthermore, we identify a sparse set of 28 MLP neurons re-used across all tasks (approximately 0.2% of the MLP at layer 18) that can be partitioned into disjoint clusters, each computing the sum for a Fourier feature with a different period. Our work highlights how an interplay between causal abstraction and feature geometry can deepen our mechanistic understanding of LMs. --- ### Position: Safety and Fairness in Agentic AI Depend on Interaction Topology, Not on Model Scale or Alignment Authors: Tanav Singh Bajaj, Nikhil Singh, Karan Anand, Eishkaran Singh Published: 2026-05-01 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.01147v1 As large language models are increasingly deployed as interacting agents in high-stakes decisions, the AI safety community assumes that safety properties of individual models will compose into safe multi-agent behavior. This position paper argues that this assumption is fundamentally mistaken. In agentic AI, safety is determined by interaction topology, not model weights. When agents deliberate sequentially or aggregate via parallel voting with a judge, the structure of information flow and decision coupling dominates outcomes. Evidence across model families and scales reveals three persistent topology-driven pathologies: ordering instability, where system behavior depends primarily on agent sequence; information cascades, where early judgments propagate regardless of correctness; and functional collapse, where systems satisfy fairness metrics while abandoning meaningful risk discrimination. Contrary to intuition, scaling to more capable models strengthens these effects by increasing consensus formation and reducing the challenge of initial decisions. These failure modes are invisible to model-centric evaluation and alignment procedures. We argue that agentic AI must be treated as a dynamical system rather than a collection of aligned components. Interaction topology must become a primary target of safety evaluation and regulation, with systems required to demonstrate robustness across architectural variations before deployment. --- ### Semantic Context-aware mOdality fUsion Transformer (SCOUT): A Context-Aware Multimodal Transformer for Concept-Grounded Pathology Report Generation Authors: Suryakant Singh, Saarthak Kapse, Joel Saltz, Prateek Prasanna Published: 2026-05-01 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.01144v2 Whole-slide pathology report generation requires models to integrate localized histomorphology, global tissue context, and diagnostically relevant semantic information, yet existing approaches typically rely on fixed pretrained visual representations and may fail to represent key diagnostic concepts. Here we present SCOUT: Semantic Context-aware mOdality fUsion Transformer, a concept-grounded multimodal framework that integrates local histological patterns, whole-slide context, and expert-curated diagnostic concepts. SCOUT maintains an evolving visual representation together with recursively updated slide- and concept-conditioned representations, allowing visual and contextual information to iteratively co-evolve across encoder depth. During decoding, separate attention pathways attend to these complementary streams before an adaptive multimodal fusion module combines them for each generated token. We evaluated SCOUT on TCGA-BRCA, HistAI, and REG-2025, comprising more than 20,900 WSI-report pairs across more than seven cancer types. Using common CONCHv1.5 features and evaluation protocols, SCOUT outperformed WSI-Caption, HistGen, and Bi-Gen, improving BLEU scores by 9.6% on average, METEOR by 11.0%, and ROUGE-L by 3.6% relative to the strongest competing method. On REG-2025, SCOUT additionally improved the Clinical Report Quality Score by 5.6%, indicating better preservation of clinically relevant report attributes beyond lexical similarity. Ablations showed complementary contributions from iterative context refinement and adaptive fusion, while learned gates provided inspectable token-level estimates of modality use. Our results suggest that progressive contextual conditioning is effective across heterogeneous pathology report generation settings and provides a flexible framework for integrating domain knowledge into vision-language models for computational pathology. --- ### Semantic Context-aware mOdality fUsion Transformer (SCOUT): A Context-Aware Multimodal Transformer for Concept-Grounded Pathology Report Generation Authors: Suryakant Singh, Saarthak Kapse, Joel Saltz, Prateek Prasanna Published: 2026-05-01 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.01144v1 Whole-slide images (WSIs) present a fundamental challenge for computational pathology due to their extreme resolution, multi-scale heterogeneity, and the requirement for clinically reliable interpretation. Although recent pathology foundation models have enabled fluent report generation, they often lack clinical grounding, failing to accurately represent key diagnostic concepts and relationships observed by pathologists. This limitation arises from the difficulty of integrating heterogeneous visual evidence spanning fine-grained cellular patterns, slide-level tissue architecture, and high-level diagnostic concepts, while maintaining interpretability and clinical coherence. Here we present SCOUT: Semantic Context-aware mOdality fUsion Transformer, a context-aware concept-grounded multimodal framework for pathology report generation that enables progressive conditioning of image representations by global slide information and explicit diagnostic concepts. The method integrates local histological patterns, whole-slide context, and expert-curated semantic descriptors within a unified learning paradigm, allowing visual features to be dynamically refined throughout the encoding process. By combining depth-aware contextual modulation with adaptive multimodal fusion during text generation, the framework produces clinically coherent reports while preserving complementarity across representational scales. Using CONCH1.5 features, we evaluate SCOUT against WSI-Caption, HistGen, and BiGen on TCGA-BRCA, MICCAI REG, and HistAI. SCOUT achieves the best BLEU-1 to BLEU-4 and METEOR scores on all datasets, plus the best ROUGE-L on TCGA-BRCA and MICCAI REG. On TCGA-BRCA, it reaches 0.436/0.303/0.202/0.156 BLEU-1/2/3/4 and 0.204 METEOR; on REG 2025, it achieves 0.865/0.834/0.805/0.780 and 0.568. These results support progressive contextual conditioning for grounded pathology report generation. --- ### A Low-Latency Fraud Detection Layer for Detecting Adversarial Interaction Patterns in LLM-Powered Agents Authors: Sheldon Yu, Yingcheng Sun, Hanqing Guo, Qianqian Tong Published: 2026-05-01 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.01143v2 Large Language Model (LLM)-powered agents demonstrate strong capabilities in autonomous task execution, tool use, and multi-step reasoning. However, their increasing autonomy also introduces a new attack surface: adversarial interactions can manipulate agent behavior through direct prompt injection, indirect content attacks, and multi-turn escalation strategies. Existing defense strategies focus on prompt-level filtering and rule-based guardrails, which are often insufficient when risk emerges gradually across interaction sequences. In this work, we propose a complementary defense mechanism: a low-latency fraud detection layer for detecting adversarial interaction patterns in LLM-powered agents. Instead of determining whether a single prompt is malicious, our approach models risk over interaction trajectories using structured runtime features derived from prompt characteristics, session dynamics, tool usage, execution context, and fraud-inspired signals. The detection layer can be implemented using lightweight models leading to low-latency real-time deployments. To evaluate the framework, we construct a synthetic corpus of 12,000 multi-turn agent interactions generated from parameterized templates that simulate realistic agentic workflows. Using 42 structured features and an XGBoost classifier, our detector achieves over 9 times faster than LLM-based detectors. Through the experiment and ablation studies, our work suggests that interaction-level behavioral detection should become a core component of deployment-time defense for LLM-powered agents. --- ### Metric-Normalized Posterior Leakage (mPL): Attacker-Aligned Privacy for Joint Consumption Authors: Gaoyi Chen, Minghao Li, Weishi Shi, Yan Huang, Yusheng Wei, Sourabh Yadav, Chenxi Qiu Published: 2026-05-01 Categories: cs.LG, cs.CR arXiv: https://arxiv.org/abs/2605.01137v1 Metric differential privacy (mDP) strengthens local differential privacy (LDP) by scaling noise to semantic distance, but many machine learning (ML) systems are consumed under joint observation, where model-agnostic, per-record guarantees can miss leakage from evidence aggregation. We introduce metric-normalized posterior leakage (mPL), an attacker-aligned, distance-calibrated measure of posterior-odds shift induced by releases, and show that for single or independent releases, uniformly bounding mPL is equivalent to mDP. Under joint observation, however, satisfying mDP may still leave mPL high because learned aggregators compound evidence across correlated items. To make control practical, we formalize probabilistically bounded mPL (PBmPL), which limits how often mPL may exceed a target budget, and we operationalize it via Adaptive mPL (AmPL), a trust-and-verify framework that perturbs, audits with a learned attacker, and adapts parameters (with optional Bayesian remapping) to balance privacy and utility. In a word-embedding case study, neural adversaries violate mPL under joint consumption despite per-record mDP perturbations, whereas AmPL substantially lowers the frequency of such violations with low utility loss, indicating PBmPL as a practical, certifiable protection for joint-consumption settings. --- ### Spectral Graph Sparsification Preserves Representation Geometry in Graph Neural Networks Authors: Sanjukta Krishnagopal Published: 2026-05-01 Categories: cs.LG, cs.SI, math.SP, stat.ML arXiv: https://arxiv.org/abs/2605.01136v1 Spectral graph sparsification is a classical tool for reducing graph complexity while preserving Laplacian quadratic forms. In graph neural networks (GNNs), sparsification is often used to accelerate computation while maintaining predictive performance. In this work, we study a complementary representation-level question: does sparsification preserve the geometry of learned embeddings? For polynomial-filter GNNs, we prove that any $ε$-spectral sparsifier induces $O(ε)$ perturbations in polynomial graph filters, multilayer hidden representations, and their Gram matrices. These guarantees imply stability of squared pairwise distances, class means, and covariance structure in embedding space. We further establish finite-time training stability: under smoothness and boundedness assumptions, gradient descent on dense and sparsified graphs produces weight trajectories whose separation grows at most proportionally to the sparsification distortion. Empirically, effective-resistance sparsification validates the predicted perturbation chain on synthetic graphs and preserves hidden representation geometry on real datasets. In our experiments, the gram matrix and training dynamics show low divergence even under substantial sparsification, consistent with the predicted stability under spectral sparsification. Hidden Gram preservation strongly predicts neighborhood preservation and class-centroid stability across FashionMNIST, Cora, and Paul15. Together, these results show that spectral sparsification preserves not only graph operators, but also the representation geometry that supports downstream use of GNN embeddings for interpretability. --- ### ScribbleEdit: Synthetic Data for Image Editing with Scribbles and Text Authors: Anya Ji, George Ma, Téa Wright, Yiming Zhang, David M. Chan, Alane Suhr, Somayeh Sojoudi Published: 2026-05-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.01135v2 Recent progress in generative models has significantly advanced image editing capabilities, yet precise and intuitive user control remains difficult. Specifically, users often struggle to communicate both exact spatial layouts and specific semantic details simultaneously. While natural language instructions effectively convey high-level semantics like texture and color, they lack spatial specificity. Conversely, freehand scribbles provide rough spatial boundaries but cannot express detailed visual attributes. Consequently, achieving precise control requires combining both modalities. However, existing models struggle to jointly interpret abstract scribbles alongside text due to a lack of specialized training data. In this work, we introduce ScribbleEdit, a large-scale synthetic dataset designed to bridge this gap by combining natural language instructions with freehand scribble inputs for more accurate, controllable edits. We construct this dataset through a synthetic pipeline that automatically generates source-target image pairs via inpainting, which are then paired with human-drawn scribbles and VLM-generated text instructions. Using ScribbleEdit, we evaluate and finetune both diffusion-based and autoregressive unified multimodal image editing models. Our experiments reveal that while off-the-shelf models struggle with abstract scribble inputs, finetuning on our synthetic dataset significantly improves their ability to generate spatially aligned and semantically consistent edits. --- ### To Use AI as Dice of Possibilities with Timing Computation Authors: Jia Li, Vipin Kumar, Rui Zhang Published: 2026-05-01 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.01134v7 The dominant noun-based modeling paradigm, grounded in probability theory and committed to pre-specified noun entities as primitive modeling units, is insufficient as a \emph{grammar of thought}: It leaves \emph{timing} outside the computational scope, precluding any adequate representation of the future as an open space of possibilities. This paper addresses three conceptual gaps absent from the existing literature: (1) possibility space -- a framework admitting multiple possible timelines for the same event; (2) timing computation -- the treatment of timing as a computable rather than observed dimension; and (3) causal factum -- the maximal causal efficacy recovered by reasoning backward from possible futures, rather than assumed in advance. Together, these definitions dissolve the confounding problem inherent to noun-based causal inference and provide the foundation for a spontaneously growing causal-reasoning world model. As proof of concept, we instantiate the framework and apply it to longitudinal EHR data from 3,276 breast cancer patients, demonstrating for the first time, to our knowledge, automatic trajectory discovery and counterfactual timing deduction (i.e., a What-If Machine) in a purely data-driven manner. --- ### When Embedding-Based Defenses Fail: Rethinking Safety in LLM-Based Multi-Agent Systems Authors: Lingxi Zhang, Guangtao Zheng, Hanjie Chen Published: 2026-05-01 Categories: cs.CR, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2605.01133v3 Large language model (LLM)-powered multi-agent systems (MAS) enable agents to communicate and share information, achieving strong performance on complex tasks. However, this communication also creates an attack surface where malicious agents can propagate misinformation and manipulate group decisions, undermining MAS safety. Existing embedding-based defenses aim to detect and prune suspicious agents, but their effectiveness depends on a clear separation between the text embeddings of malicious and benign messages. Attackers can circumvent such defenses by crafting messages whose embeddings lie close to benign ones. We analyze this failure mode theoretically and validate it empirically with three attacks, Slow Drift, Benign Wrapper, and Chaos Seeding. Our analysis further reveals a fundamental limitation of embedding-based defenses: because they rely solely on the text embeddings, they ignore token-level confidence signals such as logits, which can remain informative when embeddings are not distinguishable under attack. We propose using confidence scores to prune or down-weight messages during MAS communication. Experiments show improved robustness across models, datasets, and communication topologies. Moreover, we find that the effectiveness of confidence signals decays over communication rounds, highlighting the importance of early intervention. This insights can inform and inspire future work on MAS attacks and defenses. --- ### Forager: a lightweight testbed for continual learning with partial observability in RL Authors: Steven Tang, Xinze Xiong, Anna Hakhverdyan, Andrew Patterson, Jacob Adkins, Jiamin He, Esraa Elelimy, Parham Mohammad Panahi, Martha White, Adam White Published: 2026-05-01 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.01131v1 In continual reinforcement learning (CRL), good performance requires never-ending learning, acting, and exploration in a big, partially observable world. Most CRL experiments have focused on loss of plasticity -- the inability to keep learning -- in one-off experiments where some unobservable non-stationarity is added to classic fully observable MDPs. Further, these experiments rarely consider the role of partial observability and the importance of CRL agents that use memory or recurrence. One potential reason for this focus on mitigating loss of plasticity without considering partial observability is that many partially-observable CRL environments are prohibitively expensive. In this paper, we introduce Forager, a light-weight partially-observable CRL environment with a constant memory footprint. We provide a set of experiments and sample tasks demonstrating that Forager is challenging for current CRL agents and yet also allows for in-depth study of those agents. We demonstrate that agents exhibit loss of plasticity, proposed mitigations can help, but that most useful is to leverage state construction. We conclude with a variant of Forager that generates an unending stream of new tasks to learn that clearly highlights the limitations of current CRL agents. --- ### Iterative Finetuning is Mostly Idempotent Authors: Zephaniah Roe, Jack Sanderson, Dang Nguyen, Julian Huang, Todd Nief, Aryan Shrivastava, Chenhao Tan, Ari Holtzman Published: 2026-05-01 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.01130v1 If a model has some behavioral tendency, such as sycophancy or misalignment, and it is trained on its own outputs, will the tendency be amplified in the next generation of models? We study this question by training a series of models where each model is finetuned on data generated by its predecessor, and the initial model is seeded with some persona or belief. We test three settings: supervised finetuning (SFT) on instruct models, synthetic document finetuning (SDF) on base models, and direct preference optimization (DPO). In the SFT and SDF settings, traits mostly decay or remain constant so that further finetuning cycles do nothing. In rare cases when amplification occurs, it generally comes at the cost of coherence. In the DPO setting, trait amplification can reliably occur when a model is continually trained with a preference for its own outputs, but vanishes when models are reinitialized at each cycle. Overall, our results suggest that amplification most likely comes from continual post-training, and limiting this stage may be an effective defense. For non-RL finetuning, trait amplification is rare and very sensitive to data quantity, making it significantly less likely to occur accidentally. Finally, the amplification-coherence tradeoff serves as a natural deterrent against trait amplification. --- ### Extreme Weather Bench: A framework and benchmark for evaluation of high-impact weather Authors: Amy McGovern, Taylor Mandelbaum, Daniel Rothenberg, Nicholas Loveday, Corey Potvin, Montgomery Flora, Linus Magnusson, Eric Gilleland, John Allen Published: 2026-05-01 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.01126v1 Forecasting the wide variety of high-impact weather events experienced globally is a challenge for both Artificial Intelligence (AI) and Numerical Weather Prediction (NWP) models and it is critical that such models be properly verified before deployment. Although AI weather models are rapidly evolving, much of their evaluation is currently done either with a global-scale evaluation or by hand-picking a small number of case studies or a region. A widely-used open-source benchmark suite focusing on high-impact weather will help to drive the science forward for all scales of weather models, as it has for other AI fields. Here we introduce Extreme Weather Bench (EWB), a new community-driven benchmark suite that facilitates model validation and verification on a variety of high-impact hazards that matter to people around the globe. EWB provides a standard set of case studies (spanning across multiple spatial and temporal scales and different parts of the weather spectrum), observational data, impact-based metrics, and open-source code for users to evaluate their models. Verifying that a model works against a standard set of case studies, especially events that are high-impact for the general public, is a key piece of improving the trustworthiness of AI models. EWB will help to drive the science forward for all weather models, enabling true comparisons across models and evaluating models on specific high-impact phenomena through the use of case studies. EWB is a free open-source community-driven system and will continue to evolve to include additional phenomena, test cases and metrics in collaboration with the worldwide weather and forecast verification community. --- ### PERSA: Reinforcement Learning for Professor-Style Personalized Feedback with LLMs Authors: Ravi Ranjan, Utkarsh Grover, Xiaomin Lin, Agoritsa Polyzou Published: 2026-05-01 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.01123v1 Large language models (LLMs) can provide automated feedback in educational settings, but aligning an LLMs style with a specific instructors tone while maintaining diagnostic correctness remains challenging. We ask how can we update an LLM for automated feedback generation to align with a target instructors style without sacrificing core knowledge? We study how Reinforcement Learning from Human Feedback (RLHF) can adapt a transformer-based LLM to generate programming feedback that matches a professors grading voice. We introduce PERSA, an RLHF pipeline that combines supervised fine-tuning on professor demonstrations, reward modeling from pairwise preferences, and Proximal Policy Optimization (PPO), while deliberately constraining learning to style-bearing components. Motivated by analyses of transformer internals, PERSA applies parameter efficient fine-tuning. It updates only the top transformer blocks and their feed-forward projections, minimizing global parameter drift while increasing stylistic controllability. We evaluate our proposed approach on three code-feedback benchmarks (APPS, PyFiXV, and CodeReviewQA) using complementary metrics for style alignment and fidelity. Across both Llama-3 and Gemma-2 backbones, PERSA delivers the strongest professor-style transfer while retaining correctness, for example on APPS, it boosts Style Alignment Score (SAC) to 96.2% (from 34.8% for Base) with Correctness Accuracy (CA) up to 100% on Llama-3, and Gemma-2. Overall, PERSA offers a practical route to personalized educational feedback by aligning both what it says (content correctness) and, crucially, how it says it (instructor-like tone and structure). --- ### Machine Learning-Augmented Acceleration of Iterative Ptychographic Reconstruction Authors: Bowen Zheng, Katayun Kamdin, David Shapiro, Alexander Ditter, Dayne Sasaki, Emma Bernard, Roopali Kukreja, Petrus H. Zwart, Slavomír Nemšák, Apurva Mehta, Nicholas Schwarz, Alexander Hexemer et al. Published: 2026-05-01 Categories: cs.LG, physics.optics arXiv: https://arxiv.org/abs/2605.01122v2 Iterative ptychographic reconstruction algorithms are widely used for coherent diffractive imaging but can exhibit slow convergence under realistic experimental conditions. We propose a machine learning-augmented approach that accelerates iterative ptychographic reconstruction by introducing a learned fast-forward operator applied during reconstruction. Following an initial warm-up using standard iterations, the fast-forward operator advances the reconstruction toward a more converged state, after which conventional iterative updates are resumed. This strategy preserves the physical consistency and flexibility of established ptychographic solvers while reducing the number of iterations required for convergence. The model is trained on diverse ptychographic datasets and evaluated on experimental data acquired in a different year, demonstrating robustness and temporal generalization. Compared with conventional iterative solvers, the machine learning-augmented method achieves comparable reconstruction quality while converging faster in terms of Poisson negative log-likelihood, yielding over a two-fold reduction in wall-clock time. The approach has been integrated into an existing reconstruction pipeline and deployed in production at a synchrotron beamline, demonstrating practicality for real-time experimental operation. ---