# Research Papers — 2026-05 · bundle page 301 of 326 > Full-text markdown of papers #15001–15050 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/301 [← Previous bundle](https://aipod.dev/papers/archive/2026-05/page/300.md) [Next bundle →](https://aipod.dev/papers/archive/2026-05/page/302.md) ### HY-Himmel Technical Report: Hierarchical Interleaved Multi-stream Motion Encoding for Long Video Understanding Authors: Haopeng Jin, Hongzhu Yi, Wenlong Zhao, Jinwen Luo, Shani Ye, Zhenyu Guan, Shiquan Dong, Tiankun Yang, Tao Yu Published: 2026-05-04 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.08158v1 Long-video understanding with multimodal language models suffers from three compounding bottlenecks: heavy decode cost to obtain dense RGB frames, quadratic token growth with frame count, and weak motion perception under sparse keyframe sampling. We present HY-Himmel, a hierarchical video-language framework that allocates semantic and motion capacity separately. A small set of sparse anchor I-frames is routed to the expensive host ViT to ground object identity and scene layout, while the far denser inter-frame intervals are encoded by a lightweight compressed-domain tri-stream adapter that distils motion evidence from motion-vector maps, residual maps, and I-frame context into aligned motion tokens. These tokens are injected into the LLM via a differentiable placeholder mechanism after a dedicated Stage-1 contrastive alignment that places the motion representation in a geometry compatible with the frozen visual backbone. On Video-MME, HY-Himmel surpasses the dense 32-frame baseline by +2.3 pp (61.2 to 63.5%) while using 3.6x fewer context tokens. Extensive ablations over stream composition, motion encoder family, fusion mode, alignment objective, anchor count, LoRA rank, and video duration confirm that the full tri-stream is necessary and sufficient for the observed gains. --- ### LAGO: Language-Guided Adaptive Object-Region Focus for Zero-Shot Visual-Text Alignment Authors: Junyi Hu, Qiji Zhou, Lei Zhang, Yue Zhang Published: 2026-05-04 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.08156v2 Zero-shot visual recognition often depends on localized parts, attributes, and textures that are diluted in global image representations. Existing training-free localized methods alleviate this limitation by evaluating multiple image regions, but their candidate locations are typically generated before class semantics determine where to look, restricting language to post-hoc scoring of already sampled evidence. We introduce LAGO (LAnguage-Guided adaptive Object-region focus), which reframes localized recognition as language-guided directed region discovery. LAGO first establishes a compact, class-agnostic object-centric visual initialization, then constructs a soft semantic prototype from the intermediate prediction to actively steer subsequent search toward class-relevant evidence during inference. This object-first, language-second design addresses the circular dependence between recognizing a class and locating its supporting evidence, while preserving complementary local, contextual, and global cues. Across standard and distribution-shift benchmarks, LAGO transfers with a single fixed configuration and uses candidate regions more effectively under matched budgets. Controlled experiments further isolate the proposed mechanism, showing that allowing language to alter the search trajectory retrieves more relevant regions and improves recognition over applying the same semantic signal only after candidate generation. --- ### LAGO: Language-Guided Adaptive Object-Region Focus for Zero-Shot Visual-Text Alignment Authors: Junyi Hu, Qiji Zhou, Lei Zhang, Yue Zhang Published: 2026-05-04 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.08156v1 Zero-shot recognition aims to classify an image by selecting the most compatible label description from a set of candidate classes without any task-specific supervision. In fine-grained settings, however, the relevant evidence often lies in localized parts, attributes, or textures rather than in the full image, making whole-image alignment suboptimal. Recent localized visual-text alignment methods address this by comparing class descriptions with multiple image regions, but they typically rely on large sets of random or redundant crops, increasing inference cost and introducing many highly redundant or weakly relevant candidates. Moreover, introducing semantic guidance too early can create an error-amplifying feedback process in which inaccurate intermediate predictions bias later localization and reinforce subsequent mistakes; we refer to this failure mode as the prediction loop. We propose LAGO (LAnguage-Guided adaptive Object-region focus), a framework for efficient and robust zero-shot localized visual-text alignment. LAGO first performs class-agnostic object-centric candidate discovery to obtain a stable visual initialization, and then applies adaptive language-guided refinement with the strength of semantic guidance controlled by intermediate confidence. It further combines object-level, contextual, and full-image evidence through an effective object-context dual-channel aggregation strategy. Extensive experiments show that LAGO consistently achieves state-of-the-art performance on standard zero-shot benchmarks and challenging distribution-shift settings, while requiring substantially fewer candidate regions at inference time. --- ### Temporal-Decay Shapley: A Time-Aware Data Valuation Framework for Time-Series Data Authors: Chuwen Pang, Bing Mi, Kongyang Chen Published: 2026-05-04 Categories: cs.LG, cs.GT arXiv: https://arxiv.org/abs/2605.08153v1 With the rapid development of machine learning applications on time-series data, accurately assessing the value of training samples has become essential for data selection, noise detection, and model optimization. However, traditional data valuation methods usually assume that samples are independent and identically distributed, and thus ignore the time-varying nature of sample value in time-series data. This paper proposes an improved temporal Shapley data valuation method that enables accurate sample valuation for time-series data through a temporal decay mechanism and a multi-scale fusion strategy. Specifically, we propose three progressively enhanced temporal Shapley methods. Temporal-Decay Shapley (TDS) incorporates temporal information into Shapley value computation through exponential decay weights; the improved TDS adopts power exponential decay to better adapt to nonlinear temporal drift; and Multi-Scale Temporal-Decay Shapley (MS-TDS) constructs a multi-scale fusion mechanism that balances the value of short-term hotspot samples and long-term foundational samples through parallel multi-scale valuation and sample-level adaptive fusion. Experimental results show that the proposed methods generally outperform traditional methods in noise detection and high-value data identification tasks, with more evident advantages under most strongly temporal settings, thereby effectively improving the accuracy and robustness of data valuation. --- ### Privacy-Preserving Federated Learning: Integrating Zero-Knowledge Proofs in Scalable Distributed Architectures Authors: Divya Gupta Published: 2026-05-04 Categories: cs.DC, cs.AI arXiv: https://arxiv.org/abs/2605.08152v1 The intersection of Artificial Intelligence (AI) and distributed systems has given rise to Federated Learning (FL), a paradigm that enables decentralized model training without compromising local data privacy. As organizational data silos grow, deploying complex machine learning models across highly distributed edge networks becomes a critical infrastructural challenge. Standard FL implementations suffer from severe vulnerabilities related to adversarial gradient updates and computational bottlenecks at the aggregation layer. This paper presents a novel, end-to-end distributed architecture that hardens FL pipelines using advanced cryptographic verification and optimized big data processing frameworks. We introduce a Zero-Knowledge Proof (ZKP) wrapper that cryptographically validates node computations before global aggregation, neutralizing model poisoning attacks without inspecting raw gradients. Additionally, we evaluate the system's performance using extreme gradient boosting models optimized for distributed edge execution. We formalize the mathematical transformation of the machine learning loss functions into Rank-1 Constraint Systems (R1CS) suitable for succinct verification. Extensive experimental results demonstrate that our hybrid architecture achieves a 94.2\% accuracy retention under adversarial conditions while maintaining scalable throughput across 1,000 parallel distributed nodes, effectively bridging the gap between rigorous cryptographic security and high-performance distributed AI. --- ### SPECTRE: Hybrid Ordinary-Parallel Speculative Serving for Resource-Efficient LLM Inference Authors: Jincheng Xie, Yawen Ling, Qi Xiao, Feiyu Zhang, Zhongyi Huang, Wen Hu, Yu Zheng Published: 2026-05-04 Categories: cs.DC, cs.AI arXiv: https://arxiv.org/abs/2605.08151v2 LLM serving platforms are increasingly deployed as multi-model cloud systems, where user demand is often long-tailed: a few popular large models receive most requests, while many smaller tail models remain underutilized. We propose \textbf{SPECTRE} (Parallel \textbf{SPEC}ulative Decoding with a Multi-\textbf{T}enant \textbf{RE}mote Drafter), a serving framework that reuses underutilized tail-model services as remote drafters for heavily loaded large-model services through speculative decoding. SPECTRE enables draft generation and target-side verification to run in parallel, and makes such parallelism effective through three techniques: a hybrid ordinary-parallel speculative decoding strategy guided by a threshold derived from throughput analysis, speculative priority scheduling to preserve draft--target overlap under multi-tenant traffic, and draft-side prompt compression to reduce draft latency. We implement SPECTRE in \texttt{SGLang} and evaluate it across multiple draft--target model pairs, reasoning benchmarks, real-world long-context workloads, and a wide range of batch sizes. Results show that SPECTRE consistently improves large-model serving throughput while causing only minor interference to the native workloads of tail-model services. In large-model deployments, including Qwen3-235B-A22B with TP=8, SPECTRE achieves up to \textbf{2.28$\times$ speedup} over autoregressive decoding and up to an additional \textbf{66\% relative improvement} over the strongest speculative decoding baselines. Talk is cheap, we show you the code: https://github.com/sgl-project/sglang/pull/22272. --- ### Hidden Coalitions in Multi-Agent AI: A Spectral Diagnostic from Internal Representations Authors: Cameron Berg, Susan L. Schneider, Mark M. Bailey Published: 2026-05-04 Categories: cs.AI, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2605.06696v1 Collections of interacting AI agents can form coalitions, creating emergent group-level organization that is critical for AI safety and alignment. However, observing agent behavior alone is often insufficient to distinguish genuine informational coupling from spurious similarity, as consequential coalitions may form at the level of internal representations before any overt behavioral change is apparent. Here, we introduce a practical method for detecting coalition structure from the internal neural representations of multi-agent systems. The approach constructs a pairwise mutual-information graph from the hidden states of agents and applies spectral partitioning to identify the most salient coalition boundary. We validate this method in two domains. First, in multi-agent reinforcement learning environments, the method successfully recovers programmed hierarchical and dynamic coalition structures and correctly rejects false positives arising from behavioral coordination without informational coupling. Second, using a large language model, the method identifies coalition structures implied by descriptive prompts, tracks dynamic team reassignments, and reveals a representational hierarchy where explicit labels dominate over conflicting interaction patterns. Across both settings, the recovered partition reveals subgroup organization that a scalar cross-agent mutual-information measure cannot distinguish. The results demonstrate that analyzing hidden-state mutual information through spectral partitioning provides a scalable diagnostic for identifying representational coalitions, offering a valuable tool for monitoring emergent structure in distributed AI systems. --- ### Memory-Efficient EDA Denoising via Knowledge Distillation for Wearable IoT Under Severe Motion Artifacts and Underwater Conditions Authors: Yongbin Lee, Andrew Peitzsch, Youngsun Kong, Jarod Zizza, Dong-hee Kang, Farnoush Baghestani, Ki H. Chon Published: 2026-05-04 Categories: eess.SP, cs.AI arXiv: https://arxiv.org/abs/2605.05246v1 Electrodermal activity (EDA) is widely used in wearable Internet of Medical Things (IoMT) systems for continuous health monitoring, including autonomic assessment. However, EDA signals are highly vulnerable to motion artifacts and environmental noise, limiting reliable deployment in harsh operating conditions such as underwater. This study proposes a robust, deployable EDA denoising framework that generalizes across multiple measurement locations and harsh environments. The framework integrates a hybrid CNN-Transformer teacher model with a lightweight depth-wise separable CNN student model via a knowledge distillation (KD) strategy. To further improve robustness, a realistic data augmentation scheme is introduced to simulate diverse motion artifacts and environmental distortions. The KD-based student model significantly reduces model size (7.87 MB to 0.51 MB) and computational cost (105.1M to 11.61M FLOPs) while maintaining denoising performance (MAE: 0.144, SNR improvement: 12.08 dB) using the public dataset validation. In real-world underwater conditions (UMAC dataset) testing, the proposed method substantially improves skin conductance response reconstruction, reducing mean absolute error from 2.809 to 0.215. Furthermore, on independent testing using the CNS-OT dataset, the denoised signals enhanced downstream CNS-OT prediction performance, achieving the highest AUROC (0.806) compared to prior denoising methods. The proposed method also improved the early prediction rate (sensitivity) from 0.550 to 0.767, enabling CNS-OT prediction up to a median of 6.9 minutes before symptom onset. These results demonstrate that the proposed framework not only improves EDA signal quality but also enhances clinically relevant prediction performance while remaining suitable for deployment in resource-constrained wearable Internet of Things systems operating in harsh environments. --- ### AdaGATE: Adaptive Gap-Aware Token-Efficient Evidence Assembly for Multi-Hop Retrieval-Augmented Generation Authors: Yilin Guo, Yinshan Wang, Yixuan Wang Published: 2026-05-04 Categories: cs.CL, cs.IR arXiv: https://arxiv.org/abs/2605.05245v1 Retrieval-augmented generation (RAG) remains brittle on multi-hop questions in realistic deployment settings, where retrieved evidence may be noisy or redundant and only limited context can be passed to the generator. Existing controllers address parts of this problem, but typically either expand context additively, select from a fixed top-k set, or optimize relevance without explicitly repairing missing bridge facts. We propose AdaGATE, a training-free evidence controller for multi-hop RAG that frames evidence selection as a token-constrained repair problem. AdaGATE combines entity centric gap tracking, targeted micro-query generation, and a utility based selection mechanism that balances gap coverage, corroboration, novelty, redundancy, and direct question relevance. We evaluate AdaGATE on HotpotQA under clean, redundancy, and noise injected retrieval conditions. Across all three settings, AdaGATE achieves the best evidence F1 among the compared controllers, reaching 62.3% on clean data and 71.2% under redundancy injection, while using 2.6x fewer input tokens than Adaptive-k. These results suggest that explicit gap-aware repair, combined with token-efficient evidence selection, improves robustness in multi-hop RAG under imperfect retrieval. Our code and evaluation pipeline are available at https://github.com/eliguo/AdaGATE. --- ### Towards Dependable Retrieval-Augmented Generation Using Factual Confidence Prediction Authors: Florian Geissler, Francesco Carella, Laura Fieback, Jakob Spiegelberg Published: 2026-05-04 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2605.05244v1 Incorporating specific knowledge into large language models via retrieval-augmented generation (RAG) is a widespread technique that fuels many of today's industry AI applications. A fundamental problem is to assess if the context retrieved by some similarity search provides indeed supporting facts, or instead misguides the generator with irrelevant information. It is critical to associate meaningful confidence measures about the factuality of the retrieval process with the generated answers. We present a new, two-staged approach to predict fact faithfulness of the output of retrieval-augmented generations. First, we employ conformal prediction to select only those retrieved chunks who have a high chance to come from the correct source. This approach in itself can improve answer quality by up to 6% in some of the studied datasets, however, the associated statistical guarantees do not hold generally, since the assumption of sample exchangeability depends on the retriever setup. We present diagnostic metrics to assess whether a setup is suitable. Second, we quantify confidence in the consistency of a generated final answer with a given retrieved context, using an attention-based factuality classifier. This approach can detect inconsistent answers with a chance of up to 77%. Our work helps to establish a novel type of certified RAG systems for a broad range of natural language industry applications. --- ### Resource Utilization of Differentiable Logic Gate Networks Deployed on FPGAs Authors: Stephen Wormald, Gilon Kravatsky, Damon Woodard, Domenic Forte Published: 2026-05-04 Categories: cs.AR, cs.AI arXiv: https://arxiv.org/abs/2605.04109v1 On-edge machine learning (ML) often strives to maximize the intelligence of small models while miniaturizing the circuit size and power needed to perform inference. Meeting these needs, differentiable Logic Gate Networks (LGN) have demonstrated nanosecond-scale prediction speeds while reducing the required resources as compares to traditional binary neural networks. Despite these benefits, the trade-offs between LGN parameters and resulting hardware synthesis characteristics are not well characterized. This paper therefore studies the tradeoffs between power, resource utilization, inference speed, and model accuracy when varying the depth and width of LGNs synthesized for Field Programmable Gate Arrays (FPGA). Results reveal that the final layer of an LGN is critical to minimize timing and resource usage (i.e. 28\% decrease), as this layer dictates the logic size of summing operations. Subject to timing and routing constraints, deeper and wider LGNs can be synthesized for FPGA when the final layer is narrow. Further tradeoffs are presented to help ML engineers select baseline LGN architectures for FPGAs with a set number of Look Up Tables (LUT). --- ### MuCALD-SplitFed: Causal-Latent Diffusion for Privacy-Preserving Multi-Task Split-Federated Medical Image Segmentation Authors: Chamani Shiranthika, Hadi Hadizadeh, Parvaneh Saeedi Published: 2026-05-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.04108v1 Federated Learning enables decentralized training by aggregating model updates across clients without sharing raw data, while Split Federated Learning further partitions the model between clients and a server to reduce computation and communication at the client side. However, decentralized medical institutions rarely operate on a single shared task, making standard Federated and SplitFed collaborations poorly aligned with real clinical workflows. Multi-task FL extends these frameworks by allowing clients to handle different tasks, but often introduces instability and privacy vulnerabilities. This study proposes \textbf{MuCALD-SplitFed}, a multi-task SplitFed framework that integrates causal representation learning and latent diffusion. Experiments show MuCALD-SplitFed consistently improves segmentation, while baseline SplitFed fails to converge. The proposed approach further reduces information leakage at split points, mitigating reconstruction-based and membership inference attacks. Additionally, MuCALD SplitFed outperforms state-of-the-art personalized FL and multi-task FL approaches. The code repository is: https://github.com/ChamaniS/MuCALD_SplitFed. --- ### TSCG: Deterministic Tool-Schema Compilation for Agentic LLM Deployments Authors: Furkan Sakizli Published: 2026-05-04 Categories: cs.SE, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2605.04107v1 Production agent frameworks (OpenAI Function Calling, Anthropic Tool Use, MCP) transmit tool schemas as JSON, a format designed for machine parsing, not for interpretation by language models. For small models (4B-14B), this protocol mismatch accounts for the majority of tool-use failure at production catalog sizes. We present TSCG, a deterministic tool-schema compiler that resolves this mismatch at the API boundary, converting JSON schemas into token-efficient structured text without model access, fine-tuning, or runtime search. TSCG combines eight composable operators with a formal compression bound (>=51% on well-formed schemas). On TSCG-Agentic-Bench (about 19,000 calls, 12 models, 5 scenarios), TSCG restores Phi-4 14B from 0% to 84.4% accuracy at 20 tools (90.3% at 50 tools) and achieves 108-181% accuracy-retained ratio across three models on BFCL. Format-versus-compression decomposition (R^2=0.88 -> 0.03) establishes representation change as the dominant mechanism. Per-operator isolation across three frontier models reveals three distinct operator-response profiles: operator-hungry (Opus 4.7), operator-sensitive (GPT-5.2), and operator-robust (Sonnet 4), providing per-model deployment guidance. Scaling experiments show accuracy advantages persisting on heavy production MCP schemas (+5.0 pp at about 10,500 input tokens) despite saturation on light synthetic catalogs, with 52-57% token savings throughout. The synthetic benchmark generalizes to real MCP schemas within 0.1 accuracy points. TSCG ships as a 1,200-line zero-dependency TypeScript package. --- ### Conformalized Percentile Interval: Finite Sample Validity and Improved Conditional Performance Authors: Ran Zou, Wanrong Zhu, Bin Nan Published: 2026-05-04 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2605.03233v1 Conformal prediction provides distribution-free predictive intervals with finite-sample marginal coverage. However, achieving conditional validity and interval efficiency (in terms of short interval length) remains challenging, particularly in complex settings with heteroskedasticity, skewed responses, or estimation errors. We propose a conformal-style calibration method for responses obtained by the probability integral transform (PIT) of the conditional cumulative distribution function (CDF) estimated via neural networks to construct a finite-sample-adjusted percentile interval with the shortest length determined by the estimated conditional CDF. Calibrating in PIT space is effective because PIT values are asymptotically feature-independent when the CDF estimator is accurate, which mitigates feature-dependent miscoverage and improves conditional calibration. On the other hand, our percentile calibration adapts to the empirical PIT distribution, which is robust against a possibly imperfect estimation of the conditional CDF. We prove the finite-sample marginal coverage property of the proposed method and show its asymptotic conditional coverage under mild consistency conditions. Experiments on diverse synthetic and real-world benchmarks demonstrate better conditional calibration and substantially shorter intervals than existing methods. --- ### cotomi Act: Learning to Automate Work by Watching You Authors: Masafumi Oyamada, Kunihiro Takeoka, Kosuke Akimoto, Ryoma Obara, Masafumi Enomoto, Haochen Zhang, Daichi Haraguchi, Takuya Tamura Published: 2026-05-04 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.03231v1 What if a browser agent could learn your work simply by watching you do it? We present cotomi Act, a browser-based computer-using agent that combines reliable multi-step task execution with persistent organizational knowledge learned from user behavior. For execution, an agent scaffold with adaptive lazy observation, verbal-diff-based history compression, coarse-grained actions, and test-time scaling via best-of-N action selection achieves 80.4% on the 179-task WebArena human-evaluation subset, exceeding the reported 78.2% human baseline. For organizational knowledge, a behavior-to-knowledge pipeline passively observes the user's browsing and progressively abstracts it into artifacts (task boards, wiki) exposed through a shared workspace editable by both user and agent. A controlled proxy evaluation confirms that task success improves as behavior-derived knowledge accumulates. In our live demonstration, attendees interact with the system in a real browser, issuing tasks and observing end-to-end autonomous execution and shared knowledge management. --- ### Sparse Memory Finetuning as a Low-Forgetting Alternative to LoRA and Full Finetuning Authors: Prakhar Gupta, Garv Shah, Satyam Goyal, Anirudh Kanchi Published: 2026-05-04 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2605.03229v2 Adapting a pretrained language model to a new task often hurts the general capabilities it already had, a problem known as catastrophic forgetting. Sparse Memory Finetuning (SMF) tries to avoid this by adding key-value memory layers to the model and, on each training step, updating only the small set of memory rows that the current batch reads most heavily. We re-implement SMF on Qwen-2.5-0.5B-Instruct and compare it with LoRA and full finetuning on MedMCQA, a 4-choice medical exam task, using WikiText perplexity and TriviaQA accuracy as forgetting probes. SMF improves MedMCQA by 2.5 percentage points while keeping both forgetting probes within roughly 1 point of the base model, whereas LoRA and full finetuning achieve larger gains but with clear drift on both. We also compare two row-selection rules (KL-divergence and TF-IDF), which balance the two forgetting metrics differently. --- ### Safeguarding LLM Agents against Long-Horizon Threats via Shadow Memory Authors: Yuhui Wang, Tanqiu Jiang, Jiacheng Liang, Charles Fleming, Ting Wang Published: 2026-05-04 Categories: cs.CR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2605.03228v2 As large language model (LLM)-powered agents are increasingly deployed to perform complex, real-world tasks, they face a growing class of attacks that exploit extended user-agent-environment interactions to pursue malicious objectives improbable in single-turn settings. Such long-horizon threats pose significant risks to the safe deployment of LLM agents in critical domains. In this paper, we present ShadowMem, a novel defensive framework designed to counter a wide range of long-horizon threats. Inspired by the "shadow stack" abstraction in systems security, ShadowMem maintains a dedicated, safety-focused agentic memory that distills and retains safety-critical context across the agent's full execution trajectory, leveraging this shadow memory to proactively assess the risk of pending actions prior to their execution. Extensive evaluation demonstrates that ShadowMem substantially outperforms existing defenses across diverse long-horizon threats in detection accuracy, achieves early-stage detection for the majority of attacks, and introduces only negligible overhead to agent utility. To our best knowledge, ShadowMem represents the first framework to detect and mitigate long-horizon threats using an agentic memory approach, establishing a new paradigm for this critical challenge and opening promising directions for future research. The artifacts are available at https://github.com/ZJUWYH/ShadowMem --- ### MAGE: Safeguarding LLM Agents against Long-Horizon Threats via Shadow Memory Authors: Yuhui Wang, Tanqiu Jiang, Jiacheng Liang, Charles Fleming, Ting Wang Published: 2026-05-04 Categories: cs.CR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2605.03228v1 As large language model (LLM)-powered agents are increasingly deployed to perform complex, real-world tasks, they face a growing class of attacks that exploit extended user-agent-environment interactions to pursue malicious objectives improbable in single-turn settings. Such long-horizon threats pose significant risks to the safe deployment of LLM agents in critical domains. In this paper, we present MAGE (Memory As Guardrail Enforcement), a novel defensive framework designed to counter a wide range of long-horizon threats. Inspired by the "shadow stack" abstraction in systems security, MAGE maintains a dedicated, safety-focused agentic memory that distills and retains safety-critical context across the agent's full execution trajectory, leveraging this shadow memory to proactively assess the risk of pending actions prior to their execution. Extensive evaluation demonstrates that MAGE substantially outperforms existing defenses across diverse long-horizon threats in detection accuracy, achieves early-stage detection for the majority of attacks, and introduces only negligible overhead to agent utility. To our best knowledge, MAGE represents the first framework to detect and mitigate long-horizon threats using an agentic memory approach, establishing a new paradigm for this critical challenge and opening promising directions for future research. --- ### Evaluating Prompting and Execution-Based Methods for Deterministic Computation in LLMs Authors: Hongkun Yu Published: 2026-05-04 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.03227v2 Large Language Models (LLMs) have demonstrated strong capabilities in natural language understanding and reasoning. However, their ability to perform exact, deterministic computation remains unclear. In this work, we systematically evaluate multiple prompting strategies, including Chain-of-Thought (CoT), Least-to-Most decomposition, Program-of-Thought (PoT), and Self-Consistency (SC), on tasks requiring precise and error-free outputs, including binary counting, longest substring detection, and arithmetic evaluation. To support this study, we introduce a synthetic dataset with diverse natural language instructions, enabling controlled evaluation of exact computation across multiple task types. Our results show that standard prompting methods achieve only moderate accuracy on sequence-based tasks. CoT provides limited improvement, while Least-to-Most suffers from error accumulation. In contrast, PoT achieves perfect accuracy by generating executable code and delegating computation to an external interpreter. Self-Consistency improves robustness through majority voting, but incurs substantial computational overhead. We further train a small domain-specific model (CodeT5-small) to generate executable programs, which achieves perfect accuracy on held-out synthetic test data across all tasks with minimal training cost. Overall, our findings suggest that LLMs may simulate reasoning patterns rather than reliably perform exact symbolic computation. For deterministic tasks, combining LLMs with external tools or using specialized models provides a more reliable and efficient solution. --- ### Self-Mined Hardness for Safety Fine-Tuning Authors: Prakhar Gupta, Garv Shah, Donghua Zhang Published: 2026-05-04 Categories: cs.LG, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2605.03226v2 Safety fine-tuning of language models typically requires a curated adversarial dataset. We take a different approach: score each candidate prompt's difficulty by how often the target model's own rollouts are judged harmful, then fine-tune on the hardest prompts paired with the model's own non-jailbroken rollouts. On Llama-3-8B-Instruct and Llama-3.2-3B-Instruct, this approach cuts the WildJailbreak attack success rate from 11.5% and 20.1% down to 1-3%, but pushes refusal on jailbreak-shaped benign prompts from 14-22% to 74-94%. Interleaving the same hard prompts 1:1 with adversarially-framed benign prompts (prompts that look like jailbreaks but have benign intent) cuts that refusal back down to 30-51% on 8B and 52-72% on 3B, at a cost of 2-6 percentage points of attack success rate. Within the mixed regime, training on the hardest half of the eligible pool rather than a random half cuts the remaining ASR by 35-50% (about 3 percentage points) on both models. --- ### Beyond Activation Alignment: The Geometry of Neural Sensitivity Authors: Amirhossein Yavari, Farnaz Zamani Esfahlani Published: 2026-05-04 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2605.03222v2 Activation-alignment measures such as Representational Similarity Analysis (RSA), Canonical Correlation Analysis (CCA), and Centered Kernel Alignment (CKA) are widely used to compare biological and artificial neural representations. Recent theoretical work interprets many of these methods as assessing agreement between optimal linear readouts over broad families of global tasks. However, agreement at the level of global readouts does not determine how a system uses local stimulus evidence. Specifically, representations may align in activation space yet differ in their sensitivity to small perturbations. To address this challenge, we introduce a complementary framework based on local decodable information, which focuses on a representation's ability, under noise, to discriminate small perturbations within a specified stimulus-coordinate subspace. Building on Fisher information and local representation geometry, we summarize each representation using the expected projected pullback/Fisher metric over that subspace. This formulation induces a second-moment family of local discrimination tasks, for which the resulting operator provides a minimal, complete dataset-level summary of expected discriminability. We compare these regularized signatures using a log-spectral distance on the manifold of symmetric positive definite (SPD) matrices, yielding the Spectral Riemannian Alignment Score (S-RAS) and a uniform multiplicative certificate over the corresponding family of lifted task values. Empirically, this framework enables the recovery of corresponding layers across independently trained artificial neural networks, supports transferable class-conditional probes, reveals controlled dissociations between standard and robust training, and uncovers stimulus-coordinate family effects across mouse visual cortex using the Allen Brain Observatory static gratings dataset. --- ### Synthetic Data Generation for Long-Tail Medical Image Classification: A Case Study in Skin Lesions Authors: Jiaxiang Jiang, Mahesh Subedar, Omesh Tickoo Published: 2026-05-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.03221v1 Long-tailed class distributions are pervasive in multi-class medical datasets and pose significant challenges for deep learning models which typically underperform on tail classes with limited samples. This limitation is particularly problematic in medical applications, where rare classes often correspond to severe or high-risk diseases and therefore require high diagnostic accuracy. Existing solutions-including specialized architectures, rebalanced loss functions, and handcrafted data augmentation-offer only marginal improvements and struggle to scale due to their limited and largely deterministic variability. To address these challenges, we introduce a diffusion-model-driven synthetic data augmentation pipeline tailored for medical long-tailed classification. Our approach features a novel inpainting diffusion model combined with an Out-of-Distribution (OOD) post-selection mechanism to ensure diverse, realistic, and clinically meaningful synthetic samples. Evaluated on the ISIC2019 skin lesion classification dataset, one of the largest and most imbalanced medical imaging benchmarks, our method yields substantial improvements in overall performance, with particularly pronounced gains on tail classes with more than $28\%$ improvement on the class with the fewest samples. These results demonstrate the effectiveness of diffusion-based augmentation in mitigating long-tail imbalance and enhancing medical classification robustness. --- ### Moral Sensitivity in LLMs: A Tiered Evaluation of Contextual Bias via Behavioral Profiling and Mechanistic Interpretability Authors: Yash Aggarwal, Atmika Gorti, Vinija Jain, Aman Chadha, Krishnaprasad Thirunarayan, Manas Gaur Published: 2026-05-04 Categories: cs.LG, cs.CY arXiv: https://arxiv.org/abs/2605.03217v3 Large language models (LLMs) are increasingly deployed in settings that require nuanced ethical reasoning, yet existing bias evaluations treat model outputs as simply "biased" or "unbiased." This binary framing misses the gradual, context-sensitive way bias actually emerges. We address this gap in two stages: behavioral profiling and mechanistic validation. In the behavioral stage, we introduce the Moral Sensitivity Index (MSI), a metric that quantifies the probability of biased output across a graduated, seven-tier stress test ranging from abstract numerical problems to scenarios rooted in historical and socioeconomic injustice. Evaluating four leading models (Claude 3.5, Qwen 3.5, Llama 3, and Gemini 1.5), we identify distinct behavioral signatures shaped by alignment design: for instance, Gemini 1.5 reaches 72.7% MSI by Tier 5 under socioeconomic framing, while Claude exhibits sharp suppression consistent with identity-based safety training. We then verify these behavioral patterns mechanistically. We select criminal-bias scenarios, which produced the highest MSI scores across models, as probes and apply logit lens, attention analysis, activation patching, and semantic probing to a controlled set of six models spanning three capability tiers: small language models (SLMs), instruction-tuned base models, and reasoning-distilled variants. Circuit-level analysis reveals a U-curve of bias: SLMs exhibit strong criminal bias; scaling to instruction-tuned models eliminates it; reasoning distillation reintroduces bias to SLM-like levels despite identical parameter counts, suggesting distillation compresses reasoning traces in ways that reactivate shallow statistical associations. Critically, the socially loaded cues that drive high MSI scores activate the same bias-driving circuits identified mechanistically, providing cross-stage validation. --- ### MenuNet: A Strategy-Proof Mechanism for Matching Markets Authors: Zhaohong Sun, Makoto Yokoo Published: 2026-05-04 Categories: cs.GT, cs.AI arXiv: https://arxiv.org/abs/2605.03216v1 Strategy-proofness is a fundamental desideratum in mechanism design, ensuring truthful reporting and robust participation. Stability is another central requirement in matching markets, widely adopted in applications such as school choice and labor market clearing. In practice, however, these markets are invariably governed by complex distributional constraints, ranging from diversity quotas and regional balance to global capacity slacks, under which stable matchings often fail to exist. This raises a fundamental question: how to distribute unavoidable instability across agents while preserving strategy-proofness? To address this, we propose \texttt{MenuNet}, a strategy-proof mechanism design framework based on a neural representation of menus. Rather than directly constructing assignments, \texttt{MenuNet} learns to generate personalized probabilistic menus, from which assignments are realized via a structured sequential choice rule that guarantees strategy-proofness by construction. By decomposing stability into fairness (no envy) and non-wastefulness, our approach models these properties as vector-valued quantities and optimizes their distribution through differentiable objectives, providing a principled trade-off between competing axioms. Empirically, \texttt{MenuNet} navigates this trade-off effectively: it consistently outperforms Random Serial Dictatorship (RSD) in terms of envy and Deferred Acceptance (DA) in terms of waste, while maintaining scalability and computational efficiency. These results suggest that learning-based menu mechanisms provide a flexible and scalable paradigm for mechanism design in highly constrained, real-world environments. --- ### When Agents Handle Secrets: A Survey of Confidential Computing for Agentic AI Authors: Javad Forough, Marios Kogias, Hamed Haddadi Published: 2026-05-04 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2605.03213v2 Agentic AI systems, specifically LLM-driven agents that plan, invoke tools, maintain persistent memory, and delegate tasks to peer agents via protocols such as MCP and A2A, introduce a threat surface that differs materially from standalone model inference. Agents accumulate sensitive context, hold credentials, and operate across pipelines no single party fully controls, enabling prompt injection, context exfiltration, credential theft, and inter-agent message poisoning. Current defenses operate entirely within the software stack and can be silently bypassed by a sufficiently privileged adversary such as a compromised cloud operator. Confidential computing (CC) offers a hardware-rooted alternative: Trusted Execution Environments (TEEs) isolate agent code and data from privileged system software, while remote attestation enables verifiable trust across distributed deployments. This survey synthesizes the design space in four parts: (i) a unified taxonomy of six TEE platforms (Intel SGX, Intel TDX, AMD SEV-SNP, ARM TrustZone, ARM CCA, and NVIDIA H100 CC) covering deployment roles and performance tradeoffs; (ii) an agent-centric threat model spanning perception, planning, memory, action, and coordination layers mapped to nine security goals; (iii) a comparative survey of CC-based defenses distinguishing findings that transfer from single-call inference versus what requires new agentic designs; and (iv) six open challenges including compound attestation for multi-hop agent chains and GPU-TEE performance at LLM scale. While several hardware trust primitives appear mature enough for targeted deployments, no broadly established end-to-end framework yet binds them into a coherent security substrate for production agentic AI. --- ### ADAPTS: Agentic Decomposition for Automated Protocol-agnostic Tracking of Symptoms Authors: Alexandria K. Vail, Marcelo Cicconet, Katie Aafjes-van Doorn, Ryan Maroney, Marc Aafjes Published: 2026-05-04 Categories: cs.AI, cs.CL, cs.HC, stat.AP, stat.CO arXiv: https://arxiv.org/abs/2605.03212v2 Modeling latent clinical constructs from unconstrained clinical interactions is a unique challenge in affective computing. We present ADAPTS (Agentic Decomposition for Automated Protocol-agnostic Tracking of Symptoms), a framework for automated rating of depression and anxiety severity using a mixture-of-agents LLM architecture. This approach decomposes long-form clinical interviews into symptom-specific reasoning tasks, producing auditable justifications while preserving temporal and speaker alignment. Generalization was evaluated across two independent datasets ($N=204$) with distinct interview structures. On high-discrepancy interviews, automated ratings approximated expert benchmarks ($\text{absolute error}=22$) more closely than original human ratings ($\text{absolute error}=26$). Implementing an ``extended'' protocol that incorporates qualitative clinical conventions significantly stabilized ratings, with absolute agreement reaching $\text{ICC(2,1)} = 0.877$. These findings suggest that the ADAPTS framework enables promising evaluations of psychiatric severity. While the current implementation is purely text-based, the underlying architecture is readily extensible to multimodal inputs, including acoustic and visual features. By approximating expert-level precision in a protocol-agnostic manner, this framework provides a foundation for objective and scalable psychiatric assessment, especially in resource-limited settings. --- ### Human-Provenance Verification should be Treated as Labor Infrastructure in AI-Saturated Markets Authors: Erin McGurk, David Khachaturov Published: 2026-05-04 Categories: cs.CY, cs.AI, econ.GN arXiv: https://arxiv.org/abs/2605.03210v1 We argue that AI-saturated markets are likely to create Veblen-good premiums, which we term human-provenance premiums, for verified human presence, and hence AI governance should treat human-provenance verification as labor infrastructure. Generative and agentic AI systems lower the cost of many standardized cognitive, creative, and coordination tasks, weakening the scarcity premiums that have supported much middle-tier knowledge work. We argue that this pressure may produce an asymmetric barbell-shaped structure of value capture in advanced economies: high-volume synthetic production controlled by owners of AI infrastructure at one pole, and scarce, high-status human labor valued for verified human presence at the other. We advance three claims. First, AI compresses the value of standardized middle-tier labor by making good-enough synthetic substitutes scalable at low marginal cost, hollowing out the middle of the skill distribution currently categorized by knowledge work. Second, this compression reallocates demand for human labor toward work valued for its visible human character. We term this performative humanity and distinguish three forms of labor: relational presence, aesthetic provenance, and accountability. Third, as these premiums depend on credible verification, AI governance should treat human-provenance systems as labor infrastructure rather than as luxury authenticity labels. To evaluate hybrid human-AI work, we propose constitutive human presence as the relevant standard: human labor retains premium value when human judgment, attention, accountability, authorship, or relational participation is not incidental to the output but constitutive of what is being purchased. --- ### From Knowledge to Action: Outcomes of the 2025 Large Language Model (LLM) Hackathon for Applications in Materials Science and Chemistry Authors: Aritra Roy, Kevin Shen, Andrew MacBride, Awwal Oladipupo, Mudassra Taskeen, Wojtek Treyde, Ruaa A. E. A. Abakar, Ahmad D. Abbas, Elsayed Abdelfatah, Abbas A. Abdullahi, Seham S. Abyah, Chahd Rahyl Adjmi et al. Published: 2026-05-04 Categories: cond-mat.mtrl-sci, cs.AI arXiv: https://arxiv.org/abs/2605.03205v1 Large language models (LLMs) are rapidly changing how researchers in materials science and chemistry discover, organize, and act on scientific knowledge. This paper analyzes a broad set of community-developed LLM applications in an effort to identify emerging patterns in how these systems can be used across the scientific research lifecycle. We organize the projects into two complementary categories: Knowledge Infrastructure, systems that structure, retrieve, synthesize, and validate scientific information; and Action Systems, systems that execute, coordinate, or automate scientific work across computational and experimental environments. The submissions reveal a shift from single-purpose LLM tools toward integrated, multi-agent workflows that combine retrieval, reasoning, tool use, and domain-specific validation. Prominent themes include retrieval-augmented generation as grounding infrastructure, persistent structured knowledge representations, multimodal and multilingual scientific inputs, and early progress toward laboratory-integrated closed-loop systems. Together, these results suggest that LLMs are evolving from general-purpose assistants into composable infrastructure for scientific reasoning and action. This work provides a community snapshot of that transition and a practical taxonomy for understanding emerging LLM-enabled workflows in materials science and chemistry. --- ### A Partition-Based Generating Function for Row-Convex Polyominoes Authors: Vincenzo M. Scarrica Published: 2026-05-04 Categories: math.CO, cs.CV arXiv: https://arxiv.org/abs/2605.03203v1 An alternative generating function is proposed to enumerate row-convex polyominoes without internal holes on a discrete grid. The approach is based on integer partitions of the total area, where each partition corresponds to a sequence of row lengths, and the product of all permutations of the parts accounts for all possible horizontal alignments of consecutive rows. Summing over the products yields a formula for the total number of convex polyominoes of a given size. Numerical examples are provided for small areas, and the exact generating function is derived via a transfer series argument, establishing the asymptotic growth S(N) as A2^(N) cos(N*theta) + phi) with theta = arctan(sqrt(7)/3). The method establishes a direct connection between integer partitions and polyomino enumeration, offering a simple yet effective framework for both exact and asymptotic combinatorial analysis. Potential applications include shape priors in discrete image analysis, grid-based modeling, and combinatorial generation of convex structures. --- ### Stop Automating Peer Review Without Rigorous Evaluation Authors: Joachim Baumann, Jiaxin Pei, Sanmi Koyejo, Dirk Hovy Published: 2026-05-04 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.03202v2 Large language models offer a tempting solution to address the peer review crisis. This position paper argues that today's AI systems should not be used to produce paper reviews. We ground this position in an empirical comparison of human- versus AI-generated ICLR 2026 reviews and an evaluation of the effect of automated paper rewriting on different AI reviewers. We identify two critical issues: 1) AI reviewers exhibit a hivemind effect of excessive agreement within and across papers that reduces perspective diversity. 2) AI review scores are trivially gameable through paper laundering: prompting an LLM to rewrite a paper could significantly increase the scores from AI reviewers, demonstrating that LLM reviewers are easy to game through stylistic changes rather than scientific results. However, non-gameability and review diversity are necessary but not sufficient conditions for automation. We argue that addressing the peer review crisis requires a science of peer review automation -- not general-purpose LLMs deployed without rigorous evaluation. --- ### Geometric Deviation as an Unsupervised Pre-Generation Reliability Signal: Probing LLM Representations for Answerability Authors: Yucheng Du Published: 2026-05-04 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2605.03196v1 A reliable language model should be able to signal, prior to generation, when a query falls outside its knowledge. We investigate whether representation geometry can provide such a pre-generation signal by measuring the deviation of hidden states from an answerable reference set, requiring no labeled failure data and no access to model outputs. Across three instruction-tuned models (Llama 3.1-8B, Qwen 2.5-7B, and Mistral-7B-Instruct) and three prompt forms (Math, Fact, Code), we find that geometry primarily encodes task form. Within mathematical prompts, unanswerable inputs consistently deviate from the answerable centroid, yielding strong separation (ROC-AUC 0.78-0.84). This single-pass pre-generation signal outperforms a simple refusal baseline and compares favorably to self-consistency. It also captures cases where models do not explicitly refuse. In contrast, no reliable geometric signal emerges for factual prompts, indicating that the effect is form-conditional rather than universal. Code prompts show large effect sizes with higher variance, suggesting partial generalization beyond mathematical form. A layer-wise analysis reveals that the signal arises in early layers and gradually attenuates toward the output. These results suggest that answerability-related geometry is established before the final stages of generation. Together, these findings indicate that geometric deviation can serve as a lightweight pre-generation signal that is reliable in structured domains with formal answerability constraints, with clear boundaries on where it generalizes. --- ### Terminus-4B: Can a Smaller Model Replace Frontier LLMs at Agentic Execution Tasks? Authors: Spandan Garg, Vikram Nitin, Yufan Huang Published: 2026-05-04 Categories: cs.AI, cs.SE arXiv: https://arxiv.org/abs/2605.03195v2 Modern coding agents increasingly delegate specialized subtasks to subagents, which are smaller, focused agentic loops that handle narrow responsibilities like search, debugging or terminal execution. This architectural pattern keeps the main agent's context window clean by isolating verbose outputs (e.g. build logs, test results, etc.) within the subagent context. Typically when agents employ subagents for such tasks, they use frontier models as these subagents. In this paper, we investigate whether a finetuned small language model (SLM) can achieve comparable performance to frontier models in the task of agentic terminal execution. We present Terminus-4B, which is a post-trained Qwen3-4B model via Supervised Finetuning (SFT) and Reinforcement Learning (RL) using rubric-based LLM-as-judge reward, specifically for this task. In our extensive evaluation spanning various frontier models, training ablations and main agent configurations, we find that Terminus-4B is able to reduce the token usage of the main agent by up to ~30% compared to the No Subagent baseline with no impact to agent performance on benchmarks like SWE-Bench Pro and our internal SWE-Bench C# benchmark, which tends to be heavy in verbose execution tasks. Furthermore, Terminus-4B improves key metrics showing the main agent relying on the outputs of the subagent and doing fewer terminal execution tasks by itself. We see that our model not only closes the gap between the Vanilla Qwen model and frontier models like Claude Sonnet / Opus / GPT-5.3-Codex, but often even exceeds their performance. --- ### Sentinel2Cap: A Human-Annotated Benchmark Dataset for Multimodal Remote Sensing Image Captioning Authors: Lucrezia Tosato, Gianluca Lombardi, Ronny Hansch Published: 2026-05-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.03189v1 Image captioning has become an important task in computer vision, enabling models to generate natural language descriptions of visual content. While several datasets exist for natural images and high-resolution optical remote sensing imagery, the availability of captioning datasets for multimodal satellite data remains limited, particularly for SAR imagery and medium-resolution sensors. We introduce Sentinel2Cap, a human-annotated multimodal captioning dataset containing Sentinel-1 SAR and Sentinel-2 multi-spectral image patches at 10 m and 20 m spatial resolution with diverse land cover compositions. Captions are created manually and carefully validated to ensure both semantic accuracy and linguistic quality. To evaluate Sentinel2Cap, we perform a zero-shot captioning using the Qwen3-VL-8B-Instruct model across three image modalities: RGB, multi-spectral, and SAR pseudo-RGB representations. Results show that RGB images achieve the highest captioning performance, while SAR images remain more challenging for vision-language models. Providing modality-specific contextual prompts consistently improves performance across all metrics. These findings highlight both the challenges of multimodal remote sensing image captioning and the potential value of human-annotated datasets for advancing research in cross-modal scene understanding. All the material is publicly avaiable. --- ### Enhancing AI-Based ECG Delineation with Deep Learning Denoising Techniques Authors: Jeff Breeding-Allison, Emil Walleser Published: 2026-05-04 Categories: cs.LG, eess.SP arXiv: https://arxiv.org/abs/2605.03183v2 Evaluating canine electrocardiograms (ECGs) is challenging due to noise that can obscure clinically relevant cardiac electrical activity. Common sources of interference include respiration, muscle activity, poor lead contact, and external electrical artifacts. Classical signal denoising techniques, such as filtering and wavelet-based methods, struggle to suppress diverse noise patterns while preserving morphological features critical for accurate ECG delineation. We propose an autoencoder-based neural network model and training strategy for ECG denoising as a preprocessing step for canine ECG analysis. The model is trained to reconstruct clean cardiac signals from noisy inputs, enabling effective noise reduction without degrading diagnostically important waveforms. Our approach demonstrates strong performance across both noisy and clean ECG recordings, indicating robustness to varying signal conditions and suitability for downstream delineation tasks. --- ### DINO Soars: DINOv3 for Open-Vocabulary Semantic Segmentation of Remote Sensing Imagery Authors: Ryan Faulkenberry, Saurabh Prasad Published: 2026-05-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.03175v1 The remote sensing (RS) domain suffers from a lack of densely labeled datasets, which are costly to obtain. Thus, models that can segment RS imagery well without supervised fine-tuning are valuable, but existing solutions fall behind supervised methods. Recently, DINOv3 surpassed SOTA RS foundation models on the GEO-bench segmentation benchmark without pre-training on RS data. Additionally, DINO.txt has enabled open vocabulary semantic segmentation (OVSS) with the DINOv3 backbone. We leverage these developments to form an OVSS model for RS imagery, free of RS-domain fine-tuning. Our model, CAFe-DINO (Cost Aggregation + Feature Upsampling with DINO) exploits the strong OVSS performance of DINOv3 for RS imagery via cost aggregation and training-free upsampling of text-image similarity scores. The robust latent of the DINOv3 backbone eliminates the need for fine-tuning on RS imagery; we instead fine-tune our model on a RS-targeted subset of COCO-Stuff. CAFe-DINO achieves state-of-the-art performance on key RS segmentation datasets, outperforming OVSS methods fine-tuned on RS data. Our code and data are publicly available at https://github.com/rfaulk/DINO_Soars. --- ### Global and Local Topology-Aware Attention with Persistent Homology and Euler Biases for Time-Series Forecasting Authors: Usef Faghihi, Amir Saki Published: 2026-05-04 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.03163v1 Scientific time series often encode predictive geometric structure, including connectivity, cycles, shell-like geometry, directional changes, and nonlinear neighborhoods, that standard dot-product attention does not explicitly represent. We introduce a topology-aware attention framework that adds such structure to attention logits using persistent homology (H0-H2), anchored Euler characteristic transforms, and kernel-Hilbert channels. A validation-gated local residual captures local topological signals, including a Zeng-style local H0 component, only when held-out validation data support the correction. Exact Vietoris-Rips computations and smooth topological surrogates are evaluated under a no-leakage protocol with train-only calibration, validation-only selection, and test-only reporting. We evaluate guarded topology-aware variants across three architecture families: lightweight attention/Ridge, PatchTSTForRegression, and TimeSeriesTransformerForPrediction. Experiments include synthetic benchmarks isolating higher-order topology and real datasets covering CO2, S&P 500 return-window geometry, and NASA IMS bearing degradation. The audit uses matched paired comparisons across seven dataset units, three random seeds, and three chronological splits, giving 63 paired units per architecture and 189 paired units overall. Topology-aware models show positive paired effects when geometry is predictive, with heterogeneous magnitude across datasets and architectures. Lightweight attention/Ridge improves in 46 of 63 units, with mean relative RMSE reduction of 12.5% and paired randomization p=7.2e-4; PatchTST improves in 33 units and retains the baseline in 20 units, with 23.5% reduction and p=3.5e-5; and TimeSeriesTransformer improves in 47 units, with 47.8% reduction and p<1e-4. The results support topology as a validation-selected, architecture-compatible inductive bias. --- ### Steering grids for sparse-autoencoder features: when a top-context label names an activation regime rather than a causal axis Authors: Michael A. Riegler, Birk Sebastian Frostelid Torpmann-Hagen Published: 2026-05-04 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.03160v2 The standard protocol for interpreting sparse-autoencoder (SAE) features labels each feature from its top-activating contexts and validates the label by steering that single feature at a typical magnitude. We argue that this inspects one cell of a larger steering grid, steering condition (single feature, joint feature set, matched random direction) crossed with steering coefficient, and show that other cells carry information that changes the label. On Qwen3-1.7B-Instruct and Gemma-2-2B-it, with the matched-geometry control extended to Llama-3.1-8B-Instruct: (1) features labelled AI self-disclaimer from their top contexts switch to a second surface form under steering, a contemplative voice on Qwen, a collective we-voice on Gemma, so the label names an activation regime, not the causal axis; two anchor features separate genuine mode switches from monotonic response and from breakdown. (2) Three near-orthogonal features that are individually substitutable are jointly necessary for grounded composition: joint suppression collapses unrelated control tasks into placeholder text that single-feature suppression at the same coefficient leaves intact. (3) A matched-geometry random-direction control shows the collapse is direction-pattern-dependent, not magnitude-dependent: at the same residual-stream distortion, feature directions damage unrelated tasks where magnitude-matched random directions do not, with non-overlapping 95% confidence intervals on all three models, including the one SAE trained on the model it is applied to. --- ### Learning Correct Behavior from Examples: Validating Sequential Execution in Autonomous Agents Authors: Reshabh K Sharma, Gaurav Mittal, Yu Hu Published: 2026-05-04 Categories: cs.AI, cs.SE arXiv: https://arxiv.org/abs/2605.03159v1 As autonomous agents become increasingly sophisticated, validating their sequential behavior presents a significant challenge. Traditional testing approaches require manual specification, exact sequence matching, or thousands of training examples. We present a novel algorithm that automatically learns correct behavior from just 2-10 passing execution traces and validates new executions against this learned model. Our approach combines dominator analysis from compiler theory with multimodal large language model-powered semantic understanding to identify essential states and handle non-deterministic behavior. The system constructs a generalized ground truth model using Prefix Tree Acceptors, merges traces through multi-tiered equivalence detection, and validates new executions via topological subsequence matching. In controlled experiments, our system achieved high accuracy in detecting product bugs and false successes using only 3 training traces. This approach provides explainable validation results with coverage metrics and works across diverse domains including UI testing, code generation, and robotic processes. --- ### OCRR: A Benchmark for Online Correction Recovery under Distribution Shift Authors: Adrian Grassi Published: 2026-05-04 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2605.03153v1 Static benchmarks measure a model frozen at training time. Real systems face distribution shift: new categories, paraphrased queries, drift: and must recover online via user corrections. No existing benchmark measures recovery speed under correction streams. We introduce OCRR (Online Correction Recovery Rate): a benchmark that streams a corpus through a classification system, applies oracle or stochastic corrections to wrong predictions, and reports two curves: novel-class accuracy and original-distribution accuracy versus correction count. We evaluate the substrate alongside nine baseline algorithms from five families plus seven bounded-storage variants of the substrate for the Pareto sweep, including standard online-learning baselines (river), continual-learning methods (EWC, A-GEM, LwF), retrieval/parametric hybrids (kNN-LM), parameter-efficient fine-tuning of a 1.5 B-parameter encoder (LoRA on DeBERTa-v3-large), and a hash-chained append-only substrate (Substrate). On Banking77 and CLINC150, under oracle and sparse correction policies, the substrate is the only system that simultaneously recovers novel-class accuracy (88.7 +/- 2.9 %) and retains original-distribution accuracy (95.4 +/- 0.8 %) beating the next-best published continual-learning baseline by 32.6 percentage points at equal memory budget, and beating LoRA-on-DeBERTa-v3-large by 84.6 percentage points on retention. We further find that classification accuracy remains stable at 99 % even as approximate-nearest-neighbour recall@5 degrades from 0.69 to 0.23 across 10 k to 10 M corpus scales, suggesting the substrate's margin-band majority vote is robust to retrieval imperfection in a way that pure top-k recall metrics do not predict. Code and data are available at https://github.com/adriangrassi/ocrr-benchmark. --- ### Are you with me? A Framework for Detecting Mental Model Discrepancies in Task-Based Team Dialogues Authors: Katharine Kowalyshyn, Matthias Scheutz Published: 2026-05-04 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.03149v1 Humans typically use natural language to update teammates on task states. Since not all updates are communicated, discrepancies arise between the team members' mental models that negatively affect overall team performance. How can we categorize such discrepancies? Do misalignments detected in team dialogue predict future mental model misalignments? Traditional shared mental model (SMM) assessment methods rely on retrospective expert coding that cannot capture real-time coordination dynamics. We propose a framework to identify and categorize four types of mental model discrepancies: unsupported beliefs, false beliefs, belief contradictions, and omissions, all of which can naturally emerge in team dialogues. Using dialogues from twenty dyad teams performing collaborative object identification tasks across four sequential levels, we demonstrate that these discrepancy patterns contain predictive signals. Averaging historical discrepancy counts achieves meaningful prediction accuracy using uniform weighting as an exploratory baseline, with differential predictability across discrepancy types. --- ### Boundary-Aware Uncertainty Quantification for Wildfire Spread Prediction Authors: Jonas V. Funk Published: 2026-05-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.03148v2 Reliable wildfire spread prediction is vital for risk-aware emergency planning, yet most deep learning models lack principled uncertainty quantification (UQ). Further, for boundary-sensitive cases like wildfire spread, evaluating models with global metrics alone is often insufficient. To shift the focus of UQ evaluation toward a more operationally relevant approach, the Fire-Centered Evaluation Region (FCER) framework is introduced as a spatially conditioned protocol to characterize UQ within critical fire zones. Using FCER, an Ensemble is compared against an distilled single-pass student model on the WildfireSpreadTS dataset. The student model demonstrates comparable calibration and complementary uncertainty ranking in boundary-relevant regimes. Code is available at https://github.com/jonasvilhofunk/WildfireUQ-FCER --- ### Effective Performance Measurement: Challenges and Opportunities in KPI Extraction from Earnings Calls Authors: Rasmus T. Aavang, Rasmus Tjalk-Bøggild, Alexandre Iolov, Giovanni Rizzi, Mike Zhang, Johannes Bjerva Published: 2026-05-04 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.03147v1 Earnings calls are a key source of financial information about public companies. However, extracting information from these calls is difficult. Unlike the templatic filings required by the U.S. Securities and Exchange Commission (SEC) to report a company's financial situation, earnings conference calls have no built-in labels, are unstructured, and feature conversational language. We explore this challenging domain by assessing the information captured by models trained on SEC filings and in-context learning methods. To establish a baseline, we first evaluate the generalization capabilities of SEC-trained models across established SEC datasets. To support our investigation, we introduce three novel benchmarks: (1) SEC Filings Benchmark (SECB), (2) Earnings Calls Benchmark (ECB), and ECB-A, a subset with 2,460 expert annotation groups to support our qualitative analysis. We find that encoder-based models struggle with the domain shift. Finally, we propose a system utilizing LLMs to perform open-ended extraction from unstructured call transcripts, verified by human evaluation (79.7% precision), providing a baseline for this valuable domain through the consistent tracking of emergent KPIs. --- ### NucEval: A Robust Evaluation Framework for Nuclear Instance Segmentation Authors: Amirreza Mahbod, Ramona Woitek, Jeanne Shen Published: 2026-05-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.03144v1 In computational pathology, nuclear instance segmentation is a fundamental task with many downstream clinical applications. With the advent of deep learning, many approaches, including convolutional neural networks (CNNs) and vision transformers (ViTs), have been proposed for this task, along with both machine learning-based and non-machine learning-based pre- and post-processing techniques to further boost performance. However, one fundamental aspect that has received less attention is the evaluation pipeline. In this study, we identify four key issues associated with nuclear instance segmentation evaluation and propose corresponding solutions. Our proposed modifications, namely handling vague regions, score normalization, overlapping instances, and border uncertainty, are integrated into a unified framework called NucEval, which enables robust evaluation of nuclear instance segmentation. We evaluate this pipeline using the NuInsSeg dataset, which provides unique characteristics that make it particularly suitable for this study, as well as two additional external datasets, with three CNN- and ViT-based nuclear instance segmentation models, to demonstrate the impact of these modifications on instance segmentation metrics. The code, along with complete guidelines and illustrative examples, is publicly available at: https://github.com/masih4/nuc_eval. --- ### Pact: A Choreographic Language for Agentic Ecosystems Authors: Kiran Gopinathan, Jack Feser, Michelangelo Naim, Zenna Tavares, Eli Bingham Published: 2026-05-04 Categories: cs.PL, cs.AI, cs.DC arXiv: https://arxiv.org/abs/2605.03143v1 Recent advances in large language models have led to the rise of software systems (i.e. agents) that execute with increasing autonomy on behalf of users in open, multi-party settings, interacting with untrusted counterparts and managing private information. Choreographic programming offers correct-by-construction protocol-design for such settings, but assumes cooperative participants -- it has no notion of agent self-interest, that is, why an agent will follow a protocol. In this talk we introduce Pact, a choreographic language extended with operations to describe agent choices and preferences, drawing from the rich literature of game theory. Every Pact protocol maps to a formal game, allowing protocol designers to reason about game-theoretic properties of their protocols, such as solving for decision policies. We present Pact's design and a preliminary implementation -- a bounded-rational solver that computes decision policies over Pact protocols -- and findings from applying this language to multi-party coordination with self-interested agentic participants. --- ### Instance-Level Costs for Nuanced Classifier Evaluation Authors: Kabir Kang, Stephen Mussmann Published: 2026-05-04 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.03135v2 Standard classification treats all errors equally, but in applications such as content moderation and medical screening, mistakes on clear-cut cases are more costly than errors on ambiguous ones. From a contextual bandit framework, we propose normalized excess cost (NEC), a metric that weighs classification errors by per-example costs and reduces to standard error rate when costs are uniform. Costs can derive from annotator vote margins, distance from decision thresholds, or confidence ratings. Across text, image, and tabular benchmarks, we find that NEC is often substantially lower than error rate: models with 5% error rate can achieve 1.8% NEC, revealing that most mistakes concentrate on ambiguous, low-cost examples. We also find that incorporating costs into training via loss weighting, sampling strategies, or regression yields inconsistent benefits. Our framework provides a practical methodology for deriving and evaluating instance-level misclassification costs, even if cost-sensitive training offers limited benefit. --- ### Bayesian inference with sources of uncertainty: from confidence modelling to sparse estimation Authors: Rafael Mouallem Rosa, Julyan Arbel, Hien Duy Nguyen Published: 2026-05-04 Categories: stat.ME, stat.ML arXiv: https://arxiv.org/abs/2605.03134v1 We introduce a general framework that extends Bayesian inference by allowing the researcher to explicitly encode confidence in each source of uncertainty within the model. This mechanism provides a new handle for model design and regularisation control. Building on this framework, we develop a general approach for inducing sparsity in statistical models and illustrate its use in linear and logistic regression, as well as in Bayesian neural networks. --- ### EMOVIS: Emotion-Optimized Image Processing Authors: Dor Barber, Rony Zatzarinni, Hava Matichin, Noam Levy Published: 2026-05-04 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2605.03131v1 In cinematography, visual attributes such as color grading, contrast, and brightness are manipulated to reinforce the emotional narrative of a scene. However, conventional Image Signal Processors (ISPs) prioritize scene fidelity, effectively neglecting this expressive dimension. To bring this cinematic capability to real-time camera pipelines during video capture, we introduce EMOVIS (EMotion-Optimized VISual processing). We establish a systematic mapping between a compact set of high-level emotional states (Happy, Calm, Angry, Sad) and low-level ISP controls - including color saturation, local tone mapping, and sharpness - supported by a calibration user study with statistically significant effects across parameters. We propose a control framework that integrates these emotion-driven adjustments into standard ISP hardware without altering the underlying processing stages. Validation via blind A/B testing shows that viewers prefer the emotion-optimized rendering in 87% of trials when the target emotion matches the scene context, indicating that emotion-aligned ISP control improves perceived suitability for expressive visual content. --- ### PIIGuard: Mitigating PII Harvesting under Adversarial Sanitization Authors: Mingshuo Liu, Yiwei Zha, Min Chen Published: 2026-05-04 Categories: cs.CR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2605.03129v1 Browsing-enabled LLM assistants can fetch webpages and answer contact-seeking queries, creating a practical channel for scraping contact-style personally identifiable information (PII) from public pages. Many prior defenses are deployed at the model, service, or agent layer rather than at the webpage itself, leaving ordinary page owners with limited deployable options. We present PIIGuard, a webpage-level defense that repurposes indirect prompt injection as a protective mechanism: the page owner embeds optimized hidden HTML fragments that steer the model away from verbatim or reconstructible disclosure of contact PII. PIIGuard searches over fragment text and insertion position using rule-based leakage scoring, evolutionary mutation, and final judge-based recoverability assessment. In direct-HTML evaluation on three target models (GPT-5.4-nano, Claude-haiku-4.5, and DeepSeek-chat(latest v3.2)), PIIGuard achieves at least 97.0% defense success rate under both rule-based and judge-based leakage evaluation, often reaching 100.0%, while preserving benign same-page QA utility. We further evaluate two harder settings: public-URL browsing and attacker-side LLM sanitization of fetched webpage. These results show that page-side defensive fragments can remain effective in deployment for some model-position pairs, but robustness varies substantially across browsing interfaces and sanitizer prompts. Overall, PIIGuard demonstrates that page owners can use page-side fragments as a practical mitigation for web-grounded PII leakage. --- ### Taming the Curses of Multiagency in Robust Markov Games with Large State Space through Linear Function Approximation Authors: Jingchu Gai, Laixi Shi Published: 2026-05-04 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.03125v2 Multi-agent reinforcement learning (MARL) holds great potential but faces robustness challenges due to environmental uncertainty. To address this, distributionally robust Markov games (RMGs) optimize worst-case performance when the environment deviates from the nominal model within a uncertainty set. Beyond robustness, an equally urgent goal for MARL is data efficiency -- sampling from vast state and action spaces that grow exponentially with the number of agents potentially leads to the curse of multiagency. However, current provably data-efficient algorithms for RMGs are limited to tabular settings with finite state and action spaces, which are only computationally manageable for small-scale problems, leaving RMGs with large-scale (or infinite) state spaces largely unexplored. The only existing work beyond tabular settings focuses on linear function approximation (LFA) for a restrictive class of RMGs using vanish minimal value assumption and still suffers from sample complexity with the curse of multiagency. In this work, we focuses on general RMGs with LFA. For uncertainty sets defined by total variation distance, we develop provably data-efficient algorithms that break the curse of multiagency in both the generative model setting and a newly proposed online interactive setting. To our knowledge, our results are the first to break the curse of multiagency of sample complexity for RMGs with large (possibly infinite) state spaces, regardless of the uncertainty set construction. --- ### ARISE: A Repository-level Graph Representation and Toolset for Agentic Program Repair and Fault Localization Authors: Shahd Seddik, Fahd Seddik, Amirrezza Esmaeili, Mahdieh Sadatbenis, Fatemeh Fard Published: 2026-05-04 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2605.03117v2 Automated program repair at repository scale requires an agent to locate a fault among thousands of files and synthesize a correct patch. Existing graph-based agents represent how a repository is organized into files, classes, and functions, but they do not model how variable values flow within a procedure, which leaves the agent without the semantic precision that function-level and line-level localization demand. We present ARISE (Agentic Repository-level Issue Solving Engine), a framework-agnostic toolset that builds a multi-granularity program graph, extending structural relationships down to statement-level nodes connected by intra-procedural definition-use edges, and exposes it through a three-tier tool API that mounts on any tool-use agentic framework. The central primitive is data-flow slicing, a queryable agent tool that traces in a single call which statements define or consume a variable of interest. On SWE-bench Lite (300 real GitHub issues across 11 Python repositories) with the open-source Qwen2.5-Coder-32B-Instruct backbone, mounting ARISE on SWE-agent as the host resolves 22.0% of issues (66/300), a 4.7 percentage-point gain over the unmodified SWE-agent baseline under the identical backbone and host. We show this gain is largely attributable to sharper localization, with Function Recall@1 (R@1) rising from 0.43 to 0.60 (a 40% relative gain) and Line R@1 from 0.26 to 0.41 (a 58% relative gain). Controlled ablations attribute the improvement to the data-flow graph rather than the tool schema, and we further mount the same toolset on a second host framework to study its portability. Decoupled from any single scaffold, the graph builder and slicing API form a drop-in toolset for future repair research. ---