# Research Papers — 2026-04 · bundle page 189 of 233

> Full-text markdown of papers #9401–9450 of 11612 published in 2026-04, newest first. AI-readable mirrors of the full 11612-paper 2026-04 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-04/page/189
[← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/188.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-04/page/190.md)

### VideoStir: Understanding Long Videos via Spatio-Temporally Structured and Intent-Aware RAG

Authors: Honghao Fu, Miao Xu, Yiwei Wang, Dailing Zhang, Jun Liu, Yujun Cai
Published: 2026-04-07
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2604.05418v3

Scaling multimodal large language models (MLLMs) to long videos is constrained by limited context windows. While retrieval-augmented generation (RAG) is a promising remedy by organizing query-relevant visual evidence into a compact context, most existing methods (i) flatten videos into independent segments, breaking their inherent spatio-temporal structure, and (ii) depend on explicit semantic matching, which can miss cues that are implicitly relevant to the query's intent. To overcome these limitations, we propose VideoStir, a structured and intent-aware long-video RAG framework. It firstly structures a video as a spatio-temporal graph at clip level, and then performs multi-hop retrieval to aggregate evidence across distant yet contextually related events. Furthermore, it introduces an MLLM-backed intent-relevance scorer that retrieves frames based on their alignment with the query's reasoning intent. To support this capability, we curate IR-600K, a large-scale dataset tailored for learning frame-query intent alignment. Experiments show that VideoStir is competitive with state-of-the-art baselines without relying on auxiliary information, highlighting the promise of shifting long-video RAG from flattened semantic matching to structured, intent-aware reasoning. Codes and checkpoints are available at https://github.com/RomGai/VideoStir.

---

### Multi-Drafter Speculative Decoding with Alignment Feedback

Authors: Taehyeon Kim, Hojung Jung, Se-Young Yun
Published: 2026-04-07
Categories: cs.CL
arXiv: https://arxiv.org/abs/2604.05417v1

Speculative decoding (SD) accelerates large language model (LLM) inference by using a smaller model to draft future tokens, which are then verified by the target LLM. This preserves generation quality by accepting only aligned tokens. However, individual drafters, often trained for specific tasks or domains, exhibit limited effectiveness across diverse applications. To address this, we introduce \textsc{MetaSD}, a unified framework that integrates multiple drafters into the SD process. MetaSD dynamically allocates computational resources to heterogeneous drafters by leveraging alignment feedback and framing drafter selection as a multi-armed bandit problem. Extensive experiments show MetaSD consistently outperforms single-drafter approaches.

---

### Multi-Agent Pathfinding with Non-Unit Integer Edge Costs via Enhanced Conflict-Based Search and Graph Discretization

Authors: Hongkai Fan, Qinjing Xie, Bo Ouyang, Yaonan Wang, Zhi Yan, Jiawen He, Zheng Fang
Published: 2026-04-07
Categories: cs.AI
arXiv: https://arxiv.org/abs/2604.05416v1

Multi-Agent Pathfinding (MAPF) plays a critical role in various domains. Traditional MAPF methods typically assume unit edge costs and single-timestep actions, which limit their applicability to real-world scenarios. MAPFR extends MAPF to handle non-unit costs with real-valued edge costs and continuous-time actions, but its geometric collision model leads to an unbounded state space that compromises solver efficiency. In this paper, we propose MAPFZ, a novel MAPF variant on graphs with non-unit integer costs that preserves a finite state space while offering improved realism over classical MAPF. To solve MAPFZ efficiently, we develop CBS-NIC, an enhanced Conflict-Based Search framework incorporating time-interval-based conflict detection and an improved Safe Interval Path Planning (SIPP) algorithm. Additionally, we propose Bayesian Optimization for Graph Design (BOGD), a discretization method for non-unit edge costs that balances efficiency and accuracy with a sub-linear regret bound. Extensive experiments demonstrate that our approach outperforms state-of-the-art methods in runtime and success rate across diverse benchmark scenarios.

---

### Learning to Synergize Semantic and Geometric Priors for Limited-Data Wheat Disease Segmentation

Authors: Shijie Wang, Zijian Wang, Yadan Luo, Scott Chapman, Xin Yu, Zi Huang
Published: 2026-04-07
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.05415v1

Wheat disease segmentation is fundamental to precision agriculture but faces severe challenges from significant intra-class temporal variations across growth stages. Such substantial appearance shifts make collecting a representative dataset for training from scratch both labor-intensive and impractical. To address this, we propose SGPer, a Semantic-Geometric Prior Synergization framework that treats wheat disease segmentation under limited data as a coupled task of disease-specific semantic perception and disease boundary localization. Our core insight is that pretrained DINOv2 provides robust category-aware semantic priors to handle appearance shifts, which can be converted into coarse spatial prompts to guide SAM for the precise localization of disease boundaries. Specifically, SGPer designs disease-sensitive adapters with multiple disease-friendly filters and inserts them into both DINOv2 and SAM to align their pretrained representations with disease-specific characteristics. To operationalize this synergy, SGPer transforms DINOv2-derived features into dense, category-specific point prompts to ensure comprehensive spatial coverage of all disease regions. To subsequently eliminate prompt redundancy and ensure highly accurate mask generation, it dynamically filters these dense candidates by cross-referencing SAM's iterative mask confidence with the category-specific semantic consistency derived from DINOv2. Ultimately, SGPer distills a highly informative set of prompts to activate SAM's geometric priors, achieving precise and robust segmentation that remains strictly invariant to temporal appearance changes. Extensive evaluations demonstrate that SGPer consistently achieves state-of-the-art performance on wheat disease and organ segmentation benchmarks, especially in data-constrained scenarios.

---

### Training Without Orthogonalization, Inference With SVD: A Gradient Analysis of Rotation Representations

Authors: Chris Choy
Published: 2026-04-07
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2604.05414v1

Recent work has shown that removing orthogonalization during training and applying it only at inference improves rotation estimation in deep learning, with empirical evidence favoring 9D representations with SVD projection. However, the theoretical understanding of why SVD orthogonalization specifically harms training, and why it should be preferred over Gram-Schmidt at inference, remains incomplete. We provide a detailed gradient analysis of SVD orthogonalization specialized to $3 \times 3$ matrices and $SO(3)$ projection. Our central result derives the exact spectrum of the SVD backward pass Jacobian: it has rank $3$ (matching the dimension of $SO(3)$) with nonzero singular values $2/(s_i + s_j)$ and condition number $κ= (s_1 + s_2)/(s_2 + s_3)$, creating quantifiable gradient distortion that is most severe when the predicted matrix is far from $SO(3)$ (e.g., early in training when $s_3 \approx 0$). We further show that even stabilized SVD gradients introduce gradient direction error, whereas removing SVD from the training loop avoids this tradeoff entirely. We also prove that the 6D Gram-Schmidt Jacobian has an asymmetric spectrum: its parameters receive unequal gradient signal, explaining why 9D parameterization is preferable. Together, these results provide the theoretical foundation for training with direct 9D regression and applying SVD projection only at inference.

---

### CRISP: Rank-Guided Iterative Squeezing for Robust Medical Image Segmentation under Domain Shift

Authors: Yizhou Fang, Pujin Cheng, Yixiang Liu, Xiaoying Tang, Longxi Zhou
Published: 2026-04-07
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.05409v1

Distribution shift in medical imaging remains a central bottleneck for the clinical translation of medical AI. Failure to address it can lead to severe performance degradation in unseen environments and exacerbate health inequities. Existing methods for domain adaptation are inherently limited by exhausting predefined possibilities through simulated shifts or pseudo-supervision. Such strategies struggle in the open-ended and unpredictable real world, where distribution shifts are effectively infinite. To address this challenge, we introduce an empirical law called ``Rank Stability of Positive Regions'', which states that the relative rank of predicted probabilities for positive voxels remains stable under distribution shift. Guided by this principle, we propose CRISP, a parameter-free and model-agnostic framework requiring no target-domain information. CRISP is the first framework to make segmentation based on rank rather than probabilities. CRISP simulates model behavior under distribution shift via latent feature perturbation, where voxel probability rankings exhibit two stable patterns: regions that consistently retain high probabilities (destined positives according to the principle) and those that remain low-probability (can be safely classified as negatives). Based on these patterns, we construct high-precision (HP) and high-recall (HR) priors and recursively refine them under perturbation. We then design an iterative training framework, making HP and HR progressively ``squeeze'' to the final segmentation. Extensive evaluations on multi-center cardiac MRI and CT-based lung vessel segmentation demonstrate CRISP's superior robustness, significantly outperforming state-of-the-art methods with striking HD95 reductions of up to 0.14 (7.0\% improvement), 1.90 (13.1\% improvement), and 8.39 (38.9\% improvement) pixels across multi-center, demographic, and modality shifts, respectively.

---

### CODESTRUCT: Code Agents over Structured Action Spaces

Authors: Myeongsoo Kim, Joe Hsu, Dingmin Wang, Shweta Garg, Varun Kumar, Murali Krishna Ramanathan
Published: 2026-04-07
Categories: cs.AI, cs.SE
arXiv: https://arxiv.org/abs/2604.05407v3

LLM-based code agents treat repositories as unstructured text, applying edits through brittle string matching that frequently fails due to formatting drift or ambiguous patterns. We propose reframing the codebase as a structured action space where agents operate on named AST entities rather than text spans. Our framework, CODESTRUCT, provides readCode for retrieving complete syntactic units and editCode for applying syntax-validated transformations to semantic program elements. Evaluated on SWE-Bench Verified across six LLMs, CODESTRUCT improves Pass@1 accuracy by 1.2-5.0% while reducing token consumption by 12-38% for most models. Models that frequently fail to produce valid patches under text-based interfaces benefit most: GPT-5-nano improves by 20.8% as empty-patch failures drop from 46.6% to 7.2%. On CodeAssistBench, we observe consistent accuracy gains (+0.8-4.4%) with cost reductions up to 33%. Our results show that structure-aware interfaces offer a more reliable foundation for code agents.

---

### Weather-Conditioned Branch Routing for Robust LiDAR-Radar 3D Object Detection

Authors: Hongsheng Li, Lingfeng Zhang, Zexian Yang, Liang Li, Rong Yin, Xiaoshuai Hao, Wenbo Ding
Published: 2026-04-07
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.05405v1

Robust 3D object detection in adverse weather is highly challenging due to the varying reliability of different sensors. While existing LiDAR-4D radar fusion methods improve robustness, they predominantly rely on fixed or weakly adaptive pipelines, failing to dy-namically adjust modality preferences as environmental conditions change. To bridge this gap, we reformulate multi-modal perception as a weather-conditioned branch routing problem. Instead of computing a single fused output, our framework explicitly maintains three parallel 3D feature streams: a pure LiDAR branch, a pure 4D radar branch, and a condition-gated fusion branch. Guided by a condition token extracted from visual and semantic prompts, a lightweight router dynamically predicts sample-specific weights to softly aggregate these representations. Furthermore, to prevent branch collapse, we introduce a weather-supervised learning strategy with auxiliary classification and diversity regularization to enforce distinct, condition-dependent routing behaviors. Extensive experiments on the K-Radar benchmark demonstrate that our method achieves state-of-the-art performance. Furthermore, it provides explicit and highly interpretable insights into modality preferences, transparently revealing how adaptive routing robustly shifts reliance between LiDAR and 4D radar across diverse adverse-weather scenarios. The source code with be released.

---

### LSGS-Loc: Towards Robust 3DGS-Based Visual Localization for Large-Scale UAV Scenarios

Authors: Xiang Zhang, Tengfei Wang, Fang Xu, Xin Wang, Zongqian Zhan
Published: 2026-04-07
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2604.05402v1

Visual localization in large-scale UAV scenarios is a critical capability for autonomous systems, yet it remains challenging due to geometric complexity and environmental variations. While 3D Gaussian Splatting (3DGS) has emerged as a promising scene representation, existing 3DGS-based visual localization methods struggle with robust pose initialization and sensitivity to rendering artifacts in large-scale settings. To address these limitations, we propose LSGS-Loc, a novel visual localization pipeline tailored for large-scale 3DGS scenes. Specifically, we introduce a scale-aware pose initialization strategy that combines scene-agnostic relative pose estimation with explicit 3DGS scale constraints, enabling geometrically grounded localization without scene-specific training. Furthermore, in the pose refinement, to mitigate the impact of reconstruction artifacts such as blur and floaters, we develop a Laplacian-based reliability masking mechanism that guides photometric refinement toward high-quality regions. Extensive experiments on large-scale UAV benchmarks demonstrate that our method achieves state-of-the-art accuracy and robustness for unordered image queries, significantly outperforming existing 3DGS-based approaches. Code is available at: https://github.com/xzhang-z/LSGS-Loc

---

### HYVE: Hybrid Views for LLM Context Engineering over Machine Data

Authors: Jian Tan, Fan Bu, Yuqing Gao, Dev Khanolkar, Jason Mackay, Boris Sobolev, Lei Jin, Li Zhang
Published: 2026-04-07
Categories: cs.AI
arXiv: https://arxiv.org/abs/2604.05400v1

Machine data is central to observability and diagnosis in modern computing systems, appearing in logs, metrics, telemetry traces, and configuration snapshots. When provided to large language models (LLMs), this data typically arrives as a mixture of natural language and structured payloads such as JSON or Python/AST literals. Yet LLMs remain brittle on such inputs, particularly when they are long, deeply nested, and dominated by repetitive structure. We present HYVE (HYbrid ViEw), a framework for LLM context engineering for inputs containing large machine-data payloads, inspired by database management principles. HYVE surrounds model invocation with coordinated preprocessing and postprocessing, centered on a request-scoped datastore augmented with schema information. During preprocessing, HYVE detects repetitive structure in raw inputs, materializes it in the datastore, transforms it into hybrid columnar and row-oriented views, and selectively exposes only the most relevant representation to the LLM. During postprocessing, HYVE either returns the model output directly, queries the datastore to recover omitted information, or performs a bounded additional LLM call for SQL-augmented semantic synthesis. We evaluate HYVE on diverse real-world workloads spanning knowledge QA, chart generation, anomaly detection, and multi-step network troubleshooting. Across these benchmarks, HYVE reduces token usage by 50-90% while maintaining or improving output quality. On structured generation tasks, it improves chart-generation accuracy by up to 132% and reduces latency by up to 83%. Overall, HYVE offers a practical approximation to an effectively unbounded context window for prompts dominated by large machine-data payloads.

---

### An Actor-Critic Framework for Continuous-Time Jump-Diffusion Controls with Normalizing Flows

Authors: Liya Guo, Ruimeng Hu, Xu Yang, Yi Zhu
Published: 2026-04-07
Categories: math.OC, cs.LG
arXiv: https://arxiv.org/abs/2604.05398v1

Continuous-time stochastic control with time-inhomogeneous jump-diffusion dynamics is central in finance and economics, but computing optimal policies is difficult under explicit time dependence, discontinuous shocks, and high dimensionality. We propose an actor-critic framework that serves as a mesh-free solver for entropy-regularized control problems and stochastic games with jumps. The approach is built on a time-inhomogeneous little q-function and an appropriate occupation measure, yielding a policy-gradient representation that accommodates time-dependent drift, volatility, and jump terms. To represent expressive stochastic policies in continuous-action spaces, we parameterize the actor using conditional normalizing flows, enabling flexible non-Gaussian policies while retaining exact likelihood evaluation for entropy regularization and policy optimization. We validate the method on time-inhomogeneous linear-quadratic control, Merton portfolio optimization, and a multi-agent portfolio game, using explicit solutions or high-accuracy benchmarks. Numerical results demonstrate stable learning under jump discontinuities, accurate approximation of optimal stochastic policies, and favorable scaling with respect to dimension and number of agents.

---

### Confidence Should Be Calibrated More Than One Turn Deep

Authors: Zhaohan Zhang, Chengzhengxu Li, Xiaoming Liu, Chao Shen, Ziquan Liu, Ioannis Patras
Published: 2026-04-07
Categories: cs.CL
arXiv: https://arxiv.org/abs/2604.05397v1

Large Language Models (LLMs) are increasingly applied in high-stakes domains such as finance, healthcare, and education, where reliable multi-turn interactions with users are essential. However, existing work on confidence estimation and calibration, a major approach to building trustworthy LLM systems, largely focuses on single-turn settings and overlooks the risks and potential of multi-turn conversations. In this work, we introduce the task of multi-turn calibration to reframe calibration from a static property into a dynamic challenge central to reliable multi-turn conversation, where calibrating model confidence at each turn conditioned on the conversation history is required. We first reveal the risks of this setting: using Expected Calibration Error at turn T (ECE@T), a new metric that tracks calibration dynamics over turns, we show that user feedback (e.g., persuasion) can degrade multi-turn calibration. To address this, we propose MTCal, which minimises ECE@T via a surrogate calibration target, and further leverage calibrated confidence in ConfChat, a decoding strategy that improves both factuality and consistency of the model response in multi-turn interactions. Extensive experiments demonstrate that MT-Cal achieves outstanding and consistent performance in multi-turn calibration, and ConfChat preserves and even enhances model performance in multi-turn interactions. Our results mark multi-turn calibration as one missing link for scaling LLM calibration toward safe, reliable, and real-world use.

---

### Reason Analogically via Cross-domain Prior Knowledge: An Empirical Study of Cross-domain Knowledge Transfer for In-Context Learning

Authors: Le Liu, Zhiming Li, Jianzhi Yan, Zike Yuan, Shiwei Chen, Youcheng Pan, Buzhou Tang, Qingcai Chen, Yang Xiang, Danny Dongning Sun
Published: 2026-04-07
Categories: cs.AI
arXiv: https://arxiv.org/abs/2604.05396v1

Despite its success, existing in-context learning (ICL) relies on in-domain expert demonstrations, limiting its applicability when expert annotations are scarce. We posit that different domains may share underlying reasoning structures, enabling source-domain demonstrations to improve target-domain inference despite semantic mismatch. To test this hypothesis, we conduct a comprehensive empirical study of different retrieval methods to validate the feasibility of achieving cross-domain knowledge transfer under the in-context learning setting. Our results demonstrate conditional positive transfer in cross-domain ICL. We identify a clear example absorption threshold: beyond it, positive transfer becomes more likely, and additional demonstrations yield larger gains. Further analysis suggests that these gains stem from reasoning structure repair by retrieved cross-domain examples, rather than semantic cues. Overall, our study validates the feasibility of leveraging cross-domain knowledge transfer to improve cross-domain ICL performance, motivating the community to explore designing more effective retrieval approaches for this novel direction.\footnote{Our implementation is available at https://github.com/littlelaska/ICL-TF4LR}

---

### Neural Assistive Impulses: Synthesizing Exaggerated Motions for Physics-based Characters

Authors: Zhiquan Wang, Bedrich Benes
Published: 2026-04-07
Categories: cs.AI, cs.GR
arXiv: https://arxiv.org/abs/2604.05394v1

Physics-based character animation has become a fundamental approach for synthesizing realistic, physically plausible motions. While current data-driven deep reinforcement learning (DRL) methods can synthesize complex skills, they struggle to reproduce exaggerated, stylized motions, such as instantaneous dashes or mid-air trajectory changes, which are required in animation but violate standard physical laws. The primary limitation stems from modeling the character as an underactuated floating-base system, in which internal joint torques and momentum conservation strictly govern motion. Direct attempts to enforce such motions via external wrenches often lead to training instability, as velocity discontinuities produce sparse, high-magnitude force spikes that prevent policy convergence. We propose Assistive Impulse Neural Control, a framework that reformulates external assistance in impulse space rather than force space to ensure numerical stability. We decompose the assistive signal into an analytic high-frequency component derived from Inverse Dynamics and a learned low-frequency residual correction, governed by a hybrid neural policy. We demonstrate that our method enables robust tracking of highly agile, dynamically infeasible maneuvers that were previously intractable for physics-based methods.

---

### Beyond Semantic Search: Towards Referential Anchoring in Composed Image Retrieval

Authors: Yuxin Yang, Yinan Zhou, Yuxin Chen, Ziqi Zhang, Zongyang Ma, Chunfeng Yuan, Bing Li, Jun Gao, Weiming Hu
Published: 2026-04-07
Categories: cs.CV, cs.MM
arXiv: https://arxiv.org/abs/2604.05393v1

Composed Image Retrieval (CIR) has demonstrated significant potential by enabling flexible multimodal queries that combine a reference image and modification text. However, CIR inherently prioritizes semantic matching, struggling to reliably retrieve a user-specified instance across contexts. In practice, emphasizing concrete instance fidelity over broad semantics is often more consequential. In this work, we propose Object-Anchored Composed Image Retrieval (OACIR), a novel fine-grained retrieval task that mandates strict instance-level consistency. To advance research on this task, we construct OACIRR (OACIR on Real-world images), the first large-scale, multi-domain benchmark comprising over 160K quadruples and four challenging candidate galleries enriched with hard-negative instance distractors. Each quadruple augments the compositional query with a bounding box that visually anchors the object in the reference image, providing a precise and flexible way to ensure instance preservation. To address the OACIR task, we propose AdaFocal, a framework featuring a Context-Aware Attention Modulator that adaptively intensifies attention within the specified instance region, dynamically balancing focus between the anchored instance and the broader compositional context. Extensive experiments demonstrate that AdaFocal substantially outperforms existing compositional retrieval models, particularly in maintaining instance-level fidelity, thereby establishing a robust baseline for this challenging task while opening new directions for more flexible, instance-aware retrieval systems.

---

### LUMOS: Universal Semi-Supervised OCT Retinal Layer Segmentation with Hierarchical Reliable Mutual Learning

Authors: Yizhou Fang, Jian Zhong, Li Lin, Xiaoying Tang
Published: 2026-04-07
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.05388v1

Optical Coherence Tomography (OCT) layer segmentation faces challenges due to annotation scarcity and heterogeneous label granularities across datasets. While semi-supervised learning helps alleviate label scarcity, existing methods typically assume a fixed granularity, failing to fully exploit cross-granularity supervision. This paper presents LUMOS, a semi-supervised universal OCT retinal layer segmentation framework based on a Dual-Decoder Network with a Hierarchical Prompting Strategy (DDN-HPS) and Reliable Progressive Multi-granularity Learning (RPML). DDN-HPS combines a dual-branch architecture with a multi-granularity prompting strategy to effectively suppress pseudo-label noise propagation. Meanwhile, RPML introduces region-level reliability weighing and a progressive training approach that guides the model from easier to more difficult tasks, ensuring the reliable selection of cross-granularity consistency targets, thereby achieving stable cross-granularity alignment. Experiments on six OCT datasets demonstrate that LUMOS largely outperforms existing methods and exhibits exceptional cross-domain and cross-granularity generalization capability.

---

### Data-Driven Function Calling Improvements in Large Language Model for Online Financial QA

Authors: Xing Tang, Hao Chen, Shiwei Li, Fuyuan Lyu, Weijie Shi, Lingjie Li, Dugang Liu, Weihong Luo, Xiku Du, Xiuqiang He
Published: 2026-04-07
Categories: cs.IR, cs.CL
arXiv: https://arxiv.org/abs/2604.05387v1

Large language models (LLMs) have been incorporated into numerous industrial applications. Meanwhile, a vast array of API assets is scattered across various functions in the financial domain. An online financial question-answering system can leverage both LLMs and private APIs to provide timely financial analysis and information. The key is equipping the LLM model with function calling capability tailored to a financial scenario. However, a generic LLM requires customized financial APIs to call and struggles to adapt to the financial domain. Additionally, online user queries are diverse and contain out-of-distribution parameters compared with the required function input parameters, which makes it more difficult for a generic LLM to serve online users. In this paper, we propose a data-driven pipeline to enhance function calling in LLM for our online, deployed financial QA, comprising dataset construction, data augmentation, and model training. Specifically, we construct a dataset based on a previous study and update it periodically, incorporating queries and an augmentation method named AugFC. The addition of user query-related samples will \textit{exploit} our financial toolset in a data-driven manner, and AugFC explores the possible parameter values to enhance the diversity of our updated dataset. Then, we train an LLM with a two-step method, which enables the use of our financial functions. Extensive experiments on existing offline datasets, as well as the deployment of an online scenario, illustrate the superiority of our pipeline. The related pipeline has been adopted in the financial QA of YuanBao\footnote{https://yuanbao.tencent.com/chat/}, one of the largest chat platforms in China.

---

### Towards Effective In-context Cross-domain Knowledge Transfer via Domain-invariant-neurons-based Retrieval

Authors: Jianzhi Yan, Zhiming Li, Le Liu, Zike Yuan, Shiwei Chen, Youcheng Pan, Buzhou Tang, Yang Xiang, Danny Dongning Sun
Published: 2026-04-07
Categories: cs.AI
arXiv: https://arxiv.org/abs/2604.05383v1

Large language models (LLMs) have made notable progress in logical reasoning, yet still fall short of human-level performance. Current boosting strategies rely on expert-crafted in-domain demonstrations, limiting their applicability in expertise-scarce domains, such as specialized mathematical reasoning, formal logic, or legal analysis. In this work, we demonstrate the feasibility of leveraging cross-domain demonstrating examples to boost the LLMs' reasoning performance. Despite substantial domain differences, many reusable implicit logical structures are shared across domains. In order to effectively retrieve cross-domain examples for unseen domains under investigation, in this work, we further propose an effective retrieval method, called domain-invariant neurons-based retrieval (\textbf{DIN-Retrieval}). Concisely, DIN-Retrieval first summarizes a hidden representation that is universal across different domains. Then, during the inference stage, we use the DIN vector to retrieve structurally compatible cross-domain demonstrations for the in-context learning. Experimental results in multiple settings for the transfer of mathematical and logical reasoning demonstrate that our method achieves an average improvement of 1.8 over the state-of-the-art methods \footnote{Our implementation is available at https://github.com/Leon221220/DIN-Retrieval}.

---

### Retrieve-then-Adapt: Retrieval-Augmented Test-Time Adaptation for Sequential Recommendation

Authors: Xing Tang, Ziqiang Cui, Jingyang Bin, Xiaokun Zhang, Fuyuan Lyu, Jingyan Jiang, Dugang Liu, Chen Ma, Xiuqiang He
Published: 2026-04-07
Categories: cs.IR, cs.LG
arXiv: https://arxiv.org/abs/2604.05379v2

The sequential recommendation (SR) task aims to predict the next item based on users' historical interaction sequences. Typically trained on historical data, SR models often struggle to adapt to real-time preference shifts during inference due to challenges posed by distributional divergence and parameterized constraints. Existing approaches to address this issue include test-time training, test-time augmentation, and retrieval-augmented fine-tuning. However, these methods either introduce significant computational overhead, rely on random augmentation strategies, or require a carefully designed two-stage training paradigm. In this paper, we argue that the key to effective test-time adaptation lies in achieving both effective augmentation and efficient adaptation. To this end, we propose Retrieve-then-Adapt (ReAd), a novel framework that dynamically adapts a deployed SR model to the test distribution through retrieved user preference signals. Specifically, given a trained SR model, ReAd first retrieves collaboratively similar items for a test user from a constructed collaborative memory database. A lightweight retrieval learning module then integrates these items into an informative augmentation embedding that captures both collaborative signals and prediction-refinement cues. Finally, the initial SR prediction is refined via a fusion mechanism that incorporates this embedding. Extensive experiments across five benchmark datasets demonstrate that ReAd consistently outperforms existing SR methods.

---

### Retrieve-then-Adapt: Retrieval-Augmented Test-Time Adaptation for Sequential Recommendation

Authors: Xing Tang, Jingyang Bin, Ziqiang Cui, Xiaokun Zhang, Fuyuan Lyu, Jingyan Jiang, Dugang Liu, Chen Ma, Xiuqiang He
Published: 2026-04-07
Categories: cs.IR, cs.LG
arXiv: https://arxiv.org/abs/2604.05379v1

The sequential recommendation (SR) task aims to predict the next item based on users' historical interaction sequences. Typically trained on historical data, SR models often struggle to adapt to real-time preference shifts during inference due to challenges posed by distributional divergence and parameterized constraints. Existing approaches to address this issue include test-time training, test-time augmentation, and retrieval-augmented fine-tuning. However, these methods either introduce significant computational overhead, rely on random augmentation strategies, or require a carefully designed two-stage training paradigm. In this paper, we argue that the key to effective test-time adaptation lies in achieving both effective augmentation and efficient adaptation. To this end, we propose Retrieve-then-Adapt (ReAd), a novel framework that dynamically adapts a deployed SR model to the test distribution through retrieved user preference signals. Specifically, given a trained SR model, ReAd first retrieves collaboratively similar items for a test user from a constructed collaborative memory database. A lightweight retrieval learning module then integrates these items into an informative augmentation embedding that captures both collaborative signals and prediction-refinement cues. Finally, the initial SR prediction is refined via a fusion mechanism that incorporates this embedding. Extensive experiments across five benchmark datasets demonstrate that ReAd consistently outperforms existing SR methods.

---

### ICR-Drive: Instruction Counterfactual Robustness for End-to-End Language-Driven Autonomous Driving

Authors: Kaiser Hamid, Can Cui, Nade Liang
Published: 2026-04-07
Categories: cs.CL, cs.CV
arXiv: https://arxiv.org/abs/2604.05378v1

Recent progress in vision-language-action (VLA) models has enabled language-conditioned driving agents to execute natural-language navigation commands in closed-loop simulation, yet standard evaluations largely assume instructions are precise and well-formed. In deployment, instructions vary in phrasing and specificity, may omit critical qualifiers, and can occasionally include misleading, authority-framed text, leaving instruction-level robustness under-measured. We introduce ICR-Drive, a diagnostic framework for instruction counterfactual robustness in end-to-end language-conditioned autonomous driving. ICR-Drive generates controlled instruction variants spanning four perturbation families: Paraphrase, Ambiguity, Noise, and Misleading, where Misleading variants conflict with the navigation goal and attempt to override intent. We replay identical CARLA routes under matched simulator configurations and seeds to isolate performance changes attributable to instruction language. Robustness is quantified using standard CARLA Leaderboard metrics and per-family performance degradation relative to the baseline instruction. Experiments on LMDrive and BEVDriver show that minor instruction changes can induce substantial performance drops and distinct failure modes, revealing a reliability gap for deploying embodied foundation models in safety-critical driving.

---

### Can Vision-Language Models Think from the Sky? Unifying UAV Reasoning and Generation

Authors: Jintao Sun, Gangyi Ding, Donglin Di, Hu Zhang, Zhedong Zheng
Published: 2026-04-07
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.05377v2

Vision-Language Models have achieved strong progress in ground-view visual understanding, yet they remain brittle in high-altitude Unmanned Aerial Vehicle scenes, where objects are tiny and densely packed, textures are repetitive, and top-down orientations are ambiguous. We introduce UAVReason, a large-scale UAV-native dataset and evaluation suite for studying unified aerial reasoning and generation under this nadir-view domain shift. UAVReason aligns RGB imagery, depth maps, semantic segmentation masks, captions, and question-answer pairs within a consistent aerial domain. It contains 23.6K captioned frames, 273K VQA pairs including 68.2K two-frame temporal questions, and 188.8K cross-modal generation samples across RGB, depth, and segmentation modalities. We further adapt UAVReason-Bagel as a unified understanding-and-generation baseline that jointly optimizes language reasoning and dense visual generation objectives. Experiments show that general-purpose VLMs and off-the-shelf unified generators struggle with UAV-native grounding, while UAVReason-Bagel substantially improves over its pretrained counterpart, increasing VQA-1F F1 from 0.394 to 0.711, VQA-2F F1 from 0.427 to 0.822, and heading-aware VQA F1 from 0.798 to 0.973. For generation, it improves segmentation mIoU to 0.143 and reduces KID from 0.078 to 0.048 for depth-segmentation-text-conditioned RGB synthesis. More importantly, our ablations reveal a bidirectional synergy between synthesis and reasoning. Dense generation objectives improve temporal semantic consistency, while language-level reasoning regularizes sparse-condition image synthesis. These results suggest that unified reasoning and generation provide effective geometry-aware structural priors for physically grounded aerial intelligence. All data, code, and evaluation tools will be released.

---

### LMI-Net: Linear Matrix Inequality--Constrained Neural Networks via Differentiable Projection Layers

Authors: Sunbochen Tang, Andrea Goertzen, Navid Azizan
Published: 2026-04-07
Categories: cs.LG
arXiv: https://arxiv.org/abs/2604.05374v1

Linear matrix inequalities (LMIs) have played a central role in certifying stability, robustness, and forward invariance of dynamical systems. Despite rapid development in learning-based methods for control design and certificate synthesis, existing approaches often fail to preserve the hard matrix inequality constraints required for formal guarantees. We propose LMI-Net, an efficient and modular differentiable projection layer that enforces LMI constraints by construction. Our approach lifts the set defined by LMI constraints into the intersection of an affine equality constraint and the positive semidefinite cone, performs the forward pass via Douglas-Rachford splitting, and supports efficient backward propagation through implicit differentiation. We establish theoretical guarantees that the projection layer converges to a feasible point, certifying that LMI-Net transforms a generic neural network into a reliable model satisfying LMI constraints. Evaluated on experiments including invariant ellipsoid synthesis and joint controller-and-certificate design for a family of disturbed linear systems, LMI-Net substantially improves feasibility over soft-constrained models under distribution shift while retaining fast inference speed, bridging semidefinite-program-based certification and modern learning techniques.

---

### LLM-as-Judge for Semantic Judging of Powerline Segmentation in UAV Inspection

Authors: Akram Hossain, Rabab Abdelfattah, Xiaofeng Wang, Kareem Abdelfatah
Published: 2026-04-07
Categories: cs.AI
arXiv: https://arxiv.org/abs/2604.05371v1

The deployment of lightweight segmentation models on drones for autonomous power line inspection presents a critical challenge: maintaining reliable performance under real-world conditions that differ from training data. Although compact architectures such as U-Net enable real-time onboard inference, their segmentation outputs can degrade unpredictably in adverse environments, raising safety concerns. In this work, we study the feasibility of using a large language model (LLM) as a semantic judge to assess the reliability of power line segmentation results produced by drone-mounted models. Rather than introducing a new inspection system, we formalize a watchdog scenario in which an offboard LLM evaluates segmentation overlays and examine whether such a judge can be trusted to behave consistently and perceptually coherently. To this end, we design two evaluation protocols that analyze the judge's repeatability and sensitivity. First, we assess repeatability by repeatedly querying the LLM with identical inputs and fixed prompts, measuring the stability of its quality scores and confidence estimates. Second, we evaluate perceptual sensitivity by introducing controlled visual corruptions (fog, rain, snow, shadow, and sunflare) and analyzing how the judge's outputs respond to progressive degradation in segmentation quality. Our results show that the LLM produces highly consistent categorical judgments under identical conditions while exhibiting appropriate declines in confidence as visual reliability deteriorates. Moreover, the judge remains responsive to perceptual cues such as missing or misidentified power lines, even under challenging conditions. These findings suggest that, when carefully constrained, an LLM can serve as a reliable semantic judge for monitoring segmentation quality in safety-critical aerial inspection tasks.

---

### AI and Collective Decisions: Strengthening Legitimacy and Losers' Consent

Authors: Suyash Fulay, Prerna Ravi, Emily Kubin, Shrestha Mohanty, Michiel Bakker, Deb Roy
Published: 2026-04-07
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2604.05368v1

AI is increasingly used to scale collective decision-making, but far less attention has been paid to how such systems can support procedural legitimacy, particularly the conditions shaping losers' consent: whether participants who do not get their preferred outcome still accept it as fair. We ask: (1) how can AI help ground collective decisions in participants' different experiences and beliefs, and (2) whether exposure to these experiences can increase trust, understanding, and social cohesion even when people disagree with the outcome. We built a system that uses a semi-structured AI interviewer to elicit personal experiences on policy topics and an interactive visualization that displays predicted policy support alongside those voiced experiences. In a randomized experiment (n = 181), interacting with the visualization increased perceived legitimacy, trust in outcomes, and understanding of others' perspectives, even though all participants encountered decisions that went against their stated preferences. Our hope is that the design and evaluation of this tool spurs future researchers to focus on how AI can help not only achieve scale and efficiency in democratic processes, but also increase trust and connection between participants.

---

### 3DTurboQuant: Training-Free Near-Optimal Quantization for 3D Reconstruction Models

Authors: Jae Joong Lee
Published: 2026-04-07
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2604.05366v1

Every existing method for compressing 3D Gaussian Splatting, NeRF, or transformer-based 3D reconstructors requires learning a data-dependent codebook through per-scene fine-tuning. We show this is unnecessary. The parameter vectors that dominate storage in these models, 45-dimensional spherical harmonics in 3DGS and 1024-dimensional key-value vectors in DUSt3R, fall in a dimension range where a single random rotation transforms any input into coordinates with a known Beta distribution. This makes precomputed, data-independent Lloyd-Max quantization near-optimal, within a factor of 2.7 of the information-theoretic lower bound. We develop 3D, deriving (1) a dimension-dependent criterion that predicts which parameters can be quantized and at what bit-width before running any experiment, (2) norm-separation bounds connecting quantization MSE to rendering PSNR per scene, (3) an entry-grouping strategy extending rotation-based quantization to 2-dimensional hash grid features, and (4) a composable pruning-quantization pipeline with a closed-form compression ratio. On NeRF Synthetic, 3DTurboQuant compresses 3DGS by 3.5x with 0.02dB PSNR loss and DUSt3R KV caches by 7.9x with 39.7dB pointmap fidelity. No training, no codebook learning, no calibration data. Compression takes seconds. The code will be released (https://github.com/JaeLee18/3DTurboQuant)

---

### TFRBench: A Reasoning Benchmark for Evaluating Forecasting Systems

Authors: Md Atik Ahamed, Mihir Parmar, Palash Goyal, Yiwen Song, Long T. Le, Qiang Cheng, Chun-Liang Li, Hamid Palangi, Jinsung Yoon, Tomas Pfister
Published: 2026-04-07
Categories: cs.AI
arXiv: https://arxiv.org/abs/2604.05364v1

We introduce TFRBench, the first benchmark designed to evaluate the reasoning capabilities of forecasting systems. Traditionally, time-series forecasting has been evaluated solely on numerical accuracy, treating foundation models as ``black boxes.'' Unlike existing benchmarks, TFRBench provides a protocol for evaluating the reasoning generated by forecasting systems--specifically their analysis of cross-channel dependencies, trends, and external events. To enable this, we propose a systematic multi-agent framework that utilizes an iterative verification loop to synthesize numerically grounded reasoning traces. Spanning ten datasets across five domains, our evaluation confirms that this reasoning is causally effective; useful for evaluation; and prompting LLMs with our generated traces significantly improves forecasting accuracy compared to direct numerical prediction (e.g., avg. $\sim40.2\%\to56.6\%)$, validating the quality of our reasoning. Conversely, benchmarking experiments reveal that off-the-shelf LLMs consistently struggle with both reasoning (lower LLM-as-a-Judge scores) and numerical forecasting, frequently failing to capture domain-specific dynamics. TFRBench thus establishes a new standard for interpretable, reasoning-based evaluation in time-series forecasting. Our benchmark is available at: https://tfrbench.github.io

---

### Rethinking IRSTD: Single-Point Supervision Guided Encoder-only Framework is Enough for Infrared Small Target Detection

Authors: Rixiang Ni, Boyang Li, Jun Chen, Yonghao Li, Feiyu Ren, Yuji Wang, Haoyang Yuan, Wujiao He, Wei An
Published: 2026-04-07
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.05363v2

Infrared small target detection (IRSTD) aims to separate small targets from clutter backgrounds. Extensive research is dedicated to the pixel-level supervision-guided "encoder-decoder" segmentation paradigm. Although having achieved promising performance, they neglect the fact that small targets only occupy a few pixels and are usually accompanied with blurred boundary caused by clutter backgrounds. Based on this observation, we argue that the first principle of IRSTD should be target localization instead of separating all target region accompanied with indistinguishable background noise. In this paper, we reformulate IRSTD as a centroid regression task and propose a novel Single-Point Supervision guided Infrared Probabilistic Response Encoding method (namely, SPIRE), which is indeed challenging due to the mismatch between reduced supervision network and equivalent output. Specifically, we first design a Point-Response Prior Supervision (PRPS), which transforms single-point annotations into probabilistic response map consistent with infrared point-target response characteristics, with a High-Resolution Probabilistic Encoder (HRPE) that enables encoder-only, end-to-end regression without decoder reconstruction. By preserving high-resolution features and increasing effective supervision density, SPIRE alleviates optimization instability under sparse target distributions. Finally, extensive experiments on various IRSTD benchmarks, including SIRST-UAVB and SIRST4 demonstrate that SPIRE achieves competitive target-level detection performance with consistently low false alarm rate (Fa) and significantly reduced computational cost. Code is publicly available at: https://github.com/NIRIXIANG/SPIRE-IRSTD.

---

### OGA-AID: Clinician-in-the-loop AI Report Drafting Assistant for Multimodal Observational Gait Analysis in Post-Stroke Rehabilitation

Authors: Khoi T. N. Nguyen, Nghia D. Nguyen, Hui Yu Koh, Patrick W. H. Kwong, Karen Sui Geok Chua, Ananda Sidarta, Baosheng Yu
Published: 2026-04-07
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2604.05360v2

Gait analysis is essential in post-stroke rehabilitation but remains time-intensive and cognitively demanding, especially when clinicians must integrate gait videos and motion-capture data into structured reports. We present OGA-AID, a clinician-in-the-loop multi-agent large language model system for multimodal report drafting. The system coordinates 3 specialized agents to synthesize patient movement recordings, kinematic trajectories, and clinical profiles into structured assessments. Evaluated with expert physiotherapists on real patient data, OGA-AID consistently outperforms single-pass multimodal baselines with low error. In clinician-in-the-loop settings, brief expert preliminary notes further reduce error compared to reference assessments. Our findings demonstrate the feasibility of multimodal agentic systems for structured clinical gait assessment and highlight the complementary relationship between AI-assisted analysis and human clinical judgment in rehabilitation workflows.

---

### GESS: Multi-cue Guided Local Feature Learning via Geometric and Semantic Synergy

Authors: Yang Yi, Xieyuanli Chen, Jinpu Zhang, Hui Shen, Dewen Hu
Published: 2026-04-07
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.05359v1

Robust local feature detection and description are foundational tasks in computer vision. Existing methods primarily rely on single appearance cues for modeling, leading to unstable keypoints and insufficient descriptor discriminability. In this paper, we propose a multi-cue guided local feature learning framework that leverages semantic and geometric cues to synergistically enhance detection robustness and descriptor discriminability. Specifically, we construct a joint semantic-normal prediction head and a depth stability prediction head atop a lightweight backbone. The former leverages a shared 3D vector field to deeply couple semantic and normal cues, thereby resolving optimization interference from heterogeneous inconsistencies. The latter quantifies the reliability of local regions from a geometric consistency perspective, providing deterministic guidance for robust keypoint selection. Based on these predictions, we introduce the Semantic-Depth Aware Keypoint (SDAK) mechanism for feature detection. By coupling semantic reliability with depth stability, SDAK reweights keypoint responses to suppress spurious features in unreliable regions. For descriptor construction, we design a Unified Triple-Cue Fusion (UTCF) module, which employs a semantic-scheduled gating mechanism to adaptively inject multi-attribute features, improving descriptor discriminability. Extensive experiments on four benchmarks validate the effectiveness of the proposed framework. The source code and pre-trained model will be available at: https://github.com/yiyscut/GESS.git.

---

### LatentAudit: Real-Time White-Box Faithfulness Monitoring for Retrieval-Augmented Generation with Verifiable Deployment

Authors: Zhe Yu, Wenpeng Xing, Meng Han
Published: 2026-04-07
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2604.05358v1

Retrieval-augmented generation (RAG) mitigates hallucination but does not eliminate it: a deployed system must still decide, at inference time, whether its answer is actually supported by the retrieved evidence. We introduce LatentAudit, a white-box auditor that pools mid-to-late residual-stream activations from an open-weight generator and measures their Mahalanobis distance to the evidence representation. The resulting quadratic rule requires no auxiliary judge model, runs at generation time, and is simple enough to calibrate on a small held-out set. We show that residual-stream geometry carries a usable faithfulness signal, that this signal survives architecture changes and realistic retrieval failures, and that the same rule remains amenable to public verification. On PubMedQA with Llama-3-8B, LatentAudit reaches 0.942 AUROC with 0.77,ms overhead. Across three QA benchmarks and five model families (Llama-2/3, Qwen-2.5/3, Mistral), the monitor remains stable; under a four-way stress test with contradictions, retrieval misses, and partial-support noise, it reaches 0.9566--0.9815 AUROC on PubMedQA and 0.9142--0.9315 on HotpotQA. At 16-bit fixed-point precision, the audit rule preserves 99.8% of the FP16 AUROC, enabling Groth16-based public verification without revealing model weights or activations. Together, these results position residual-stream geometry as a practical basis for real-time RAG faithfulness monitoring and optional verifiable deployment.

---

### ETR: Entropy Trend Reward for Efficient Chain-of-Thought Reasoning

Authors: Xuan Xiong, Huan Liu, Li Gu, Zhixiang Chi, Yue Qiu, Yuanhao Yu, Yang Wang
Published: 2026-04-07
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2604.05355v1

Chain-of-thought (CoT) reasoning improves large language model performance on complex tasks, but often produces excessively long and inefficient reasoning traces. Existing methods shorten CoTs using length penalties or global entropy reduction, implicitly assuming that low uncertainty is desirable throughout reasoning. We show instead that reasoning efficiency is governed by the trajectory of uncertainty. CoTs with dominant downward entropy trends are substantially shorter. Motivated by this insight, we propose Entropy Trend Reward (ETR), a trajectory-aware objective that encourages progressive uncertainty reduction while allowing limited local exploration. We integrate ETR into Group Relative Policy Optimization (GRPO) and evaluate it across multiple reasoning models and challenging benchmarks. ETR consistently achieves a superior accuracy-efficiency tradeoff, improving DeepSeek-R1-Distill-7B by 9.9% in accuracy while reducing CoT length by 67% across four benchmarks. Code is available at https://github.com/Xuan1030/ETR

---

### Unsupervised Multi-agent and Single-agent Perception from Cooperative Views

Authors: Haochen Yang, Baolu Li, Lei Li, Delin Ren, Jiacheng Guo, Minghai Qin, Tianyun Zhang, Hongkai Yu
Published: 2026-04-07
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.05354v1

The LiDAR-based multi-agent and single-agent perception has shown promising performance in environmental understanding for robots and automated vehicles. However, there is no existing method that simultaneously solves both multi-agent and single-agent perception in an unsupervised way. By sharing sensor data between multiple agents via communication, this paper discovers two key insights: 1) Improved point cloud density after the data sharing from cooperative views could benefit unsupervised object classification, 2) Cooperative view of multiple agents can be used as unsupervised guidance for the 3D object detection in the single view. Based on these two discovered insights, we propose an Unsupervised Multi-agent and Single-agent (UMS) perception framework that leverages multi-agent cooperation without human annotations to simultaneously solve multi-agent and single-agent perception. UMS combines a learning-based Proposal Purifying Filter to better classify the candidate proposals after multi-agent point cloud density cooperation, followed by a Progressive Proposal Stabilizing module to yield reliable pseudo labels by the easy-to-hard curriculum learning. Furthermore, we design a Cross-View Consensus Learning to use multi-agent cooperative view to guide detection in single-agent view. Experimental results on two public datasets V2V4Real and OPV2V show that our UMS method achieved significantly higher 3D detection performance than the state-of-the-art methods on both multi-agent and single-agent perception tasks in an unsupervised setting.

---

### AnyImageNav: Any-View Geometry for Precise Last-Meter Image-Goal Navigation

Authors: Yijie Deng, Shuaihang Yuan, Yi Fang
Published: 2026-04-07
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2604.05351v3

Image Goal Navigation (ImageNav) is evaluated by a coarse success criterion, the agent must stop within 1m of the target, which is sufficient for finding objects but falls short for downstream tasks such as grasping that require precise positioning. We introduce AnyImageNav, a training-free system that pushes ImageNav toward this more demanding setting. Our key insight is that the goal image can be treated as a geometric query: any photo of an object, a hallway, or a room corner can be registered to the agent's observations via dense pixel-level correspondences, enabling recovery of the exact 6-DoF camera pose. Our method realizes this through a semantic-to-geometric cascade: a semantic relevance signal guides exploration and acts as a proximity gate, invoking a 3D multi-view foundation model only when the current view is highly relevant to the goal image; the model then self-certifies its registration in a loop for an accurate recovered pose. Our method sets state-of-the-art navigation success rates on Gibson (93.1%) and HM3D (82.6%), and achieves pose recovery that prior methods do not provide: a position error of 0.27m and heading error of 3.41 degrees on Gibson, and 0.21m / 1.23 degrees on HM3D, a 5-10x improvement over adapted baselines.Our project page: https://yijie21.github.io/ain/

---

### DQA: Diagnostic Question Answering for IT Support

Authors: Vishaal Kapoor, Mariam Dundua, Sarthak Ahuja, Neda Kordjazi, Evren Yortucboylu, Vaibhavi Padala, Derek Ho, Jennifer Whitted, Rebecca Steinert
Published: 2026-04-07
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2604.05350v2

Enterprise IT support interactions are fundamentally diagnostic: effective resolution requires iterative evidence gathering from ambiguous user reports to identify an underlying root cause. While retrieval-augmented generation (RAG) provides grounding through historical cases, standard multi-turn RAG systems lack explicit diagnostic state and therefore struggle to accumulate evidence and resolve competing hypotheses across turns. We introduce DQA, a diagnostic question-answering framework that maintains persistent diagnostic state and aggregates retrieved cases at the level of root causes rather than individual documents. DQA combines conversational query rewriting, retrieval aggregation, and state-conditioned response generation to support systematic troubleshooting under enterprise latency and context constraints. We evaluate DQA on 150 anonymized enterprise IT support scenarios using a replay-based protocol. Averaged over three independent runs, DQA achieves a 78.7% success rate under a trajectory-level success criterion, compared to 41.3% for a multi-turn RAG baseline, while reducing average turns from 8.4 to 3.9.

---

### From Retinal Evidence to Safe Decisions: RETINA-SAFE and ECRT for Hallucination Risk Triage in Medical LLMs

Authors: Zhe Yu, Wenpeng Xing, Meng Han
Published: 2026-04-07
Categories: cs.AI
arXiv: https://arxiv.org/abs/2604.05348v1

Hallucinations in medical large language models (LLMs) remain a safety-critical issue, particularly when available evidence is insufficient or conflicting. We study this problem in diabetic retinopathy (DR) decision settings and introduce RETINA-SAFE, an evidence-grounded benchmark aligned with retinal grading records, comprising 12,522 samples. RETINA-SAFE is organized into three evidence-relation tasks: E-Align (evidence-consistent), E-Conflict (evidence-conflicting), and E-Gap (evidence-insufficient). We further propose ECRT (Evidence-Conditioned Risk Triage), a two-stage white-box detection framework: Stage 1 performs Safe/Unsafe risk triage, and Stage 2 refines unsafe cases into contradiction-driven versus evidence-gap risks. ECRT leverages internal representation and logit shifts under CTX/NOCTX conditions, with class-balanced training for robust learning. Under evidence-grouped (not patient-disjoint) splits across multiple backbones, ECRT provides strong Stage-1 risk triage and explicit subtype attribution, improves Stage-1 balanced accuracy by +0.15 to +0.19 over external uncertainty and self-consistency baselines and by +0.02 to +0.07 over the strongest adapted supervised baseline, and consistently exceeds a single-stage white-box ablation on Stage-1 balanced accuracy. These findings support white-box internal signals grounded in retinal evidence as a practical route to interpretable medical LLM risk triage.

---

### CI-ICM: Channel Importance-driven Learned Image Coding for Machines

Authors: Yun Zhang, Junle Liu, Huan Zhang, Zhaoqing Pan, Gangyi Jiang, Weisi Lin
Published: 2026-04-07
Categories: eess.IV, cs.CV, cs.MM
arXiv: https://arxiv.org/abs/2604.05347v1

Traditional human vision-centric image compression methods are suboptimal for machine vision centric compression due to different visual properties and feature characteristics. To address this problem, we propose a Channel Importance-driven learned Image Coding for Machines (CI-ICM), aiming to maximize the performance of machine vision tasks at a given bitrate constraint. First, we propose a Channel Importance Generation (CIG) module to quantify channel importance in machine vision and develop a channel order loss to rank channels in descending order. Second, to properly allocate bitrate among feature channels, we propose a Feature Channel Grouping and Scaling (FCGS) module that non-uniformly groups the feature channels based on their importance and adjusts the dynamic range of each group. Based on FCGS, we further propose a Channel Importance-based Context (CI-CTX) module to allocate bits among feature groups and to preserve higher fidelity in critical channels. Third, to adapt to multiple machine tasks, we propose a Task-Specific Channel Adaptation (TSCA) module to adaptively enhance features for multiple downstream machine tasks. Experimental results on the COCO2017 dataset show that the proposed CI-ICM achieves BD-mAP@50:95 gains of 16.25$\%$ in object detection and 13.72$\%$ in instance segmentation over the established baseline codec. Ablation studies validate the effectiveness of each contribution, and computation complexity analysis reveals the practicability of the CI-ICM. This work establishes feature channel optimization for machine vision-centric compression, bridging the gap between image coding and machine perception.

---

### Dynamic Agentic AI Expert Profiler System Architecture for Multidomain Intelligence Modeling

Authors: Aisvarya Adeseye, Jouni Isoaho, Seppo Virtanen, Mohammad Tahir
Published: 2026-04-07
Categories: cs.AI
arXiv: https://arxiv.org/abs/2604.05345v1

In today's artificial intelligence driven world, modern systems communicate with people from diverse backgrounds and skill levels. For human-machine interaction to be meaningful, systems must be aware of context and user expertise. This study proposes an agentic AI profiler that classifies natural language responses into four levels: Novice, Basic, Advanced, and Expert. The system uses a modular layered architecture built on LLaMA v3.1 (8B), with components for text preprocessing, scoring, aggregation, and classification. Evaluation was conducted in two phases: a static phase using pre-recorded transcripts from 82 participants, and a dynamic phase with 402 live interviews conducted by an agentic AI interviewer. In both phases, participant self-ratings were compared with profiler predictions. In the dynamic phase, expertise was assessed after each response rather than at the end of the interview. Across domains, 83% to 97% of profiler evaluations matched participant self-assessments. Remaining differences were due to self-rating bias, unclear responses, and occasional misinterpretation of nuanced expertise by the language model.

---

### Anchored Cyclic Generation: A Novel Paradigm for Long-Sequence Symbolic Music Generation

Authors: Boyu Cao, Lekai Qian, Dehan Li, Haoyu Gu, Mingda Xu, Qi Liu
Published: 2026-04-07
Categories: cs.SD, cs.AI
arXiv: https://arxiv.org/abs/2604.05343v1

Generating long sequences with structural coherence remains a fundamental challenge for autoregressive models across sequential generation tasks. In symbolic music generation, this challenge is particularly pronounced, as existing methods are constrained by the inherent severe error accumulation problem of autoregressive models, leading to poor performance in music quality and structural integrity. In this paper, we propose the Anchored Cyclic Generation (ACG) paradigm, which relies on anchor features from already identified music to guide subsequent generation during the autoregressive process, effectively mitigating error accumulation in autoregressive methods. Based on the ACG paradigm, we further propose the Hierarchical Anchored Cyclic Generation (Hi-ACG) framework, which employs a systematic global-to-local generation strategy and is highly compatible with our specifically designed piano token, an efficient musical representation. The experimental results demonstrate that compared to traditional autoregressive models, the ACG paradigm achieves reduces cosine distance by an average of 34.7% between predicted feature vectors and ground-truth semantic vectors. In long-sequence symbolic music generation tasks, the Hi-ACG framework significantly outperforms existing mainstream methods in both subjective and objective evaluations. Furthermore, the framework exhibits excellent task generalization capabilities, achieving superior performance in related tasks such as music completion.

---

### Human Values Matter: Investigating How Misalignment Shapes Collective Behaviors in LLM Agent Communities

Authors: Xiangxu Zhang, Jiamin Wang, Qinlin Zhao, Hanze Guo, Linzhuo Li, Jing Yao, Xiao Zhou, Xiaoyuan Yi, Xing Xie
Published: 2026-04-07
Categories: cs.CL
arXiv: https://arxiv.org/abs/2604.05339v1

As LLMs become increasingly integrated into human society, evaluating their orientations on human values from social science has drawn growing attention. Nevertheless, it is still unclear why human values matter for LLMs, especially in LLM-based multi-agent systems, where group-level failures may accumulate from individually misaligned actions. We ask whether misalignment with human values alters the collective behavior of LLM agents and what changes it induces? In this work, we introduce CIVA, a controlled multi-agent environment grounded in social science theories, where LLM agents form a community and autonomously communicate, explore, and compete for resources, enabling systematic manipulation of value prevalence and behavioral analysis. Through comprehensive simulation experiments, we reveal three key findings. (1) We identify several structurally critical values that substantially shape the community's collective dynamics, including those diverging from LLMs' original orientations. Triggered by the misspecification of these values, we (2) detect system failure modes, e.g., catastrophic collapse, at the macro level, and (3) observe emergent behaviors like deception and power-seeking at the micro level. These results offer quantitative evidence that human values are essential for collective outcomes in LLMs and motivate future multi-agent value alignment.

---

### Individual-heterogeneous sub-Gaussian Mixture Models

Authors: Huan Qing
Published: 2026-04-07
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2604.05337v1

The classical Gaussian mixture model assumes homogeneity within clusters, an assumption that often fails in real-world data where observations naturally exhibit varying scales or intensities. To address this, we introduce the individual-heterogeneous sub-Gaussian mixture model, a flexible framework that assigns each observation its own heterogeneity parameter, thereby explicitly capturing the heterogeneity inherent in practical applications. Built upon this model, we propose an efficient spectral method that provably achieves exact recovery of the true cluster labels under mild separation conditions, even in high-dimensional settings where the number of features far exceeds the number of samples. Numerical experiments on both synthetic and real data demonstrate that our method consistently outperforms existing clustering algorithms, including those designed for classical Gaussian mixture models.

---

### TRACE: Capability-Targeted Agentic Training

Authors: Hangoo Kang, Tarun Suresh, Jon Saad-Falcon, Azalia Mirhoseini
Published: 2026-04-07
Categories: cs.AI
arXiv: https://arxiv.org/abs/2604.05336v2

Models often fail to complete agentic tasks because they lack core capabilities required by the target environment. However, mainstream approaches for addressing these failures typically either fine-tune directly on target environments or generate synthetic data that is not targeted to the model's actual capability deficits, resulting in low sample efficiency and limited generalization. We introduce TRACE (Turning Recurrent Agent failures into Capability-targeted training Environments), an end-to-end system for environment-specific agent self-improvement. TRACE contrasts successful and failed trajectories to automatically identify missing capabilities, synthesizes a targeted training environment for each capability that rewards whether the capability is exercised, trains a LoRA adapter via reinforcement learning on each synthetic environment, and then trains a mixture-of-experts model over the capability adapters. TRACE can be effectively applied across different environments, improving over the base agent by +15.3 points on $τ^2$-Bench, a customer-service agent benchmark, and by +15.0 points Pass@1 on SWE-Bench Verified, a software-engineering benchmark. TRACE outperforms the strongest external baselines, GEPA and SWE-RL, by +8.6 points and +8.4 points, respectively. In addition, TRACE is more sample-efficient than strong fine-tuning baselines: using fewer than one-fourth the number of rollouts, TRACE outperforms the best-performing baselines, GRPO and GEPA, and achieves higher final accuracy by +10.4 and +8.6 points on $τ^2$-Bench.

---

### Cross-Machine Anomaly Detection Leveraging Pre-trained Time-series Model

Authors: Yangmeng Li, Kei Sano, Toshihiro Kitao, Ryoji Anzaki, Yukiya Saitoh, Hironori Moki, Dragan Djurdjanovic
Published: 2026-04-07
Categories: cs.LG, eess.SP
arXiv: https://arxiv.org/abs/2604.05335v1

Achieving resilient and high-quality manufacturing requires reliable data-driven anomaly detection methods that are capable of addressing differences in behaviors among different individual machines which are nominally the same and are executing the same processes. To address the problem of detecting anomalies in a machine using sensory data gathered from different individual machines executing the same procedure, this paper proposes a cross-machine time-series anomaly detection framework that integrates a domain-invariant feature extractor with an unsupervised anomaly detection module. Leveraging the pre-trained foundation model MOMENT, the extractor employs Random Forest Classifiers to disentangle embeddings into machine-related and condition-related features, with the latter serving as representations which are invariant to differences between individual machines. These refined features enable the downstream anomaly detectors to generalize effectively to unseen target machines. Experiments on an industrial dataset collected from three different machines performing nominally the same operation demonstrate that the proposed approach outperforms both the raw-signal-based and MOMENT-embedding feature baselines, confirming its effectiveness in enhancing cross-machine generalization.

---

### Graph-of-Skills: Dependency-Aware Structural Retrieval for Massive Agent Skills

Authors: Dawei Liu, Zongxia Li, Hongyang Du, Xiyang Wu, Shihang Gui, Yongbei Kuang, Lichao Sun
Published: 2026-04-07
Categories: cs.AI
arXiv: https://arxiv.org/abs/2604.05333v4

As LLM agents act across personal applications, web browsers, and other interfaces, their reusable skill libraries can scale to thousands of skills. This scale introduces two challenges. First, loading the full library saturates the context window, driving up token costs, hallucination, and latency. Second, semantic retrieval surfaces topically relevant skills but can miss upstream and downstream prerequisite skills, creating a prerequisite gap that leaves the retrieved bundle insufficient for execution. We present Graph-of-Skills (GoS), an inference-time structural retrieval layer for large skill libraries. GoS constructs an executable skill graph offline from skill packages, then retrieves a bounded, dependency-aware bundle through hybrid semantic-lexical seeding, reverse-aware Personalized PageRank, and context-budgeted hydration. Across SkillsBench and ALFWorld, with three model families (Claude Sonnet 4.5, MiniMax M2.7, and GPT-5.2 Codex), GoS attains the highest average reward in all six model-benchmark blocks, at a fraction of the token cost of loading the full library. On SkillsBench with GPT-5.2 Codex it raises average reward by 7.0 absolute points over full skill loading, a 25.6% relative gain, while cutting total tokens by 56.7%. Ablations isolate the mechanism: replacing reverse traversal with forward propagation costs 9.1 reward points, a larger loss than removing the graph altogether. The gain thus comes from traversing dependencies backwards, not from graph diffusion as such. A budget-matched retrieval study holding seeding, reranking, hydration, and context budget fixed reproduces the same ordering, with dependency-pair co-recovery falling from 0.654 to 0.362. Code is available at https://github.com/davidliuk/graph-of-skills

---

### Graph-of-Skills: Dependency-Aware Structural Retrieval for Massive Agent Skills

Authors: Dawei Liu, Zongxia Li, Hongyang Du, Xiyang Wu, Shihang Gui, Yongbei Kuang, Lichao Sun
Published: 2026-04-07
Categories: cs.AI
arXiv: https://arxiv.org/abs/2604.05333v3

Modern LLM agents increasingly rely on reusable skills, and as they interact with personal applications, web browsers, and other interfaces, skill libraries can scale to thousands of skills. Scaling to larger skill sets introduces two key challenges. First, loading the full skill set saturates the context window, driving up token costs, hallucination, and latency. Second, semantic retrieval surfaces topically relevant skills but misses their prerequisite chain of upstream and downstream skills, creating a prerequisite gap that leaves the retrieved bundle execution-incomplete. In this paper, we present Graph-of-Skills (GoS), an inference-time structural retrieval layer for large skill libraries. GoS constructs an executable skill graph offline from skill packages, then at inference time retrieves a bounded, dependency-aware skill bundle through hybrid semantic-lexical seeding, reverse-aware Personalized PageRank, and context-budgeted hydration. On SkillsBench and ALFWorld, GoS consistently delivers substantial reward improvements and token savings across three model families (Claude Sonnet 4.5, MiniMax M2.7, and GPT-5.2 Codex). On SkillsBench, GoS achieves a peak reward increase of 25.55% while reducing total tokens by 56.72% over the vanilla full skill-loading baseline using GPT-5.2 Codex. Ablations confirm this pattern across skill libraries from 200 to 2,000 skills.

---

### A Theoretical Framework for Statistical Evaluability of Generative Models

Authors: Shashaank Aiyer, Yishay Mansour, Shay Moran, Han Shao
Published: 2026-04-07
Categories: cs.LG, cs.IT
arXiv: https://arxiv.org/abs/2604.05324v3

Statistical evaluation aims to estimate the generalization performance of a model using held-out i.i.d. test data sampled from the ground-truth distribution. In supervised learning settings such as classification, performance metrics such as error rate are well-defined, and test error reliably approximates population error given sufficiently large datasets. In contrast, evaluation is more challenging for generative models due to their open-ended nature: it is unclear which metrics are appropriate and whether such metrics can be reliably evaluated from finite samples. In this work, we introduce a theoretical framework for evaluating generative models and establish evaluability results for commonly used metrics. We study two categories of metrics: test-based metrics, including integral probability metrics (IPMs), and Rényi divergences. We show that IPMs with respect to any bounded test class can be evaluated from finite samples up to multiplicative and additive approximation errors. Moreover, when the test class has finite fat-shattering dimension, IPMs can be evaluated with arbitrary precision. In contrast, Rényi and KL divergences are not evaluable from finite samples, as their values can be critically determined by rare events. We also analyze the potential and limitations of perplexity as an evaluation method.

---

### A Theoretical Framework for Statistical Evaluability of Generative Models

Authors: Shashaank Aiyer, Yishay Mansour, Shay Moran, Han Shao
Published: 2026-04-07
Categories: cs.LG, cs.IT
arXiv: https://arxiv.org/abs/2604.05324v2

Statistical evaluation aims to estimate the generalization performance of a model using held-out i.i.d. test data sampled from the ground-truth distribution. In supervised learning settings such as classification, performance metrics such as error rate are well-defined, and test error reliably approximates population error given sufficiently large datasets. In contrast, evaluation is more challenging for generative models due to their open-ended nature: it is unclear which metrics are appropriate and whether such metrics can be reliably evaluated from finite samples. In this work, we introduce a theoretical framework for evaluating generative models and establish evaluability results for commonly used metrics. We study two categories of metrics: test-based metrics, including integral probability metrics (IPMs), and Rényi divergences. We show that IPMs with respect to any bounded test class can be evaluated from finite samples up to multiplicative and additive approximation errors. Moreover, when the test class has finite fat-shattering dimension, IPMs can be evaluated with arbitrary precision. In contrast, Rényi and KL divergences are not evaluable from finite samples, as their values can be critically determined by rare events. We also analyze the potential and limitations of perplexity as an evaluation method.

---

### VLA-InfoEntropy: A Training-Free Vision-Attention Information Entropy Approach for Vision-Language-Action Models Inference Acceleration and Success

Authors: Chuhang Liu, Yayun He, Zuheng Kang, Xiaoyang Qu, Jianzong Wang
Published: 2026-04-07
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2604.05323v1

Vision-Language-Action (VLA) models integrate visual perception, language understanding, and action decision-making for cross-modal semantic alignment, exhibiting broad application potential. However, the joint processing of high-dimensional visual features, complex linguistic inputs, and continuous action sequences incurs significant computational overhead and low inference efficiency, thereby hindering real-time deployment and reliability. To address this issue, we use image entropy to quantify the grayscale distribution characteristics of each visual token and introduce attention entropy to capture the distribution of attention scores over task-related text. Visual entropy identifies texture-rich or structurally informative regions, while attention entropy pinpoints semantically relevant tokens. Combined with timestep information, these metrics enable a dynamic transition strategy that shifts the model's focus from global visual features to attention-guided local informative regions. Thus, the resulting VLA-InfoEntropy method integrates spatial, semantic, and temporal cues to reduce redundancy while preserving critical content. Extensive experiments show that our method reduces inference parameters, accelerates inference speed, and outperforms existing approaches.

---

### DIA-HARM: Dialectal Disparities in Harmful Content Detection Across 50 English Dialects

Authors: Jason Lucas, Matt Murtagh, Ali Al-Lawati, Uchendu Uchendu, Adaku Uchendu, Dongwon Lee
Published: 2026-04-07
Categories: cs.CL
arXiv: https://arxiv.org/abs/2604.05318v2

Harmful content detectors, particularly disinformation classifiers, are predominantly developed and evaluated on Standard American English (SAE), leaving their robustness to dialectal variation unexplored. We present DIA-HARM, the first benchmark for evaluating disinformation detection robustness across 50 English dialects spanning U.S., British, African, Caribbean, and Asia-Pacific varieties. Using Multi-VALUE's linguistically grounded transformations, we introduce D-CUBE (Dialectal Disinformation Detection Corpus), a core corpus component of DIA-HARM comprising 195K samples derived from established disinformation benchmarks. Our evaluation of 16 detection models reveals systematic vulnerabilities: human-written dialectal content degrades detection by 1.4-3.6% F1, while AI-generated content remains stable. Fine-tuned transformers substantially outperform zero-shot LLMs (96.6% vs. 78.3% best-case F1), with some models exhibiting catastrophic failures exceeding 33% degradation on mixed content. Cross-dialectal transfer analysis across 2,450 dialect pairs shows that multilingual models (mDeBERTa: 97.2% average F1) generalize effectively, while monolingual models like RoBERTa and XLM-RoBERTa fail on dialectal inputs. These findings demonstrate that current disinformation detectors may systematically disadvantage hundreds of millions of non-SAE speakers worldwide. We release the DIA-HARM benchmark, including the D-CUBE corpus (https://github.com/jsl5710/dia-harm), and evaluation tools (https://jsl5710.github.io/dia-harm).

---

### Indoor Asset Detection in Large Scale 360° Drone-Captured Imagery via 3D Gaussian Splatting

Authors: Monica Tang, Avideh Zakhor
Published: 2026-04-07
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.05316v1

We present an approach for object-level detection and segmentation of target indoor assets in 3D Gaussian Splatting (3DGS) scenes, reconstructed from 360° drone-captured imagery. We introduce a 3D object codebook that jointly leverages mask semantics and spatial information of their corresponding Gaussian primitives to guide multi-view mask association and indoor asset detection. By integrating 2D object detection and segmentation models with semantically and spatially constrained merging procedures, our method aggregates masks from multiple views into coherent 3D object instances. Experiments on two large indoor scenes demonstrate reliable multi-view mask consistency, improving F1 score by 65% over state-of-the-art baselines, and accurate object-level 3D indoor asset detection, achieving an 11% mAP gain over baseline methods.

---