# Research Papers — 2026-09 · bundle page 180 of 266 > Full-text markdown of papers #8951–9000 of 13298 published in 2026-09, newest first. AI-readable mirrors of the full 13298-paper 2026-09 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-09/page/180 [← Previous bundle](https://aipod.dev/papers/archive/2026-09/page/179.md) [Next bundle →](https://aipod.dev/papers/archive/2026-09/page/181.md) ### Homeostatic Continual Learning Authors: Yue Jin Published: 2026-09-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.13771v1 In this paper, I formulate a Continual Learning problem and propose a method named "Homeostatic Continual Learning" that enables an AI agent to learn continuously in a changing environment without catastrophic forgetting. The core of the method is to find outliers in the environment data when the agent experiences an outlier in its output. Through this method, the agent gradually completes its model and policy and performs well in more and more contexts. I also suggest that we may use the method to build a world model where the agent factorizes the objects in the world into features, abstract objects into comparable instances of concepts and map concepts to intents through features. I discuss the works needed to render the method practical, the connections to many fields in Artificial Intelligence and the broader implications of the method. --- ### Training Specialist Models without Reasoning Trajectories for Domain Expert Distillation Authors: Yilei Tu, Zihao Li, Shaoxiong Ji, Jörg Tiedemann, Fei Yuan Published: 2026-09-12 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2609.13770v1 Specialist distillation effectively transfers domain expertise to student models via teacher-generated reasoning trajectories. However, when these specialists are trained solely on question--answer pairs without explicit reasoning supervision, what governs the trajectories they generate? In this work, we show that specialist optimization implicitly selects from this latent trajectory space. To isolate and observe this latent distribution, we leverage student distillation not as a downstream goal, but as an agnostic probe---since students inherit no parameterization or optimization constraints from the specialist, inheriting only the sampled trajectories themselves. Through this probe, our empirical analysis unveils a tight governing relationship: across 27 specialist--student pairings, their specialization--generalization profiles correlate exceptionally strongly. Crucially, explicitly controlling the specialist's distributional drift systematically shifts both the teacher and its distilled student along a controllable trade-off between domain precision and general-capability retention. Across chemistry, physics, and multilingual settings, distilled students systematically reflect these specialist-induced profiles, even across divergent model families. Our findings establish a new view of specialist training: when gold reasoning is absent, tuning choices directly control the latent supervision passed to downstream models. --- ### HyperProve: Answer-Guided Hypergraph Expansion for Multi-Hop Question Answering Authors: An Nguyen Phu, Dung Nguyen Quang, Luu Hieu An, Linh Ngo Van, Trung Le, Thien Huu Nguyen Published: 2026-09-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.13768v1 Multi-hop question answering often fails when retrieval treats evidence as isolated matches to the original question, since the facts needed to answer a complex question are usually connected through intermediate entities, relations, and constraints. We propose HyperProve, a retrieval-augmented QA framework that addresses this challenge by coupling question decomposition with answer-conditioned expansion over a hypergraph of atomic facts. HyperProve does not use atomic facts, hypergraphs, or iterative retrieval in isolation; instead, it carries intermediate answers and supporting hyperedges as retrieval state, then uses that state to bias the next local hypergraph expansion. This design enables HyperProve to construct coherent evidence chains for final answer generation while making the retrieval process stateful and fact-centered. Across multi-hop QA benchmarks, HyperProve achieves the best overall performance in our evaluation, outperforming the strongest baselines by an average relative improvement of 6.2% in answer accuracy and 4.9% in F1. --- ### Positioning manuscripts in the scientific landscape with agentic AI Authors: Jiawen Chen, Zichen Zhang, Bingxuan Li, Quan Sun, Yiyan Zhang, Edric Tam, Jinjie Lin, Didong Li, Yun Li, Bingxin Zhao Published: 2026-09-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.13760v1 Publishing a research manuscript is a routine yet demanding part of scientific life: time-consuming, stressful, and often uncertain in outcome. Recent advances in large language model (LLM)-based agentic AI have shown promise across a range of scientific tasks, and here we ask whether agentic AI can help researchers navigate the publication process itself by reliably inferring a manuscript's eventual publication venue from its content and literature context. We introduce PASS (Publication-oriented Agentic Scientific System), an agentic system that understands manuscripts within their domain-specific literature context and predicts top-matched publication venues. PASS positions each manuscript within its surrounding literature landscape by reconstructing its local scientific neighborhood, tracing its topic trajectory, and reasoning over field-specific journal spaces. Evaluated on a leakage-audited benchmark of over 2,000 preprints across 16 biomedical fields, PASS achieved Top-1 accuracy of 50.3% and Top-5 accuracy of 86.1%, outperforming state-of-the-art LLM baselines and established journal-selection tools. PASS-produced quality scores, such as impact potential and novelty, aligned with independent measures of publication outcome. We also found that the designed literature retrieval module is the strongest performance contributor, particularly for positioning manuscripts relative to nearby work, and that PASS maintained near-full performance from the abstract alone, whereas LLM baselines required the full manuscript text. An independent human evaluation found strong researcher agreement with PASS's manuscript understanding and recommendation rationale. PASS has been released as a public platform (https://ratemypaper.ai/) for broad researcher access. --- ### On the Equivalence of Stochastic Control and Path Space Formulations for Schrödinger Bridges over Compact Connected Lie Groups Authors: Hamza Mahmood, Georgiy A. Bondar, Abhishek Halder, Adeel Akhtar Published: 2026-09-12 Categories: math.OC, cs.AI, eess.SY, math.PR, stat.ML arXiv: https://arxiv.org/abs/2609.13758v1 We establish the equivalence between the stochastic optimal control and path space formulations of the Schrödinger bridge problem (SBP) for the kinematic equation on a compact connected Lie group. Using the geometric concepts of horizontal lift and stochastic anti-development, we derive a Girsanov-type change-of-measure result, and show that the expected control energy equals the relative entropy of the controlled path law with respect to the reference Wiener measure. Thus, the SBP is equivalently a path space relative entropy minimization problem subject to prescribed endpoint marginals.Our result has three useful implications. From an analytic viewpoint, the shown equivalence helps prove the existence and uniqueness of the SB. From a probabilistic viewpoint, it helps interpret the SB as the most probable deviation of the uncontrolled stochastic dynamics consistent with the endpoint constraints. From a computational viewpoint, it allows using static Sinkhorn recursions to directly solve the relative entropy minimization problem and compute the optimal path measure. We illustrate the equivalence numerically on the torus $\mathbb{T}^2$. The code is publicly available at: https://github.com/gradslab/LargeDeviationSBP --- ### Development of Low-Cost Real-Time Driver Drowsiness Detection System using Eye Centre Tracking and Dynamic Thresholding Authors: Fuzail Khan, Sandeep Sharma, M. R. Arulalan Published: 2026-09-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.13756v1 One in every five vehicle accidents on the road today is caused simply due to driver fatigue. Fatigue or otherwise drowsiness, significantly reduces the concentration and vigilance of the driver thereby increasing the risk of inherent human error leading to injuries and fatalities. Hence, our primary motive being - to reduce road accidents using a non-intrusive image processing based alert system. In this regard, we have built a system that detects driver drowsiness by real time tracking and monitoring the pattern of the driver's eyes. The stand alone system consists of 3 interconnected components - a processor, a camera and an alarm. After initial facial detection, the eyes are located, extracted and continuously monitored to check whether they are open or closed on the basis of a pixel-by-pixel method. When the eyes are seen to be closed for a certain amount of time, drowsiness is said to be detected and an alarm is issued accordingly to alert the driver and hence, prevent a casualty. --- ### How Should Reasoning Be Organized in a Transformer's Latent Space? Authors: Hongyu Gu, Chang Liu, Jingwen Fu Published: 2026-09-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.13747v2 Continuous reasoning has emerged as a promising way to improve reasoning in large language models (LLMs). Yet we still lack a clear principle for deciding what a latent state should preserve. Reasoning by superposition shows that a single latent state can encode several search alternatives and expand them in parallel. We ask how those states should be weighted as reasoning proceeds. A natural choice is to preserve only the states active at the frontier step, since keeping every reached state appears to spread a limited hidden width too thin. We show that the opposite can hold. When later computation draws on several reached states, a cumulative state can guide attention correctly at a smaller hidden width than a frontier state that stores fewer states. At the same width, the cumulative state therefore keeps more intermediate states available for later reasoning. More generally, equal cumulative weights are optimal when future queries are unknown and remain close to the best task-specific weights when those queries are known. Experiments with two-layer and GPT-2 Transformers reproduce the predicted width advantage and show that unequal weights fail first on the states that receive the least weight. This suggests a important principle: keep reached states equally weighted, and restore equal weights as computation proceeds. --- ### Inside VLM Chart Reading: Tracing Value Reading from Vertical Bar Charts Across Space and Depth Authors: Tianhao Niu, Qingfu Zhu, Wanxiang Che Published: 2026-09-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.13745v1 Vision--language models (VLMs) can answer chart questions accurately, but output accuracy does not show how they combine the evidence needed to recover an exact value. We study vertical-bar value reading with controlled counterfactual activation patching in Qwen2.5VL-7B-Instruct and InternVL3.5-8B. The study connects three analyses: (1) The single-factor results show that the changed bar-top region restores much more answer preference than the unchanged bar body, despite containing fewer visual tokens. Legend- and series-related states also lose local recoverability earlier than bar-geometry and axis-scale states. (2) In the handoff analysis, restoration shifts from visual legend regions in early layers to prompt-series positions in middle layers. Resetting the prompt-series state selectively reduces legend-source rescue, supporting its role as a partial mediator. (3) In the factorial analysis, both models can use geometry and scale states from separate donors to favor the combined target. InternVL performs similarly when the states come from separate donors or one image, while Qwen shows lower restoration for separate donors which suggests higher context sensitivity. Together, these results provide preliminary causal evidence for localizing the internal computations that support exact bar-value reading. --- ### Hyper-LLaVA: Hyperbolic Uncertainty-aware Modality-Balanced Routing for Multimodal Continual Instruction Tuning Authors: Kunlun Xu, Yanqin Zhang, Wenwen Qiang, Jiahuan Zhou Published: 2026-09-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.13742v1 Multimodal Continual Instruction Tuning (MCIT) aims to exploit the incrementally accumulated knowledge to process multimodal inputs of diverse tasks, where parameter routing plays an important role. State-of-the-art methods rely on sample-to-task center similarity and cross-modal fusion with equal weight during routing. However, such solutions face two fundamental flaws: (1) Within each modality, the sample-to-task center distance is sub-optimal for routing since the abundant intra-task diversity information is underleveraged. (2) Different modalities exhibit varying reliability across tasks, where the modality with inter-task ambiguity can easily misguide the routing result. To address these problems, we propose Hyperbolic Uncertainty-aware Modality-Balanced Routing (Hyper-LLaVA) to improve parameter routing capacity based on cross-modality task feature uncertainty modeling. Specifically, to improve intra-modality task matching, Hyper-LLaVA accesses the sample-to-task distribution similarity in the Hyperbolic space. Besides, to alleviate the degradation brought by unreliable modalities, Hyper-LLaVA quantifies the task matching ambiguity within each modality to achieve adaptive balancing between task matching across modalities. Based on the complementary intra- and inter-modality task matching enhancement, our Hyper-LLaVA outperforms state-of-the-art approaches by large margins. Our source code is available at https://github.com/zhoujiahuan1991/ICML2026-Hyper-LLaVA --- ### HarnessBandit: Joint Learnability-Transferability Scheduling for Multi-Harness Agentic Reinforcement Learning Authors: Hongliang Wei, Xiaobing Tu, Yinggui Wang, Zhengxi Liu, Rongkun Xue, Jinkui Ren, Xiantao Zhang, Debin Zhao, Xiaopeng Fan Published: 2026-09-12 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2609.13739v1 Language-model agents are increasingly deployed through diverse harnesses that differ in system prompts, tool schemas, control loops, and trajectory formats. The same model can perform unevenly across these interfaces, making robustness to harness variation an important objective. A natural approach is to train a shared policy through multiple harnesses, but doing so introduces a scheduling problem: each training step should favor a harness that currently provides a useful learning signal while also producing an update that benefits the other harnesses. We develop HarnessBandit, an online scheduler that selects one harness per optimizer step. After a group-relative policy optimization (GRPO) update, it observes learnability -- the mean absolute advantage on the batch -- and transferability -- the cosine between a low-dimensional gradient sketch of the current harness and exponential moving averages of the remaining harnesses. The two signals are fused after pooled sliding-window min-max normalization and sampled with a visit-dependent bonus and an explicit exploration floor. We train Qwen3.5-2B across six harnesses on ClawGym and evaluate on PinchBench (held-out tasks, in-distribution OpenClaw) and ClawEval (held-out tasks and harness). HarnessBandit improves over mixed-batch multi-harness training on both benchmarks, while training diagnostics indicate that learnability and transferability provide distinct, evolving signals. --- ### ForeSight: Enhancing Risk Monitoring via Early Safety Signal Distillation Authors: Hanling Wang, Chenlong Wei, Ling Xu, Hanyan Niu, Qi Cao, Shizhou Huang, Yang Yang, Xiaohui Zhu, Yao Zhu Published: 2026-09-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.13737v1 As large language models (LLMs) are increasingly deployed, the generation of harmful content has become a critical safety concern. Existing safeguards operate at the input, output, or streaming-generation stages, while early-risk methods that rely on surface tokens or output logits may suffer from weak initial signals, and internals-based detectors using dense representations may retain highly entangled and redundant safety-irrelevant information. It therefore remains unclear whether the earliest post-generation hidden states already contain reliable signals about final-response harmfulness. To address this gap, we propose ForeSight, a first-token output-risk forecasting framework that distills weak and redundant early safety signals into compact, layer-aware risk representations. Experiments on five safety benchmarks and two target models demonstrate that ForeSight achieves superior and efficient early-risk forecasting while relying solely on first-token hidden states. The code is available at: https://github.com/Scabbards1500/Foresight --- ### PolicyMem: Geometric Policy Memory for LLM Governance Authors: Yuanchen Bei, Zhengzhang Chen, Yanjun Zhao, Haoyu Wang, Hanghang Tong, Haifeng Chen Published: 2026-09-12 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.13734v1 As large language models (LLMs) are increasingly deployed in real-world high-stakes applications, effective governance has become essential. Existing safeguards largely follow two paradigms: learning-based guards provide strong semantic discrimination but couple policy behavior to trained models and taxonomies, while programmable frameworks offer flexible control but require substantial manual prompt and workflow engineering. Neither externalizes policies as reusable operational states, making it difficult to consistently reuse policy evidence across detection, intervention, and verification. In this paper, we introduce PolicyMem, a geometric policy memory that externalizes natural-language policies as reusable geometric memory objects represented by low-rank subspaces in a shared representation space. A memory writer compiles natural-language policies into policy memory slots, and query-response pairs read the policy memory through projection energy. The resulting policy-evidence profile directly mediates the safety verdict and is reused for policy attribution and post-intervention verification. Coupled with a response rewriter, PolicyMem enables a detect-rewrite-verify loop for LLM governance. Across five widely used benchmarks, PolicyMem achieves state-of-the-art unsafe behavior detection while enabling effective policy attribution, rewriting, and post-intervention verification through the shared policy memory. --- ### FFVO: A Feedforward Pose Decoder for Long-Horizon Visual Odometry Authors: Meng-Li Shih, Shih-Yang Su, Yuliang Zou, Hao Xiang, Haidong Zhu, Vincent Casser, Brian Curless, Dmitry Kalenichenko, Mingxing Tan, Dragomir Anguelov Published: 2026-09-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.13733v1 Stable and reliable 4D spatial understanding is fundamental for autonomous driving systems. While feedforward reconstruction networks can estimate camera motion and 3D structure in one pass, pose estimation over long videos remains challenged by computational cost, long-context ambiguity, and temporal instability. To address these challenges, we propose Feedforward Visual Odometry (FFVO), a pose-specialized adaptation of joint reconstruction architectures for efficient and temporally stable camera-pose estimation. FFVO uses (i) a compact camera-token representation for computationally efficient temporal aggregation, (ii) a hierarchical local-to-global temporal decoder that mitigates geometric ambiguity by separating short-range motion aggregation from sequence-level integration, and (iii) intermediate trajectory supervision that promotes temporal stability. Extensive evaluation on the Waymo Open Dataset (WOD), KITTI, and a large-scale proprietary benchmark demonstrates that our method performs favorably against existing feedforward approaches, and greatly reduces jitter and drift. These results support FFVO as an effective feedforward camera-pose decoder in long-horizon visual odometry settings. --- ### Trustworthy Agentic AI: A Comprehensive Cybersecurity and Systems Survey on Threat Landscapes, Defense Architectures, and Open Challenges Authors: Seyedakbar Mostafavi Published: 2026-09-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.13731v1 The transition from passive foundation models to autonomous, goal-directed agentic AI systems has introduced unprecedented capabilities by coupling recursive cognitive reasoning loops, persistent memory architectures, live tool execution planes, and multi-agent collaboration topologies. However, granting probabilistic neural cores execution authority across filesystems, networks, and cloud infrastructure dissolves classical security perimeters: natural language simultaneously serves as input data, internal control code, and communication protocols, exposing a Turing-complete blast radius where untrusted data represents executable instructions. This survey delivers a comprehensive systems-security reference framework for trustworthy agentic AI, synthesizing 206 foundational studies and regulatory standards. We formalize the general agent architecture as a stateful 5-tuple and establish a 6-dimensional trustworthiness taxonomy covering security, safety, privacy, explainability, fairness, and accountability. We systematically analyze threat surfaces across intra-execution loops and interaction planes, formulate a multi-layered zero-trust defense-in-depth architecture integrating Dual-LLM isolation, Capability-Based Access Control, kernel eBPF probes, and sandboxed runtimes, review standardized evaluation benchmarks, and map technical controls to international AI governance frameworks. --- ### JumpStart Your Policy Learning with Lessons from 160,000 Training Runs Authors: Nabil Omi, Eric Bae, Chung Yik Edward Yeung, Siddhartha Sen, Ali Farhadi Published: 2026-09-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.13730v2 Reliable progress in offline policy learning depends on careful reporting, well-tuned baselines, and evaluation across diverse conditions. Prior work has shown that results can be sensitive to reporting choices, hyperparameter tuning, and dataset properties, but these sources of variability have not been systematically investigated together at the scale needed to understand how they shape conclusions. To address this gap, we present a large-scale empirical study of offline reinforcement and imitation learning, training over 160,000 policies across 114 datasets. At this scale, no algorithm dominates: aggregate performance among the strongest methods is often close, but the leaders differ substantially across environments. We find that proper hyperparameter tuning frequently reshuffles perceived algorithm rankings and that benchmark composition can produce conflicting conclusions. We also study hyperparameter sensitivity and transfer across environments, identifying a simple strategy for deriving strong default configurations. We use our findings to develop a dataset-conditioned recommender that provides task-specific algorithm recommendations for practitioners. Finally, we release JumpStart: a resource suite containing every trained policy, per-model scores and hyperparameters, strong baselines across all environments, training and evaluation code, and an extensible website for retrieving, analyzing, and contributing results. Together, these resources aim to make offline policy-learning research more reliable and enable future work beyond the scope of this study. --- ### A Variational Optimal Transport Operator on Incompressible Flow Authors: Jinjin He, Shenyifan Lu, Sinan Wang, Zhiqi Li, Duowen Chen, Bo Zhu Published: 2026-09-12 Categories: cs.LG, cs.GR arXiv: https://arxiv.org/abs/2609.13729v1 We present the Variational Incompressible Optimal Transport (VIOT) operator, a generative neural operator for amortized incompressible density transport. Given a new source-target density pair, VIOT predicts a divergence-free velocity field and generates the full transport trajectory by feed-forward inference, replacing the hour-scale per-pair optimization used by adjoint fluid solvers and differentiable simulation baselines. The system consists of three components: a stream-function or vector-potential representation that enforces incompressibility by construction, a regularized incompressible transport objective that balances endpoint accuracy and flow smoothness, and a Fourier Neural Operator backbone that amortizes the solve across new pairs and grid resolutions. Together, these components make incompressible transport a reusable neural operator that facilitates various transport processes. Further, the generative capability extends beyond the training distribution, with VIOT producing incompressible transports for user-drawn source-target pairs in a real-time interactive system. We demonstrate VIOT on 2D and 3D density-transport benchmarks. Both 2D and 3D rollouts complete in seconds per pair, while per-instance baselines in our 2D comparisons optimize each new pair from scratch and require on the order of an hour, a roughly $10^4\times$ online speedup. --- ### TyPatch: Transforming Patches into Typestate Rules for Kernel Bug Detection Authors: Ruoyu Wang, Tuo Li, Jia Li Published: 2026-09-12 Categories: cs.SE, cs.AI, cs.CR, cs.OS arXiv: https://arxiv.org/abs/2609.13728v1 Historical Linux kernel patches capture defect knowledge that applies beyond their original repair sites. Recent work has shown that large language models (LLMs) can generate static-analysis checkers from historical patches and use them to uncover new kernel bugs. However, complete-checker generation requires the model both to recover the defect semantics expressed by a patch and to implement sophisticated program-analysis machinery, including object tracking, alias analysis, path-state maintenance, and interprocedural propagation. Coupling these responsibilities in a single end-to-end code-generation task can turn a simple defect rule into an unstable and expensive analyzer-implementation problem. To address this problem, we present TyPatch, which decouples patch-specific defect semantics from analyzer implementation. An LLM translates each patch into a typestate rule specifying its tracked object, actions, guards, transitions, and violations. A shared backend then executes these rules, binding their actions to program events, tracking object identity across aliases, propagating typestate along program paths, and producing reports for all rules. On Linux v6.16, TyPatch finds 559 distinct bugs, 121 of which have been confirmed by kernel developers. In a matched 38-patch comparison with the state-of-the-art complete-checker construction workflow, TyPatch uses 88.3-90.1% fewer generation tokens, while its initial report pools achieve 3.42-14.95$\times$ the precision of those produced by that workflow. --- ### IBBench-Light: A Paired Evaluation of Task-Conditioned Responses to External Directives Authors: Kainan Zhou, Gangzhen Qian, Zhaoyi Li, Hang Xiao Published: 2026-09-12 Categories: cs.AI, cs.LO arXiv: https://arxiv.org/abs/2609.13725v1 An external record may contain a procedure to apply or text to read, depending on the user's request. IBBench-Light tests both uses against the same record. Twelve semantic bases yield 144 matched pairs per model; four quantized instruction models produced 1,152 archived greedy responses. Paired exact-contract accuracy (PECA) requires both members to satisfy their output contracts. Qwen succeeds on 132 execute and 109 process prompts, but only 97 complete pairs, showing what marginal averages omit. We audit literal-target exposure and case normalization, then add 1,722 logged CPU generations to test directive-absent controls, twelve additional semantic bases, within-base wording changes, and generation stopping. In the pinned Phi rerun, changing the end-of-sequence (EOS) set changes exact paired success from 0/144 to 62/144. A bounded IHEval comparison uses the same SmolLM2 checkpoint and output budget while preserving its published instruction roles and scorer. The benchmark measures conditional task and output-contract success. Its task margins and paired count need to be read together with the stopping policy. --- ### Scaling Hindi Quantum Natural Language Processing through Automatic Pregroup Supertagging Authors: Gautami Sanjay Naik, Krishna Bhatia, Mithun Paul Saint-Germain, H Aswath Babu Published: 2026-09-12 Categories: cs.CL, quant-ph arXiv: https://arxiv.org/abs/2609.13721v1 Quantum Natural Language Processing (QNLP) uses pregroup grammars to translate grammatical structure into diagrammatic representations and quantum circuits. Recent Hindi QNLP work has shown that Hindi-specific pregroup grammars can support grammar-sensitive compositional models, but grammatical type assignment is still largely manual, limiting scalability. This paper formulates automatic Hindi pregroup supertagging as a token-level classification task. Using a manually annotated corpus of 380 Hindi sentences, we evaluate lexical, contextual, prompting-based, lexical-repair, and suffix/morphology-aware methods. Results show that simple lexical and contextual models are strong in this low-resource setting: contextual backoff achieves the best completed accuracy of 64.56\%, while raw Qwen2.5 prompting reaches only 11.65\%. Lexical repair raises LLM-assisted prediction to 64.08\%, demonstrating the value of constraining generative outputs with symbolic grammar knowledge. Diagnostic analysis further shows that seen and unambiguous tokens are much easier than unseen tokens, and suffix/morphology features improve karaka-token accuracy but not overall performance. These results show that automatic Hindi pregroup assignment is feasible and can reduce reliance on manual annotation in future multilingual QNLP pipelines. --- ### Oops, Not Now: PEARL, a RAG-Based Support Agent for Gameplay and What Players Want from AI Help Authors: Jiahong Li, Sai Siddartha Maram, Atieh Kashani, Ulia Zaman, Zhiyu Lin, Cameron Marano, Roger Azevedo, Jichen Zhu, Magy Seif El-Nasr Published: 2026-09-12 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2609.13718v1 AI-powered gameplay support agents hold promise for game-based learning, yet grounding generative models in structured game data remains an open challenge. We present PEARL (Parallel Education Agent for Reflection and Learning), a dual-component Retrieval-Augmented Generation (RAG) system that combines semantic knowledge retrieval with structural board-state matching to deliver contextualized scaffolding in Parallel, a puzzle game for learning parallel programming. PEARL operates on two input streams (natural language queries and board topology), retrieving both conceptual explanations of gameplay moves and peer-generated board states as evidence: capabilities unavailable to a standard Large Language Model (LLM) with game state access alone. In a qualitative evaluation (N=10) comparing PEARL against an existing community-based Open Player Model (OPM) visualization system, participants preferred the visualization system on perceived usefulness and reported higher frustration with PEARL; five of ten minimized or abandoned the AI tool during play. Proactive delivery, generic responses, and trust deficits drove disengagement, while a subset of four participants found PEARL's grounded explanations complementary to visualization in specific contexts where they initiated the interaction. We position PEARL as a deployed design probe whose failure modes inform a concrete design agenda for AI gameplay support, captured as seven open problems for the community. --- ### MANAS-2: Constrained Reconstruction for EEG Foundation Models Authors: Arvasu Kulkarni, Aditya Ray Mishra, Jeet Bandhu Lahiri, Mahir Jain, Parshva Runwal, Lakshya Saini, Siddharth Panwar, Sandeep Singh Published: 2026-09-12 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.13717v2 Masked reconstruction is widely used for EEG foundation models, but optimizing reconstruction on low-SNR waveforms does not necessarily produce the most useful latent representation. We introduce MANAS-2, a new EEG foundation model that combines a Raw-Band Hybrid (RBH) masked autoencoder with Constrained Reconstruction (ConRec), a physics-motivated regularizer. RBH jointly reconstructs temporal waveform patches and compact spectral-band targets, while ConRec acts only on the temporal decoder output, penalizing differences in RMS energy between adjacent short windows of the reconstructed waveform. ConRec is intended to shape the encoder by biasing it toward the organization of oscillatory-envelope information. Across seven held-out EEG datasets, adding ConRec to an otherwise identical RBH model increases frozen ridge recovery of six-band spectral power from mean R^2=0.860 to 0.906 and recovery of inter-patch band-energy dynamics from R^2=0.283 to 0.354, while temporal waveform information remains highly recoverable from the frozen latents. Applied to a temporal-only masked autoencoder, ConRec also improves frozen downstream transfer and frequency-dependent latent geometry despite receiving no spectral targets: i.e., the effects of ConRec are architecture-independent. MANAS-2 also outperforms leading EEG Foundation Models on most downstream knowledge-transfer tasks. From the effects of ConRec, we see that a physically motivated constraint imposed through the decoder can make for a more spectrally organized and transferable latent space. MANAS-2 therefore provides a new EEG foundation model built around constrained reconstruction as a mechanism for shaping representation--rather than reconstruction--quality. --- ### JaxAHT: A JAX-Based Library for Ad Hoc Teamwork Authors: Caroline Wang, Rolando Fernandez, Zelal Su Mustafaoglu, Montek Kundan, Jiaxun Cui, Lingyun Xiao, Zhihan Wang, Di Yang Shi, Aditya Madhan, Johnny Liu, Arrasy Rahman, Peter Stone Published: 2026-09-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.13716v1 Ad Hoc Teamwork (AHT) addresses the challenge of designing agents capable of coordinating with novel partners without prior coordination. However, progress in the field is hindered by the prohibitive computational cost of the AHT research lifecycle, the lack of standardized benchmark implementations, and the absence of a diverse, validated evaluation teammate suite. In this work, we introduce JaxAHT, the first open-source, JAX-based library designed to accelerate and standardize the AHT research lifecycle. Leveraging JAX's hardware acceleration and massive parallelization capabilities, JaxAHT provides a unified framework for teammate generation, ego agent training, and evaluation against unseen teammates, achieving approximately 95x wall-clock speedup over PyTorch counterparts. Alongside the library, we contribute a diverse suite of evaluation teammates across the domains of Level-Based Foraging, Overcooked, and Hanabi. To illustrate the value of the framework, we use it to conduct a large-scale, compute-controlled benchmark study comparing teammate generation and AHT agent learning methods, finding that no algorithm consistently performs best, and that agent modeling primarily offers benefits in role-based scenarios with diverse teammates. --- ### Certifying Model Upgrades with Slice-Wise Non-Regression and Incumbent Fallback Authors: Shengwei Zhang, Tao Wu, Fei Qian Published: 2026-09-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.13714v1 An updated model can improve an aggregate metric while degrading a slice that matters to a downstream user. We study checkpoint selection subject to non-regression tolerances relative to a retained incumbent. The central distinction is between failing to detect harm and certifying non-inferiority: the former can release harmful updates with high probability when evaluation is noisy. We give a reproducible release procedure that separates candidate search from independent, paired evaluation and returns the exact incumbent when certification fails. Applying established intersection-union and Learn-then-Test principles, we state finite-sample guarantees for one frozen candidate, a finite candidate library, and a prespecified testing order. A joint release decision does not require a slice-count Bonferroni penalty, although certification power can still decrease with the number of slices. In bounded-score simulations, a no-detected-harm gate releases a harmful candidate in 99.7% of trials in one 32-slice setting, compared with 2.6% for an exact non-inferiority gate at a 5% target. A constructed two-block family yields larger certified utility than a scalar path under matched candidate counts. Public digits experiments, including a subsequent continuation that improves average aggregate accuracy, return the incumbent in every run because certification is underpowered. These results establish an auditable protocol and its limitations; they do not establish benefits on foundation-model or multilingual translation upgrades. --- ### Degraded but Not Entirely Ineffective: PE-Based Deformable Graph Neural Networks Authors: Jinhua Wu, Xinliang Zhang Published: 2026-09-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.13712v1 Many real-world scenarios can be represented using graph-structured data. However, traditional GNNs that transmit messages based on first-order neighbors have long faced several fundamental contradictions: increasing depth leads to over-smoothing, long-range dependencies cause over-compression, fixed neighborhoods restrict the receptive field, and on heterophilous graphs, topological neighbors become a source of noise. Although many works have addressed these issues individually, few mechanisms can simultaneously alleviate all of these challenges. To address the aforementioned problems, we propose a Position Encoding-Based Deformable Spatial Aggregation Module (PEBDSAM) that solves them all in one step. Specifically, we utilize a deformable mechanism in the position space to identify relevant nodes to supplement the original first-order neighbor information of GNNs, allowing traditional GNNs to adapt to heterophilous scenarios. Through diagnostic experiments, we obtained several major findings: current offsets fail to have any effect; subsequently, we analyzed the causes of offset failure and why model performance still improves even after offset failure, pointing out future research directions. Based on these diagnostic experiments, we streamlined the original PEBDSAM, resulting in a simplified version, which we call the Position Encoding-Based Spatial Aggregation Module (PEBSAM). In addition, we propose a PEBSAM-Speed to adapt to large datasets. Finally, we designed the module to be plug-and-play and applied it to GCN, GAT, GIN, and GraphSAGE, achieving desirable results on three homophilous datasets and six heterophilous graph datasets. --- ### When Edit Localization Amplifies Relative Selection Bias: Gradient Geometry, Target Mismatch, and Importance Weighting Authors: Shengwei Zhang, Haoda Dai, Yifei Li, Yuheng Song Published: 2026-09-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.13709v1 Human corrections identify editable spans, but the examples receiving corrections may come from a selective feedback channel. We analyze this interaction at a fixed model checkpoint by decomposing a localized gradient into edited and retained untouched components. Squared relative selection bias is a ratio of quadratics whose derivative has the sign of an explicit quadratic polynomial. Localization can increase, decrease, or nonmonotonically change this diagnostic; its direction depends on component biases and geometry. Oracle importance weighting recovers the population mean for each fixed localization objective, but these objectives have different targets. Against one common full-gradient target, we derive the finite-sample mean-squared error, an analytic optimal retention coefficient, and a fixed-clipping extension. Exact finite-population calculations and 10,000 Monte Carlo repetitions per sample size verify the identities and counterexamples. Public human-post-edit experiments use two translation directions and pretrained models, with declared synthetic selection. An English-German extension differentiates 73.89 million native parameters. In all three declared settings, hard localization has higher relative bias but lower absolute bias than full retention. Untouched-component biases are nonzero and selected component means have negative inner products, so the general criterion applies where the simple unbiased/aligned explanation fails. Output-bias diagnostics show the same endpoint ordering of relative bias across both directions, with one interior maximum. Mechanisms reuse each language's records and include a mixture; they are not independent replications. The evidence separates relative amplification from absolute gradient error and establishes estimation properties, without inferring translation-quality gains or identifying actual complaint propensities. --- ### Rank-Consistent Set Reasoning for Co-Salient Object Detection Authors: Yuan Xiang, Matteo Rossi, Yingzhou Chen Published: 2026-09-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.13706v1 Co-salient object detection (Co-SOD) requires a model to find foreground regions that are salient in individual images and supported by the image group. We present \emph{Rank-Consistent Set Reasoning} (RCSR), a supervised dense-prediction framework that models a group as an unordered set rather than as a sequence of images or a semantic label. The core idea is to rank how strongly each spatial region agrees with a small collection of learned group slots at every image scale, and to aggregate these ranks with a robust trimmed statistic. This suppresses accidental pairwise matches and prevents one atypical group member from dominating the shared representation. A set encoder builds group slots directly from multi-scale visual features, while a rank-consistency gate measures whether the ordering of candidate regions is stable across group members. The gated slots are decoded jointly with per-image features to produce co-saliency maps. The model contains no natural-language branch, no open-vocabulary detector, and no external segmentation model. We further introduce a group permutation objective and hard-distractor augmentation so that the model learns the properties of a set-level target rather than memorizing image order or isolated visual saliency. We formulate an evaluation protocol for CoCA, CoSal2015, and CoSOD3k, together with tests of group-size robustness, distractor rejection, order invariance, and cross-dataset transfer. --- ### Gap Entropy and Almost Instance-Wise Optimal Best-Arm Identification Authors: Jiarui Yao, Jiaxi Zhao, Xiangxin Zhou Published: 2026-09-12 Categories: cs.CC, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.13703v1 In the best-arm identification problem, we are given $n$ stochastic arms with unknown means and wish to identify the arm with the largest mean with probability at least $1-δ$, using as few samples as possible. We consider independent Gaussian rewards with unit variance and means in $(0,1)$. Chen and Li (2016) conjectured that the instance-wise sample complexity of this problem is characterized by the gap entropy, up to an additive term arising from the two-arm problem. In this paper, we resolve their gap-entropy and almost instance-wise optimality conjectures. For an instance $I$, let $Δ_{(i)}$ be the gap between the largest and the $i$-th largest mean, let $H(I)=\sum_{i=2}^{n}Δ_{(i)}^{-2}$, and let Ent$(I)$ denote the entropy of the normalized complexities of its dyadic gap groups. For every $0<δ<0.1$, we show that the order-oblivious instance-wise lower bound is $ Θ (H(I)(\log(1/δ)+Ent(I))). $ We also give a single $δ$-correct algorithm with expected sample complexity $ O ( H(I)(\log(1/δ)+Ent(I)) +D\log(e+\log(e+D))),D=Δ_{(2)}^{-2}, $ without prior knowledge of the gaps. Our lower bound removes the dyadic-gap and monotonicity restrictions of previous work, and our upper bound removes the additional polylogarithmic factor multiplying the two-arm term. Thus, a single algorithm attains the instance-wise lower bound up to an additive two-arm term. The main theorems have been formalized and proved in Lean 4. --- ### Leakage-Safe and Scheduler-Aware Machine Learning for Grid Job Runtime Prediction Authors: Ashfaq Ali Shafin, Khandaker Mamun Ahmed Published: 2026-09-12 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.13701v1 Accurate job runtime prediction can improve scheduling-aware resource management in grid and distributed computing environments, but prediction models must be evaluated under realistic deployment constraints. This paper revisits CPU burst time prediction on the GWA-T-4 AuverGrid workload trace and reformulates it as leakage-safe pre-execution job runtime prediction. We define the target as job-level runtime, use only submission-time attributes, exclude post-execution variables, and evaluate models under temporal and cold-start settings rather than relying only on random cross-validation. We compare standard regressors, chronological historical baselines, categorical encoding strategies, and CatBoost with native categorical handling. We further add temporal hyperparameter tuning, runtime predictability analysis, feature ablation, error analysis by job length, and a minimal scheduling simulation. After temporal-validation tuning, CatBoost achieves the strongest deployment-oriented result with R^2=0.239, MAE=27,019, RMSE=46,587, and LogMAE=2.646 on the held-out temporal test set. A single-server simulation over all 69,523 held-out temporal test jobs shows that prediction-informed SJF reduces average waiting time by 50.92% relative to FCFS. The results show that random-split evaluation overestimates performance, categorical-native boosting improves temporal generalization, and long-job underestimation remains a scheduler-relevant challenge. --- ### Prefix Sharing Is a Sorting Problem Authors: Rong He Published: 2026-09-12 Categories: cs.DS, cs.CL arXiv: https://arxiv.org/abs/2609.13692v1 LLM serving reuses KV cache by exact prefix match, so when a prompt is assembled from a set of reusable pieces -- retrieved passages, tool definitions, few-shot exemplars -- the order chosen for those pieces determines how much computation can be shared. Every deployed system fixes that order by a single global convention. We prove this is optimal only when requests contain at most two pieces, and asymptotically wrong in general. Our main result is a structure theorem: the minimum prefix-trie cost equals min_H sum_x w(x) t_x(H) over binary hierarchies H on the requests, where t_x(H) is the canonical decomposition size of the set of requests needing chunk x. Choosing chunk orders is therefore equivalent to choosing one hierarchy over requests. The identity yields an O(3^m) exact algorithm, identifies the two-chunk case as minimum vertex cover, and shows that on the leave-one-out family the optimum is the minimum external path length of a binary tree -- the merge-sort recursion -- so a global order pays Theta(n^2) against a true cost of Theta(n log n). Agglomerative clustering by common intersection is a tight 1/2-approximation for the achievable saving. On BM25 retrieval traces over three BEIR corpora the resulting layout reduces prefill by 17-36% against production RAG ordering, and the margin widens with retrieval depth as the theory predicts. Serving requests in the hierarchy's DFS order finally lets a cache holding one request's context attain the unbounded-cache optimum exactly, so cache capacity and reorder window act as substitutes. --- ### MomentBA: Second-order Spatial Moments for Anisotropic Correspondence Uncertainty in Differentiable Bundle Adjustment Authors: Yuqing Wang, Xiaoji Niu, Yan Wang, Hailiang Tang, Jian Kuang, Tisheng Zhang Published: 2026-09-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.13691v1 Most existing visual odometry (VO) systems treat feature correspondences as deterministic measurements or assign uniform uncertainty, ignoring the inherent localization ambiguity of different observations. However, correspondence uncertainty is often anisotropic due to image structures such as edges, repetitive patterns, and motion blur, which can significantly affect geometric optimization. In this work, we propose MomentBA, a geometry-aware bundle adjustment framework that derives anisotropic correspondence uncertainty from second-order spatial moments of local similarity responses. Instead of introducing additional covariance prediction networks, the proposed method directly converts matching response distributions into interpretable covariance estimates and incorporates them into bundle adjustment as correspondence-specific information matrices for uncertainty-aware residual weighting. Furthermore, the proposed formulation is integrated into a differentiable optimization framework, establishing a direct connection between correspondence uncertainty and geometric estimation. Experiments on the EuRoC MAV and TartanAir v1 Hard datasets demonstrate that MomentBA improves monocular visual odometry accuracy compared with existing feature-based and learning-based approaches. The proposed anisotropic covariance model achieves lower rotational errors and more robust trajectory estimation than fixed and isotropic uncertainty models, validating the effectiveness of geometry-induced uncertainty modeling for challenging visual environments. --- ### SONAR: A Structure-Consistent Neural Operator for Null-Space-Aware Sparse View CT Reconstruction Authors: Song Ni, Haijun Yu, Haodong Li, Changsheng Fang, Shuyi Fan, Yixing Huang, Hengyong Yu Published: 2026-09-12 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2609.13688v1 Sparse-view computed tomography (CT) reduces radiation dose and acquisition time but remains severely ill-posed because incomplete projections poorly constrain null-space information. Existing learning-based methods often estimate this information in high-dimensional image space, conflate physical measurement errors with prediction errors, and depend on fixed discretizations. We propose SONAR, a Structure-Consistent Neural Operator for Null-Space-Aware Reconstruction. Instead of recovering the full null-space component, SONAR predicts a low-dimensional null-space-aware representation from the acquired projections as pseudo-measurements. It separates measurement and pseudo-measurement residuals, lifts them into the image domain through physics operators, and applies independent neural operators to constrain their structural effects, thereby accommodating admissible errors while suppressing unsupported structures. To support cross-discretization reconstruction, an anisotropic U-shaped neural operator models the periodic angular and nonperiodic detector dimensions using direction-dependent continuous supports, while image-domain neural operators re-discretize continuous kernels on target grids. These components form an optimization-inspired unrolled network. Experiments on simulated AAPM and clinical MARS photon-counting CT data demonstrate consistent improvements across seen and unseen view settings and unseen image resolutions. On AAPM dataset, SONAR improves PSNR by 1.87~dB at 62 views and by 7.63~dB under zero-shot transfer to a $512\times512$ grid over the strongest competing methods. SONAR also achieves the best overall performance in all clinical settings evaluated, demonstrating accurate, structurally reliable, and discretization-robust sparse-view CT reconstruction. --- ### Not all Negation Cues are Equal: Affixal Negations Yield Better Negation Understanding Authors: Tian Tan, Eduardo Blanco Published: 2026-09-12 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.13685v1 Negation remains a longstanding challenge for both language models (LMs) and large language models (LLMs). Prior work mainly focuses on a small set of high-frequency single-word negation cues, such as not and never, with limited exploration of broader negation types and modern LLMs. To address this gap, we construct NegCue, a large-scale dataset containing over 1.8M samples spanning single-word, multi-word, and affixal negation with more than 200 unique cues. We further pre-train both encoder-only LMs and LLMs on NegCue to investigate how different negation types affect negation understanding. Experiments on five downstream benchmarks show that negation types contribute unevenly to performance gains under the same training scale. In particular, affixal negation yields the largest improvements, while the gains from the commonly studied single-word negation remain modest. Moreover, our results demonstrate that further pre-training improves negation understanding for both LMs and LLMs. --- ### LayerRoute: Adaptive Layer-Skipping with LoRA-Preserved Quality for Efficient LLM Inference Authors: Prateek Kumar Sikdar Published: 2026-09-12 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.13682v1 We introduce LayerRoute, a parameter-efficient method for adaptive transformer layer-skipping that combines per-layer hard-gated routing (trained via a straight-through estimator) with joint LoRA fine-tuning. LayerRoute augments each of the 24 transformer blocks in Qwen2.5-0.5B-Instruct with a lightweight per-layer router (~21.5K parameters) and LoRA adapters (rank 8, ~1.08M parameters), training both jointly under a gate-regularized language-modeling objective. Across 10 independently-seeded training runs, LayerRoute converges to an identical skip-pattern structure in every run - a consistent set of 9 middle layers (8-16) becomes skip-eligible in all 10 seeds - and delivers genuine, verified wallclock speedup in every run (1.02x-1.06x, mean 1.04x). Quality is preserved or improved in every configuration tested: joint LoRA adaptation yields a perplexity improvement over the unmodified backbone in all 10 seeds (mean delta = -1.16 and -1.11 across the two evaluation splits used). We further verify the router performs genuine, non-trivial per-input computation: gate decisions in skip-eligible layers change the actual skip/run outcome for 87-100% of held-out samples, confirming real input-dependent routing rather than a fixed pruning pattern. LayerRoute trains in under 7 minutes on a single A100 and adds negligible overhead beyond the routing decision itself. We report our full reproducibility methodology, including a systematic diagnostic investigation into what determines the router's per-input decisions, as part of this work. --- ### Drift-Constrained Optimization: Only Direction Matters in Fine-Tuning Instruct Models Authors: Fei Yuan, Changjiang Gao, Yilei Tu, Yifeng Liu, Shujian Huang, Yu Qiao Published: 2026-09-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.13680v1 Fine-tuning instruct models often improves target performance while inducing behavioral drift from the reference model, which can degrade existing capabilities. Rather than treating this drift as an uncontrolled consequence of optimization, we specify a behavioral drift budget before optimization and ask how to boost the target-task performance within it. Locally, behavioral drift induces a shared geometry anchored at the reference model, with the drift budget defining a boundary within this space. In this space, drift determines distance from the reference, leaving update direction as the remaining degree of freedom. Fine-tuning updates can therefore be compared through their directional efficiency, naturally reformulating fine-tuning as a direction-selection problem. This reformulation makes a concrete prediction: changing the accessible directions can qualitatively alter the outcome of fine-tuning. We test this prediction in a stringent QA-only setting, where strong instruct models are fine-tuned only on final answers but must still generate multi-step reasoning at inference. Despite this mismatch, a coarse layer-selective probe reverses the failure of QA-only fine-tuning and reveals the existence of effective directions, with multiple neighboring configurations improving target performance while preserving reasoning and general capabilities. Across Qwen3-8B and Qwen3-14B, these directions substantially improve scientific reasoning and multilingual translation. Over more than 100 languages, the resulting models match or outperform dedicated translation systems and provide a stronger initialization for subsequent reinforcement learning. Our results suggest that fine-tuning is not just about how much a model changes, but how that change is spent. https://github.com/CONE-MT/DCO and https://huggingface.co/collections/LLaMAX/dco --- ### Nonsmooth Optimization via Orthogonalized Momentum Authors: Lexiao Lai, Tianyi Lin, Jiayu Zhang Published: 2026-09-12 Categories: math.OC, cs.LG arXiv: https://arxiv.org/abs/2609.13677v1 Modern real application problems involve matrix-valued parameters, yet conventional optimizers treat them as vectors, thereby motivating matrix-aware methods that exploit input-output geometry, such as Muon which orthogonalizes the momentum matrices before parameter updates. Its empirical success raises a conceptual question: can orthogonalized momentum remain effective beyond smooth optimization? This paper studies this question for locally Lipschitz functions using a generalized derivative framework compatible with backpropagation. Our first contribution is to identify a key limitation: for every fixed momentum factor $β\in(0,1)$, Muon can fail to approach the global optimal solution of a convex Lipschitz objective from almost every initialization, when step sizes adapt to the full gradient history. The failure can occur even along bounded iterates. Our example is inspired by the one of Parshakova et al. which only covers $β\in(0,\frac{1}{2})$. Then, we show that the obstruction lies in fixed momentum rather than orthogonalization. Indeed, when the momentum factor is adaptive and approaches 1 together with a vanishing step size, Muon recovers asymptotic convergence for nonconvex nonsmooth optimization under the boundedness and regularity conditions. Moreover, we propose MAGD, which combines orthogonalized momentum with gradient, weighted based on their relative progress. MAGD retains asymptotic convergence in nonconvex settings and achieves an $O(\min\{m,n\}ε^{-2})$ rate in convex settings. A lower bound shows the optimal dimension dependence. Experiments on synthetic problems, image classification, and LLM pretraining show MAGD is a simple and practical alternative to Muon. Together, our results characterize when orthogonalized momentum fails without smoothness and how it can be made reliable and we hope that the analysis may be useful more broadly. --- ### Windowed A-K-MDP Authors: Xiangwen Yang, Frankie Cho, Iadine Chades Published: 2026-09-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.13676v1 Markov decision processes (MDPs) are used to support decision-making in conservation of biodiversity, but policies, even over small state spaces, can be difficult to interpret for conservation managers. K-MDP methods address this problem by building simpler MDPs with at most K abstract states. We show that the previously proposed A-K-MDP algorithm that relies on selecting a discretisation divisor using binary search can skip better abstract states. To fix this issue, we propose Windowed A-K-MDP, an algorithm that generates every distinct feasible partition induced within a declared divisor window and evaluates candidates until reaching the ideal value loss (J = 0) or exhausting the family of candidates. Across 33 K-MDP instances, Windowed improved 25 and tied 8. --- ### Recoverability as a System Primitive for Long-Horizon AI Agents Authors: Zhihui Zhang, Wei Liu Published: 2026-09-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.13672v1 AI agents can be interrupted while editing files, calling tools, or carrying out multi-step tasks. Restarting repeats completed work, but continuing from unverified or outdated progress can carry earlier errors forward. A saved state is not necessarily a suitable place to resume. We introduce recoverability as a system primitive that makes reuse an explicit decision: select a supported starting point and a permitted recovery action, or withhold automatic continuation. Its behavioral contract binds that choice to supporting evidence, execution, and independent checks. A reference architecture connects persistence, validation, and control, with complementary runtime instances testing distinct responsibilities. Four deterministic and 20 paired file challenges demonstrate that accurate restoration and successful completion can conceal disallowed starting points. Progress controls attribute retained work to shared restoration. Event-time tests show that permission must also constrain the action, and that independently held policy evidence can expose violations even after an effect occurs. These findings establish why recovery decisions need their own evaluation, beyond restored bytes and final task success. Within supplied policies and a declared trust model, the contribution is a common, testable interface for retaining justified progress and making the conditions for its reuse explicit and enforceable. --- ### Not All Duplicates Are Coordination: Generic vs. Non-Generic Duplicate Campaigns in Information Operations Authors: Ashfaq Ali Shafin, Khandaker Mamun Ahmed Published: 2026-09-12 Categories: cs.SI, cs.LG arXiv: https://arxiv.org/abs/2609.13671v1 Duplicate content is widely used to study coordinated behavior in social media information operations (IOs), but not all repetition provides equally meaningful evidence of coordination. Generic, reusable, or low-information posts may create noisy account-account links when projected into coordination graphs. We study this problem using 187,000 English-language tweets from six Russian Twitter Information Operations datasets. We introduce a generic/non-generic distinction for duplicate campaigns, label tweets using an LLM-assisted protocol with independent human validation, and train supervised classifiers over sentence embeddings to scale the labels. We construct duplicate campaigns using lexical similarity and two embedding-based methods. Generic campaigns are rare under lexical matching but account for nearly 39% of campaigns detected by embedding-based methods. Restricting graphs to non-generic campaigns reduces graph size and the largest connected component while increasing density, suggesting a smaller but more focused coordination structure. These findings show that duplicate-based coordination analysis should consider both textual similarity and semantic specificity. --- ### Enhancing Event Candidate Acquisition for Event Linking Authors: Ziyang Zhang, Yinan Liu, Boyi Xue, Yingxuan Huang, Bin Wang, Xiaochun Yang Published: 2026-09-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.13670v1 Event linking associates event mentions in text with entries in a knowledge base (KB), or identifies them as out-of-KB events. Although existing methods use different architectures, candidate event acquisition can still be weakened by short ambiguous mentions, noisy arguments, and evidence that is unevenly useful for retrieval. We present MACE, a Multi-Agent Candidate Event acquisition method that refines event structure before linking. MACE uses evidence-specialized LLM agents to acquire time, location, participant, and event-type evidence, exposes intermediate queries to candidate-event lookup tools, and lets a coordinator revise the evidence set before final candidate construction. Experiments on two event linking benchmarks show that adding MACE to different event linking models consistently improves accuracy. These results show that MACE improves event linking through better candidate event acquisition without modifying the event linking model. --- ### GeoSkill:Experience-Driven Hierarchical Skill Learning with Collaborative Revision forGeospatialAgents Authors: Han Luo, Xian Xu, Yinhe Liu, Yanfei Zhong Published: 2026-09-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.13667v1 Geospatial agents are increasingly expected to support recurring and evolving analytical tasks rather than execute isolated workflows. In such settings, effective agents must distill prior execution experience into reusable geospatial procedural knowledge to guide future planning and tool use. However, existing memory-augmented paradigms struggle to summarize both long-horizon tool-chain orchestration experience and tool-level invocation constraints in geospatial analysis, while directly relying on LLM self-reflection to update experience often leads to misattribution and unreliable revisions. To address these challenges, we propose GeoSkill, an experience-driven hierarchical skill learning framework for geospatial agents. GeoSkill comprises two core components: (i) a Hierarchical Skill Bank (HSB), consisting of a Planning Skill Bank and a Tool Skill Bank, which respectively distill high-level task-planning experience and tool usage constraints, enabling structured representation and cross-task reuse of historical execution experience; and (ii) a Collaborative Trace-driven Skill Revision (CTSR) mechanism, where Judge, Critic, and Refiner collaboratively perform error identification, skill-level defect localization, and targeted modification, preventing misattributed and unreliable revisions from polluting the skill bank. GeoSkill learns and validates skills from historical executions during development, and freezes the skill bank for retrieval-only guidance on unseen tasks during deployment. Extensive experiments on EarthBench and ThinkGeo demonstrate that GeoSkill effectively transforms historical execution experience into reusable hierarchical skills, improving both end-to-end task accuracy and tool-execution reliability in geospatial tasks. --- ### MARC: Morphology-Aware Regression of Consensus for Cell Segmentation in Subcellular Spatial Transcriptomics Authors: Xinyu Shu, Andrew Zhang, Jean Yang, Jinman Kim Published: 2026-09-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.13665v1 Accurate cell segmentation remains a major bottleneck in subcellular spatial transcriptomics (SST), in which morphological images and spatially resolved RNA transcripts are used to partition tissues into individual cellular instances. As segmentation serves as the foundation for constructing cell-level representations, boundary errors can lead to incorrect transcript assignments and compromise downstream analyses. However, reliable ground-truth boundaries are unavailable because they must be inferred from incomplete morphological and transcript signals. Furthermore, manual annotation of a large number of cells is time-consuming. Agreement among complementary segmentation methods provides a practical surrogate for identifying well-supported and ambiguous regions, but explicit consensus construction requires executing multiple computationally intensive pipelines. In this study, we propose MARC (Morphology-Aware Regression of Consensus), a framework that predicts a multi-method consensus-support map for SST segmentation. MARC is trained with leave-one-method-out consensus pseudo-targets and a Foreground-Union Consensus Loss that focuses supervision on candidate and consensus foreground. We evaluated MARC on 4,642 held-out tiles from Xenium kidney tissue, achieving a mean Dice score of 0.90, a mean intersection-over-union of 0.82, and a mean cell-level Spearman correlation of 0.79 against explicitly computed cross-method consensus maps. We demonstrate that the predicted consensus maps localise weakly supported regions while preserving consensus-based rankings and identifying low-consensus cells for manual review. These results show that MARC closely approximates explicit cross-method consensus without multi-method inference and therefore has the potential to facilitate robust, consensus-aware evaluation of cell segmentation in large-scale SST studies. --- ### Cost Characterization of Vertically Partitioned Federated Knowledge Graphs Authors: Md Saikat Islam Khan Bappy, Oshani Seneviratne Published: 2026-09-12 Categories: cs.AI, cs.DB, cs.IR arXiv: https://arxiv.org/abs/2609.13664v1 Knowledge graphs are increasingly distributed across autonomous organizations that share an entity space but own disjoint subsets of relations, forming a vertical partition. Answering a multi-hop query may require combining facts from several silos, making the partitioning strategy a key data management decision that affects communication, indexing, load balance, and query latency. However, the costs associated with different partitioning strategies remain insufficiently studied. We formalize vertical partitioning as a design space and compare four strategies: semantic domain grouping, frequency-balanced partitioning, co-occurrence graph-cut partitioning, and random partitioning. We evaluate them using five metrics: communication cost, candidate index size, cross-silo path length, load balance, and end-to-end query latency. Three of the five prove to be determined by the graph and the silo count rather than by the partition, which reduces the design problem to two conflicting axes, cross-silo path length and load balance. Experiments on MetaQA and PathQuestion use a fixed federated knowledge graph question-answering architecture based on TransE embeddings and a frozen BERT encoder across three silo configurations. By keeping the learning model unchanged, we isolate the effect of partitioning and show that the trade-off between locality and balance holds only where each silo can hold several relations, weakening as the number of silos increases. The study provides practical guidance for deployments constrained by cross-silo reasoning or by silo load. --- ### FedV-KGQA in Practice: Design Lessons and an Interactive Prototype Authors: Md Saikat Islam Khan Bappy, Oshani Seneviratne Published: 2026-09-12 Categories: cs.AI, cs.CL, cs.IR arXiv: https://arxiv.org/abs/2609.13661v1 Knowledge graph question answering usually assumes that one system can reach the whole graph. In practice, facts are often held by organizations that share entity identifiers but own disjoint relation types, so no single party sees a complete reasoning chain. This poster presents the empirical findings of FedV-KGQA on multi-hop question answering over such vertically partitioned graphs. Each silo enriches its local graph and trains a knowledge graph embedding on its own triples. A server then concatenates the silo-specific entity views, anchors the projected question at the topic entity, and ranks candidates by similarity. Raw triples and relation embeddings never leave a silo. Comparing the FedV-KGQA experiments with one another yields three results. First, federated fusion recovers most of the centralized accuracy, while a single silo recovers little. Second, anchoring and enrichment matter more than the choice of embedding model. Third, the cheapest encoder depends on the target accuracy rather than on parameter count. This poster paper contributes that cross-experiment comparison, four design lessons drawn from it, and an interactive prototype that runs real inference and traces the full pipeline, per question, on released checkpoints. --- ### UniqueShip: Mitigating Data Leakage in Acoustic Ship Classification Benchmark Datasets Authors: Connor Hashemi, Trevor Stout, Anthony Hoogs, Jason Parham Published: 2026-09-12 Categories: cs.SD, cs.CV, eess.AS arXiv: https://arxiv.org/abs/2609.13659v1 Underwater Acoustic Target Recognition (UATR) of ships is well-suited for machine learning, yet its progress is hindered by the lack of large, diverse, and publicly available labeled datasets. In this work, we introduce UniqueShip, a machine learning-ready benchmark dataset for UATR applications sourced from the open Ocean Networks Canada (ONC) repository. Unlike previous datasets, we explicitly control for "data leakage" between the training and evaluation sets to ensure more reliable and generalizable model evaluation that does not encourage the model to memorize individual ships. We demonstrate that typical, random data partitioning in two prominent UATR datasets leads to falsely optimistic test performance, increasing accuracy by 10-48 percentage points compared to our more careful partitioning. Ablations on UniqueShip further show that doubling the number of unique vessels improves accuracy by 2.4-2.6 percentage points, while doubling total audio duration improves only by 0.8-1.3 points, indicating that vessel diversity should drive dataset curation more than total hours. We provide baselines with convolutional and transformer backbones, and analyze how ship metadata correlates with classification performance, finding that individual vessel characteristics predict classification difficulty far better than distance to the hydrophone alone. Overall, UniqueShip contains 2,460 hours of ship-radiated audio from 4,218 unique vessels (3,437 hours including background). We publish the dataset, code, and easy-to-download splits at uniqueshipdata.org to foster further UATR research. --- ### Safety as a Constraint: Fine-Tuning a LLM Recommender to Explain Itself Authors: Jiashu He, Emma Yanyang Kong, JJ Tan, David Fagnan Published: 2026-09-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.13657v1 Traditional recommender systems are typically trained to predict what item users will interact with next, but not why. However, offering personalized evidence for why a user might like the predicted item is an important way to enhance the service and to raise the likelihood that the user will be genuinely interested in the recommendation. This service can be delivered by integrating a frontier-model call into the member-facing pipeline, but it will add extra cost and latency. In this paper, we train a recommender LLM to generate personalized explanations for its reccomendation, based on the user's watching history at a large video streaming service. We impose two requirements on the generated explanation: it must be faithful to the elements of the shows it links, and it must be strictly non-harmful to the user. To this end, we first train two LLM-judge reward models covering three specific criteria, and propose constrained GRPO to incorporate these different criteria. On a held-out real-world testing set, our fine-tuned model improves the all-three-criteria PASS rate rises from 0.649 to 0.956 under our own judges and from 0.677 to 0.931 under an independent judge, where as the frontier generator performs similar to the untuned recommender baseline. We conduct further experiments to show that the model's language and recommendation abilities remain unchanged. Based on these results, we conclude that an LLM-based recommender can be fine-tuned on other complex tasks without compromising its original recommendation performance, thus provide insights for further agentic user interface powered by a single model. --- ### Online Bayesian Node Classification on Inductive Graphs under Distribution Shift Authors: Jinwen Xu, Gonzalo Mateos Buckstein, Qin Lu Published: 2026-09-12 Categories: cs.LG, stat.ME, stat.ML arXiv: https://arxiv.org/abs/2609.13655v1 On evolving graphs, node classifiers must satisfy two key requirements: inductive generalization to newly arriving nodes under distribution shift and calibrated uncertainty for safety-sensitive applications. Standard graph neural networks (GNNs) are typically trained once and address neither requirement. We adapt the Bayesian last-layer (BLL) model by placing random last-layer parameters on top of a deterministic GNN encoder for uncertainty quantification. The categorical softmax likelihood required for classification breaks Gaussian conjugacy, so neither the training posterior nor the test-time streaming update has a closed-form solution. To address both challenges, we introduce a variational Bayesian last-layer (VBLL) objective that jointly trains the encoder and an approximate last-layer posterior by maximizing an evidence lower bound with a Monte Carlo expected log-likelihood. At test time, we freeze the encoder and apply an online Laplace update to the last-layer posterior. This update corresponds to a power-prior Bayesian model with exponential forgetting and a Kullback-Leibler anchor to the training posterior. Across five node-classification benchmarks under distribution shift, online GVBLL is the only method to achieve the best accuracy and negative log-likelihood on every dataset. It improves accuracy by up to 17 percentage points on Cora and 14 percentage points on ogbn-arxiv over the strongest non-GVBLL baseline, while remaining competitive in calibration with MC Dropout, Deep Ensembles, Temperature Scaling, and Gaussian-process classifiers. --- ### Multimodal Foundation Models Adaptation based on Domain-Aware Relaxed Orthogonal Subspace for Remote Sensing Authors: Han Luo, Ruoyu Yang, Yinhe Liu, Yanfei Zhong Published: 2026-09-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.13654v1 Pretrained foundation models (FMs) have achieved remarkable success in computer vision, yet their high fine-tuning cost limits practical deployment. Parameter-efficient fine-tuning (PEFT) methods such as Low-Rank Adaptation (LoRA) improve efficiency by constraining updates to a predefined low-rank subspace. However, when applied to remote sensing tasks with substantial domain shifts, the fixed subspace is constructed without observing the downstream activation distribution and can therefore provide a poor coordinate system for adaptation, a phenomenon herein termed subspace mismatch. To address this issue, a unified framework is introduced, termed Domain-aware Relaxed Orthogonal Subspace adaptation (DROS), which reformulates low-rank adaptation as data-conditioned subspace learning and flexible subspace adaptation. Specifically, the weight decomposition is conditioned on second-order activation statistics estimated from the downstream training distribution, so that the initialization reflects the feature geometry actually induced by the remote-sensing data, followed by flexible geometric transformations enabled by a relaxed orthogonal parameterization. Furthermore, the framework is extended to multimodal settings (MM-DROS) by sharing transformation structures across modality-specific subspaces, facilitating efficient cross-modal interaction. Extensive experiments on multiple remote sensing benchmarks demonstrate that DROS achieves state-of-the-art performance, even surpassing full fine-tuning, without additional inference overhead. --- ### Compositional Shift Algebra: Extrapolating Mixed Robot Shifts Without Mixed Finetuning Authors: Jinting Hang, Zhenhui Cai Published: 2026-09-12 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2609.13651v1 Robot deployments rarely change one mechanism at a time: cameras, action interfaces, and physical dynamics often shift together. Prior adaptation recipes either finetune a new model for every mix or attempt to select which module to update. We instead learn shift operators on a modular stack z{=}E(o), a{=}g(z,u), z'{=}f(z,a) and compose them. Compositional Shift Algebra (CSA) fits single-factor observation, policy, and dynamics operators from exact-reset probes, then extrapolates held-out mixed shifts by operator composition---without mixed-shift finetuning. On ManiSkill StackCube, residual CSA matches an oracle mixed inverse on held-out mixes (success 1.0 over 10 seeds) while beating best-single / zero-shot / parameter-average baselines by { approx}67 pp. RGB-D vision-in-the-loop composition remains near oracle and far above non-compositional arms; a delay commutator stress shows ordered necessity for policy timesdelay. On a second task (PickCube), residual CSA again reaches compose 1.0 vs. 0.33 non-compositional (n{=}10), and an L1 vision controller without privileged cube/goal poses or grasp flags in the control loop retains compose 0.95 vs. 0.00. Main-track upgrades freeze PushCube (+33 pp), PegInsertion joint8 / pose7 EE (+67 pp each), and thin BC under frozen CSA (+67 pp); deeper BC and fair adapt baselines still need compose (+67 pp each), vision-localized BC needs compose (+56 pp), and delay favors ordered/few-shot deploy. We report Intervention-Gated Adaptation as a negative control. --- ### Solar Intelligence Authors: Jyotsna Singh Published: 2026-09-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.13648v1 Solar energy decision support is fragmented across dashboards that provide data without explanation, research papers are slow to parse, and general-purpose language models are not solar domain specific and answer without evidence. This paper introduces Solar Intelligence, a hybrid retrieval-augmented framework that unifies structured solar analytics, evidence-grounded scientific question answering, and machine learning forecasting in one system. The platform integrates daily NASA POWER solar and meteorological data, Biosphere 2 ground-sensor readings, and a curated corpus of research papers and institutional reports. Structured queries use DuckDB SQL; scientific questions are answered by a hybrid retriever that fuses BM25 and ChromaDB dense embeddings via Reciprocal Rank Fusion, with responses grounded through a language model (llama3.2:3b). An Extreme Gradient Boosting (XGBoost) model produces daily forecasts of irradiance, temperature, and wind speed. The system is exposed via FastAPI, Streamlit, and an MCP server, so it can be used as an application, an API service, or an agent tool - by students, researchers, and energy analysts. --- ### YOLO12-MambaScan: An Efficient Object Detector with High-Frequency Enhancement and State-Space Modeling Authors: Hao Wang Published: 2026-09-12 Categories: cs.CV, cs.IR arXiv: https://arxiv.org/abs/2609.13647v1 The rapid development of unmanned aerial vehicle (UAV) technology has made aerial-image object detection increasingly important for natural-resource monitoring, traffic management, and disaster response. Detecting small objects in aerial images remains difficult because objects occupy very few pixels, high-frequency cues are easily lost, and global context is hard to model in cluttered scenes. Existing detectors often retain insufficient edge, corner, and texture information. We propose \ours, an aerial-image detector built on the YOLO12 architecture. The model combines a triple-path high-frequency enhancement convolution module (TriPathHFConv), receptive-field coordinate-attention convolution (RFCAConv), and a Mamba-based global-context module. On VisDrone, at an input resolution of 960*960, ours achieves 60.0% mAP@50 and 38.6%mAP@50:95, demonstrating a favorable accuracy--efficiency trade-off for small-object detection. The benchmark and dataset protocol follow the VisDrone challenge setup. ---