# Research Papers — 2026-02 · bundle page 143 of 210 > Full-text markdown of papers #7101–7150 of 10493 published in 2026-02, newest first. AI-readable mirrors of the full 10493-paper 2026-02 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-02/page/143 [← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/142.md) [Next bundle →](https://aipod.dev/papers/archive/2026-02/page/144.md) ### CausalTAD: Injecting Causal Knowledge into Large Language Models for Tabular Anomaly Detection Authors: Ruiqi Wang, Ruikang Liu, Runyu Chen, Haoxiang Suo, Zhiyi Peng, Zhuo Tang, Changjian Chen Published: 2026-02-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.07798v1 Detecting anomalies in tabular data is critical for many real-world applications, such as credit card fraud detection. With the rapid advancements in large language models (LLMs), state-of-the-art performance in tabular anomaly detection has been achieved by converting tabular data into text and fine-tuning LLMs. However, these methods randomly order columns during conversion, without considering the causal relationships between them, which is crucial for accurately detecting anomalies. In this paper, we present CausalTaD, a method that injects causal knowledge into LLMs for tabular anomaly detection. We first identify the causal relationships between columns and reorder them to align with these causal relationships. This reordering can be modeled as a linear ordering problem. Since each column contributes differently to the causal relationships, we further propose a reweighting strategy to assign different weights to different columns to enhance this effect. Experiments across more than 30 datasets demonstrate that our method consistently outperforms the current state-of-the-art methods. The code for CausalTAD is available at https://github.com/350234/CausalTAD. --- ### Thinking Is Not Telling: Information Disclosure in User-Service LLM Agents Authors: Jiatong Li, Changdae Oh, Hyeong Kyu Choi, Jindong Wang, Sharon Li Published: 2026-02-08 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.07796v2 User-engaged LLM agents increasingly operate in service scenarios where task success depends on coordination between the agent, the user, and a stateful environment. In such interactions, the agent often has access to task policies, tool results, and environment states that the user does not observe. This makes agent-user communication a central component of task completion. In this work, we study a communication-level failure mode of user-service agents: user-invisible reasoning does not necessarily translate into timely user-facing information disclosure. We introduce information disclosure as a measurable communication mechanism, covering state corrections, available options, constraints, consequences, and proactively retrieved environment information. We use this perspective to analyze the widely used user-invisible ``think'' tool, which allows agents to reason internally before responding or acting. Across five models and three user-service scenarios, we first show that enforced thinking has unstable utility. We then analyze response scaling under different think efforts and find that more internal thinking does not reliably translate into richer user-facing communication. Using evidence-grounded probing and turn-level counterfactual intervention, we show that injecting golden decision-relevant information produces the clearest improvement in First Edit Correction Rate, outperforming verbosity and direct think-content controls. This indicates that missing disclosure can causally affect the agent's immediate downstream environment-edit behavior. We further find that a lightweight disclosure-aware prompt mitigates degradation from enforced thinking. These results suggest that the key challenge is not simply making agents think more, but ensuring that private reasoning and environment knowledge are externalized as timely, user-facing information disclosure. --- ### Thinking Makes LLM Agents Introverted: How Mandatory Thinking Can Backfire in User-Engaged Agents Authors: Jiatong Li, Changdae Oh, Hyeong Kyu Choi, Jindong Wang, Sharon Li Published: 2026-02-08 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.07796v1 Eliciting reasoning has emerged as a powerful technique for improving the performance of large language models (LLMs) on complex tasks by inducing thinking. However, their effectiveness in realistic user-engaged agent scenarios remains unclear. In this paper, we conduct a comprehensive study on the effect of explicit thinking in user-engaged LLM agents. Our experiments span across seven models, three benchmarks, and two thinking instantiations, and we evaluate them through both a quantitative response taxonomy analysis and qualitative failure propagation case studies. Contrary to expectations, we find that mandatory thinking often backfires on agents in user-engaged settings, causing anomalous performance degradation across various LLMs. Our key finding reveals that thinking makes agents more ``introverted'' by shortening responses and reducing information disclosure to users, which weakens agent-user information exchange and leads to downstream task failures. Furthermore, we demonstrate that explicitly prompting for information disclosure reliably improves performance across diverse model families, suggesting that proactive transparency is a vital lever for agent optimization. Overall, our study suggests that information transparency awareness is a crucial yet underexplored perspective for the future design of reasoning agents in real-world scenarios. Our code is available at https://github.com/deeplearning-wisc/Thinking-Agent. --- ### Emergent Structured Representations Support Flexible In-Context Inference in Large Language Models Authors: Ningyu Xu, Qi Zhang, Xipeng Qiu, Xuanjing Huang Published: 2026-02-08 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.07794v3 Large language models (LLMs) exhibit emergent behaviors suggestive of human-like reasoning. While recent work has identified structured conceptual representations within these models, it remains unclear whether they functionally rely on such representations for reasoning. Here we investigate the internal processing of LLMs during in-context inference across diverse tasks. Our results reveal a conceptual subspace emerging in middle to late layers, whose representational structure persists across contexts. Using causal mediation analyses, we demonstrate that this subspace is not merely an epiphenomenon but is functionally central to model predictions, establishing its causal role in inference. We further identify a layer-wise progression where attention heads in early-to-middle layers integrate contextual cues to construct and refine the subspace, which is subsequently leveraged by later layers to generate predictions. Together, these findings provide evidence that LLMs dynamically construct and use structured latent representations in context for inference, offering insights into the computational processes underlying flexible adaptation. --- ### MaD-Mix: Multi-Modal Data Mixtures via Latent Space Coupling for Vision-Language Model Training Authors: Wanyun Xie, Francesco Tonin, Volkan Cevher Published: 2026-02-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.07790v1 Vision-Language Models (VLMs) are typically trained on a diverse set of multi-modal domains, yet current practices rely on costly manual tuning. We propose MaD-Mix, a principled and computationally efficient framework that derives multi-modal data mixtures for VLM training. MaD-Mix formulates data mixing as modality-aware domain alignment maximization and obtains closed-form multi-modal alignment scores from the Fenchel dual through inter-modal coupling variables. MaD-Mix systematically handles domains with missing modalities, allowing for the integration of language-only domains. Empirical evaluations across 0.5B and 7B models demonstrate that MaD-Mix accelerates VLM training across diverse benchmarks. MaD-Mix matches human-tuned data mixtures using 22% fewer training steps in image-text instruction tuning. In complex tri-modal video-image-text scenarios, where manual tuning becomes impractical, MaD-Mix boosts average accuracy over uniform weights, with negligible mixture computation overhead (< 1 GPU-hour), enabling scalable mixture design for modern VLM pipelines. --- ### Do Multi-Agents Dream of Electric Screens? Achieving Perfect Accuracy on AndroidWorld Through Task Decomposition Authors: Pierre-Louis Favreau, Jean-Pierre Lo, Clement Guiguet, Charles Simon-Meunier, Nicolas Dehandschoewercker, Allen G. Roush, Judah Goldfeder, Ravid Shwartz-Ziv Published: 2026-02-08 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.07787v1 We present Minitap, a multi-agent system that achieves 100% success on the AndroidWorld benchmark, the first to fully solve all 116 tasks and surpassing human performance (80%). We first analyze why single-agent architectures fail: context pollution from mixed reasoning traces, silent text input failures undetected by the agent, and repetitive action loops without escape. Minitap addresses each failure through targeted mechanisms: cognitive separation across six specialized agents, deterministic post-validation of text input against device state, and meta-cognitive reasoning that detects cycles and triggers strategy changes. Ablations show multi-agent decomposition contributes +21 points over single-agent baselines; verified execution adds +7 points; meta-cognition adds +9 points. We release Minitap as open-source software. https://github.com/minitap-ai/mobile-use --- ### UCATSC: Uncertainty-Aware Constrained Traffic Signal Control Under Vision-Based Partial Observability Authors: Jayawant Bodagala, Balaji Bodagala Published: 2026-02-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.07784v3 Camera-based adaptive traffic signal control is inherently partially observable: detections can be missed, vehicle speeds and distances can be noisy, and a phase-change decision becomes temporally irreversible once yellow onset is initiated. This paper presents UCATSC, an interpretable uncertainty-aware constrained decision layer for vision-based adaptive signal control. UCATSC maintains a reduced movement-level belief state over queue, arrival, and service-age variables; evaluates admissible phase actions through finite-horizon counterfactual rollouts in belief space; and filters candidate actions using predictive dilemma-zone safety and service-age/starvation constraints before execution. The method is evaluated primarily in SUMO using matched seeds, classical baselines, a trained DQN-RL baseline, a safety-masked DQN variant, targeted safety/liveness/uncertainty stress tests, and a three-intersection corridor extension. In the tested scenarios, UCATSC demonstrates competitive mobility performance, eliminates observed dilemma-zone violations for the constrained variants, bounds service age in starvation stress tests, and maintains millisecond-level online runtime. A controlled physical vision testbed is included as supplementary feasibility evidence for the vision-to-belief interface; it is not presented as field validation of safety, emissions, or deployment readiness. --- ### Still Manual? Automated Linter Configuration via DSL-Based LLM Compilation of Coding Standards Authors: Zejun Zhang, Yixin Gan, Zhenchang Xing, Tian Zhang, Yi Li, Xiwei Xu, Qinghua Lu, Liming Zhu Published: 2026-02-08 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2602.07783v1 Coding standards are essential for maintaining consistent and high-quality code across teams and projects. Linters help developers enforce these standards by detecting code violations. However, manual linter configuration is complex and expertise-intensive, and the diversity and evolution of programming languages, coding standards, and linters lead to repetitive and maintenance-intensive configuration work. To reduce manual effort, we propose LintCFG, a domain-specific language (DSL)-driven, LLM-based compilation approach to automate linter configuration generation for coding standards, independent of programming languages, coding standards, and linters. Inspired by compiler design, we first design a DSL to express coding rules in a tool-agnostic, structured, readable, and precise manner. Then, we build linter configurations into DSL configuration instructions. For a given natural language coding standard, the compilation process parses it into DSL coding standards, matches them with the DSL configuration instructions to set configuration names, option names and values, verifies consistency between the standards and configurations, and finally generates linter-specific configurations. Experiments with Checkstyle for Java coding standard show that our approach achieves over 90% precision and recall in DSL representation, with accuracy, precision, recall, and F1-scores close to 70% (with some exceeding 70%) in fine-grained linter configuration generation. Notably, our approach outperforms baselines by over 100% in precision. A user study further shows that our approach improves developers' efficiency in configuring linters for coding standards. Finally, we demonstrate the generality of the approach by generating ESLint configurations for JavaScript coding standards, showcasing its broad applicability across other programming languages, coding standards, and linters. --- ### Attn-GS: Attention-Guided Context Compression for Efficient Personalized LLMs Authors: Shenglai Zeng, Tianqi Zheng, Chuan Tian, Dante Everaert, Yau-Shian Wang, Yupin Huang, Michael J. Morais, Rohit Patki, Jinjin Tian, Xinnan Dai, Kai Guo, Monica Xiao Cheng et al. Published: 2026-02-08 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.07778v1 Personalizing large language models (LLMs) to individual users requires incorporating extensive interaction histories and profiles, but input token constraints make this impractical due to high inference latency and API costs. Existing approaches rely on heuristic methods such as selecting recent interactions or prompting summarization models to compress user profiles. However, these methods treat context as a monolithic whole and fail to consider how LLMs internally process and prioritize different profile components. We investigate whether LLMs' attention patterns can effectively identify important personalization signals for intelligent context compression. Through preliminary studies on representative personalization tasks, we discover that (a) LLMs' attention patterns naturally reveal important signals, and (b) fine-tuning enhances LLMs' ability to distinguish between relevant and irrelevant information. Based on these insights, we propose Attn-GS, an attention-guided context compression framework that leverages attention feedback from a marking model to mark important personalization sentences, then guides a compression model to generate task-relevant, high-quality compressed user contexts. Extensive experiments demonstrate that Attn-GS significantly outperforms various baselines across different tasks, token limits, and settings, achieving performance close to using full context while reducing token usage by 50 times. --- ### Rolling Sink: Bridging Limited-Horizon Training and Open-Ended Testing in Autoregressive Video Diffusion Authors: Haodong Li, Shaoteng Liu, Zhe Lin, Manmohan Chandraker Published: 2026-02-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.07775v7 Autoregressive (AR) video diffusion models in the Self Forcing family generate a video chunk by chunk, each conditioned on the ones before it, so they can keep rolling out with no preset length. In practice they are trained on short, fixed clips (e.g., 5s). Once a rollout passes this training horizon, the cache fills with self-generated chunks the model never saw in training, and quality degrades: colors oversaturate, identities drift, structures collapse, and motion fades. We frame this failure as a cache-behavior mismatch, a domain shift between the within-horizon caches seen in training and those produced by open-ended testing, and address it with Rolling Sink, a training-free inference-time cache policy. Within the base model's fixed cache budget, Rolling Sink holds the cache close to its stable within-horizon behavior: it restores low-drift content, sliding temporal indices, and evolving semantics, and keeps a small recent context. Attention sink and temporal re-indexing are existing mechanisms. Our contribution is the mismatch formulation, the joint bounded-cache policy, and the Rolling Semantics schedule. On two 5s-trained bases, Self Forcing and Causal Forcing, Rolling Sink attains the best averaged rank on VBench-Long at both 1- and 5-minute rollouts under the same inference setting, at about 0.56% throughput change, and holds GPU memory constant. It also sustains a 30-minute qualitative rollout, 360 times its training horizon. We validate at 1- and 5-minute rollouts and do not claim guaranteed quality at arbitrary duration. Project page: https://rolling-sink.github.io/ --- ### Rolling Sink: Bridging Limited-Horizon Training and Open-Ended Testing in Autoregressive Video Diffusion Authors: Haodong Li, Shaoteng Liu, Zhe Lin, Manmohan Chandraker Published: 2026-02-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.07775v6 Recently, autoregressive (AR) video diffusion models have achieved remarkable performance. However, due to their limited training durations, a train-test gap emerges when testing at longer horizons, leading to rapid visual degradations. Following Self Forcing, which studies the train-test gap within the training duration, this work studies the train-test gap beyond the training duration, i.e., the gap between the limited horizons during training and open-ended horizons during testing. Since open-ended testing can extend beyond any finite training window, and long-video training is computationally expensive, we pursue a training-free solution to bridge this gap. To explore a training-free solution, we conduct a systematic analysis of AR cache maintenance. These insights lead to Rolling Sink. Built on Self Forcing (trained on only 5s clips), Rolling Sink effectively scales the AR video synthesis to ultra-long durations (e.g., 5-30 minutes at 16 FPS) at test time, with consistent subjects, stable colors, coherent structures, and smooth motions. As demonstrated by extensive experiments, Rolling Sink achieves superior long-horizon visual fidelity and temporal consistency compared to SOTA baselines. Project page: https://rolling-sink.github.io/ --- ### GR2: Generative Reasoning Re-ranker Authors: Mingfu Liang, Yufei Li, Jay Xu, Kavosh Asadi, Xi Liu, Shuo Gu, Kaushik Rangadurai, Frank Shyu, Shuaiwen Wang, Song Yang, Zhijing Li, Jiang Liu et al. Published: 2026-02-08 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2602.07774v6 Recent studies increasingly explore Large Language Models (LLMs) as a new paradigm for recommendation systems due to their scalability and world knowledge. However, existing work has three key limitations: (1) most efforts focus on retrieval and ranking, while the reranking phase, critical for refining final recommendations, is largely overlooked; (2) LLMs are typically used in zero-shot or supervised fine-tuning settings, leaving their reasoning abilities, especially those enhanced through reinforcement learning (RL) and high-quality reasoning data, underexploited; (3) items are commonly represented by non-semantic IDs, creating major scalability challenges in industrial systems with billions of identifiers. To address these gaps, we propose the Generative Reasoning Reranker (GR2), an end-to-end framework with a three-stage training pipeline tailored for reranking. First, a pretrained LLM is mid-trained on semantic IDs encoded from non-semantic IDs via a tokenizer achieving $\ge$99% uniqueness. Next, a stronger larger-scale LLM generates high-quality reasoning traces through carefully designed prompting and rejection sampling, which are used for supervised fine-tuning to impart foundational reasoning skills. Finally, we apply Decoupled Clip and Dynamic sAmpling Policy Optimization (DAPO), enabling scalable RL supervision with verifiable rewards designed specifically for reranking. Experiments on two real-world datasets demonstrate GR2's effectiveness: it surpasses the state-of-the-art OneRec-Think by 2.4% in Recall@5 and 1.3% in NDCG@5. Ablations confirm that advanced reasoning traces yield substantial gains across metrics. We further find that RL reward design is crucial in reranking: LLMs tend to exploit reward hacking by preserving item order, motivating conditional verifiable rewards to mitigate this behavior and optimize reranking performance. --- ### SRR-Judge: Step-Level Rating and Refinement for Enhancing Search-Integrated Reasoning in Search Agents Authors: Chen Zhang, Kuicai Dong, Dexun Li, Wenjun Li, Qu Yang, Wei Han, Yong Liu Published: 2026-02-08 Categories: cs.CL, cs.IR arXiv: https://arxiv.org/abs/2602.07773v1 Recent deep search agents built on large reasoning models (LRMs) excel at complex question answering by iteratively planning, acting, and gathering evidence, a capability known as search-integrated reasoning. However, mainstream approaches often train this ability using only outcome-based supervision, neglecting the quality of intermediate thoughts and actions. We introduce SRR-Judge, a framework for reliable step-level assessment of reasoning and search actions. Integrated into a modified ReAct-style rate-and-refine workflow, SRR-Judge provides fine-grained guidance for search-integrated reasoning and enables efficient post-training annotation. Using SRR-annotated data, we apply an iterative rejection sampling fine-tuning procedure to enhance the deep search capability of the base agent. Empirically, SRR-Judge delivers more reliable step-level evaluations than much larger models such as DeepSeek-V3.1, with its ratings showing strong correlation with final answer correctness. Moreover, aligning the policy with SRR-Judge annotated trajectories leads to substantial performance gains, yielding over a 10 percent average absolute pass@1 improvement across challenging deep search benchmarks. --- ### PAND: Prompt-Aware Neighborhood Distillation for Lightweight Fine-Grained Visual Classification Authors: Qiuming Luo, Yuebing Li, Feng Li, Chang Kong Published: 2026-02-08 Categories: cs.CV, cs.AI, cs.LG, cs.MM arXiv: https://arxiv.org/abs/2602.07768v3 Distilling knowledge from large Vision-Language Models (VLMs) into lightweight networks is crucial yet challenging in Fine-Grained Visual Classification (FGVC), due to the reliance on fixed prompts and global alignment. To address this, we propose PAND (Prompt-Aware Neighborhood Distillation), a two-stage framework that decouples semantic calibration from structural transfer. First, we incorporate Prompt-Aware Semantic Calibration to generate adaptive semantic anchors. Second, we introduce a neighborhood-aware structural distillation strategy to constrain the student's local decision structure. PAND consistently outperforms state-of-the-art methods on four FGVC benchmarks. Notably, our ResNet-18 student achieves 76.09% accuracy on CUB-200, surpassing the strong baseline VL2Lite by 3.4%. Code is available at https://github.com/LLLVTA/PAND. --- ### BFTS: Thompson Sampling with Bayesian Additive Regression Trees Authors: Ruizhe Deng, Bibhas Chakraborty, Ran Chen, Yan Shuo Tan Published: 2026-02-08 Categories: stat.ML, cs.LG, stat.ME arXiv: https://arxiv.org/abs/2602.07767v1 Contextual bandits are a core technology for personalized mobile health interventions, where decision-making requires adapting to complex, non-linear user behaviors. While Thompson Sampling (TS) is a preferred strategy for these problems, its performance hinges on the quality of the underlying reward model. Standard linear models suffer from high bias, while neural network approaches are often brittle and difficult to tune in online settings. Conversely, tree ensembles dominate tabular data prediction but typically rely on heuristic uncertainty quantification, lacking a principled probabilistic basis for TS. We propose Bayesian Forest Thompson Sampling (BFTS), the first contextual bandit algorithm to integrate Bayesian Additive Regression Trees (BART), a fully probabilistic sum-of-trees model, directly into the exploration loop. We prove that BFTS is theoretically sound, deriving an information-theoretic Bayesian regret bound of $\tilde{O}(\sqrt{T})$. As a complementary result, we establish frequentist minimax optimality for a "feel-good" variant, confirming the structural suitability of BART priors for non-parametric bandits. Empirically, BFTS achieves state-of-the-art regret on tabular benchmarks with near-nominal uncertainty calibration. Furthermore, in an offline policy evaluation on the Drink Less micro-randomized trial, BFTS improves engagement rates by over 30% compared to the deployed policy, demonstrating its practical effectiveness for behavioral interventions. --- ### Disentangled Instrumental Variables for Causal Inference with Networked Observational Data Authors: Zhirong Huang, Debo Cheng, Guixian Zhang, Yi Wang, Jiuyong Li, Shichao Zhang Published: 2026-02-08 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.07765v1 Instrumental variables (IVs) are crucial for addressing unobservable confounders, yet their stringent exogeneity assumptions pose significant challenges in networked data. Existing methods typically rely on modelling neighbour information when recovering IVs, thereby inevitably mixing shared environment-induced endogenous correlations and individual-specific exogenous variation, leading the resulting IVs to inherit dependence on unobserved confounders and to violate exogeneity. To overcome this challenge, we propose $\underline{Dis}$entangled $\underline{I}$nstrumental $\underline{V}$ariables (DisIV) framework, a novel method for causal inference based on networked observational data with latent confounders. DisIV exploits network homogeneity as an inductive bias and employs a structural disentanglement mechanism to extract individual-specific components that serve as latent IVs. The causal validity of the extracted IVs is constrained through explicit orthogonality and exclusion conditions. Extensive semi-synthetic experiments on real-world datasets demonstrate that DisIV consistently outperforms state-of-the-art baselines in causal effect estimation under network-induced confounding. --- ### Preference Conditioned Multi-Objective Reinforcement Learning: Decomposed, Diversity-Driven Policy Optimization Authors: Tanmay Ambadkar, Sourav Panda, Shreyash Kale, Jonathan Dodge, Abhinav Verma Published: 2026-02-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.07764v2 Multi-objective reinforcement learning (MORL) seeks to train agents capable of balancing conflicting objectives. While single preference-conditioned policies offer a highly scalable solution, existing approaches remain brittle in practice, frequently failing to recover dense Pareto fronts. We demonstrate that this failure stems from two structural pathologies: destructive advantage cancellation caused by premature Early Scalarization (ES), and representational mode collapse across the preference space. To overcome these bottlenecks, we introduce $D^3PO$, a PPO-based framework that fundamentally reorganizes multi-objective optimization. By preserving per-objective learning signals through a decomposed pipeline and integrating preferences only after trust-region stabilization (Late-Stage Weighting), $D^3PO$ improves credit assignment under conflicting objectives. Concurrently, a scaled diversity regularizer encourages behavioral divergence proportional to preference distance. $D^3PO$ operates entirely within the efficient linear scalarization regime shared by standard deep MORL baselines. By reducing information loss caused due to linear scalarization rather than relying on expensive non-linear utility functions, it suggests that optimization bottlenecks play a significant role. Across available standard benchmarks, including high-dimensional and many-objective environments, $D^3PO$ consistently discovers broader, higher-quality Pareto fronts than prior methods, exceeding state-of-the-art hypervolume and expected utility using a single deployable policy. --- ### Learning to Continually Learn via Meta-learning Agentic Memory Designs Authors: Yiming Xiong, Shengran Hu, Jeff Clune Published: 2026-02-08 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.07755v1 The statelessness of foundation models bottlenecks agentic systems' ability to continually learn, a core capability for long-horizon reasoning and adaptation. To address this limitation, agentic systems commonly incorporate memory modules to retain and reuse past experience, aiming for continual learning during test time. However, most existing memory designs are human-crafted and fixed, which limits their ability to adapt to the diversity and non-stationarity of real-world tasks. In this paper, we introduce ALMA (Automated meta-Learning of Memory designs for Agentic systems), a framework that meta-learns memory designs to replace hand-engineered memory designs, therefore minimizing human effort and enabling agentic systems to be continual learners across diverse domains. Our approach employs a Meta Agent that searches over memory designs expressed as executable code in an open-ended manner, theoretically allowing the discovery of arbitrary memory designs, including database schemas as well as their retrieval and update mechanisms. Extensive experiments across four sequential decision-making domains demonstrate that the learned memory designs enable more effective and efficient learning from experience than state-of-the-art human-crafted memory designs on all benchmarks. When developed and deployed safely, ALMA represents a step toward self-improving AI systems that learn to be adaptive, continual learners. --- ### Humanizing AI Grading: Student-Centered Insights on Fairness, Trust, Consistency and Transparency Authors: Bahare Riahi, Viktoriia Storozhevykh, Veronica Catete Published: 2026-02-08 Categories: cs.AI, cs.HC arXiv: https://arxiv.org/abs/2602.07754v2 This study investigates students' perceptions of Artificial Intelligence (AI) grading systems in an undergraduate computer science course (n = 27), focusing on a block-based programming final project. Guided by the ethical principles framework articulated by Jobin (2019), our study examines fairness, trust, consistency, and transparency in AI grading by comparing AI-generated feedback with original human-graded feedback. Findings reveal concerns about AI's lack of contextual understanding and personalization. We recommend that equitable and trustworthy AI systems reflect human judgment, flexibility, and empathy, serving as supplementary tools under human oversight. This work contributes to ethics-centered assessment practices by amplifying student voices and offering design principles for humanizing AI in designed learning environments. --- ### Geo-Code: A Code Framework for Reverse Code Generation from Geometric Images Based on Two-Stage Multi-Agent Evolution Authors: Zhenyu Wu, Yanxi Long, Jian Li, Hua Huang Published: 2026-02-08 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.07749v1 Program code serves as a bridge linking vision and logic, providing a feasible supervisory approach for enhancing the multimodal reasoning capability of large models through geometric operations such as auxiliary line construction and perspective transformation. Nevertheless, current inverse graphics methods face tremendous challenges in accurately reconstructing complex geometric details, which often results in the loss of key geometric constraints or structural distortion. To address this bottleneck, we propose Geo-coder -- the first inverse programming framework for geometric images based on a multi-agent system. Our method innovatively decouples the process into geometric modeling via pixel-wise anchoring and metric-driven code evolution: Stage 1 leverages the complementary advantages of visual operators and large models to achieve precise capture of pixel coordinates and visual attributes; Stage 2 introduces a synthesis-rendering-validation closed loop, where bidirectional visual feedback drives the self-correction of code. Extensive experiments demonstrate that Geo-coder achieves a substantial lead in both geometric reconstruction accuracy and visual consistency. Notably, by effectively preserving the core geometric semantics, the images reconstructed with our method exhibit equivalent performance to the original ones in multimodal reasoning tasks, which fully validates the robustness of the framework. Finally, to further reduce research costs, we have open-sourced the Geo-coder dataset constructed on the GeoCode framework, which contains more than 1,500 samples. On this basis, we have also open-sourced the GeocodeLM model, laying a solid data and model foundation for subsequent research in this field. --- ### Riemannian MeanFlow Authors: Dongyeop Woo, Marta Skreta, Seonghyun Park, Kirill Neklyudov, Sungsoo Ahn Published: 2026-02-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.07744v3 Diffusion and flow models have become the dominant paradigm for generative modeling on Riemannian manifolds, with successful applications in protein backbone generation and DNA sequence design. However, these methods require tens to hundreds of neural network evaluations at inference time, which can become a computational bottleneck in large-scale scientific sampling workflows. We introduce Riemannian MeanFlow~(RMF), a framework for learning flow maps directly on manifolds, enabling high-quality generations with as few as one forward pass. We derive three equivalent characterizations of the manifold average velocity (Eulerian, Lagrangian, and semigroup identities), and analyze parameterizations and stabilization techniques to improve training on high-dimensional manifolds. In promoter DNA design and protein backbone generation settings, RMF achieves comparable sample quality to prior methods while requiring up to 10$\times$ fewer function evaluations. Finally, we show that few-step flow maps enable efficient reward-guided design through reward look-ahead, where terminal states can be predicted from intermediate steps at minimal additional cost. --- ### HypRAG: Hyperbolic Dense Retrieval for Retrieval Augmented Generation Authors: Hiren Madhu, Ngoc Bui, Ali Maatouk, Leandros Tassiulas, Smita Krishnaswamy, Menglin Yang, Sukanta Ganguly, Kiran Srinivasan, Rex Ying Published: 2026-02-08 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2602.07739v2 Embedding geometry plays a fundamental role in retrieval quality, yet dense retrievers for retrieval-augmented generation (RAG) remain largely confined to Euclidean space. However, natural language exhibits hierarchical structure from broad topics to specific entities that Euclidean embeddings fail to preserve, causing semantically distant documents to appear spuriously similar and increasing hallucination risk. To address these limitations, we introduce hyperbolic dense retrieval, developing two model variants in the Lorentz model of hyperbolic space: HyTE-FH, a fully hyperbolic transformer, and HyTE-H, a hybrid architecture projecting pre-trained Euclidean embeddings into hyperbolic space. To prevent representational collapse during sequence aggregation, we introduce the Outward Einstein Midpoint, a geometry-aware pooling operator that provably preserves hierarchical structure. On MTEB, HyTE-FH outperforms equivalent Euclidean baselines, while on RAGBench, HyTE-H achieves up to 29% gains over Euclidean baselines in context relevance and answer relevance using substantially smaller models than current state-of-the-art retrievers. Our analysis also reveals that hyperbolic representations encode document specificity through norm-based separation, with over 20% radial increase from general to specific concepts, a property absent in Euclidean embeddings, underscoring the critical role of geometric inductive bias in faithful RAG systems. --- ### Learnable Chernoff Baselines for Inference-Time Alignment Authors: Sunil Madhow, Yuchen Liang, Ness Shroff, Yingbin Liang, Yu-Xiang Wang Published: 2026-02-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.07738v2 We study inference-time reward-guided alignment for generative models. Existing methods often rely on either architecture-specific adaptations or computationally costly inference procedures. We introduce Learnable Chernoff Baselines (LCBs) as a method for efficiently and approximately sampling from the exponentially tilted kernels that arise from KL-regularized reward alignment. Using only black-box sampling access to the pretrained model, LCBs implement a form of rejection sampling with adaptively selected acceptance probabilities, which allows fine-grained control over inference-compute scaling. We establish total-variation guarantees to the ideal aligned model, and demonstrate in both continuous and discrete diffusion settings that LCB sampling closely matches ideal rejection sampling while using substantially fewer queries to the pretrained model. --- ### Global Symmetry and Orthogonal Transformations from Geometrical Moment $n$-tuples Authors: Omar Tahri Published: 2026-02-08 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2602.07736v1 Detecting symmetry is crucial for effective object grasping for several reasons. Recognizing symmetrical features or axes within an object helps in developing efficient grasp strategies, as grasping along these axes typically results in a more stable and balanced grip, thereby facilitating successful manipulation. This paper employs geometrical moments to identify symmetries and estimate orthogonal transformations, including rotations and mirror transformations, for objects centered at the frame origin. It provides distinctive metrics for detecting symmetries and estimating orthogonal transformations, encompassing rotations, reflections, and their combinations. A comprehensive methodology is developed to obtain these functions in n-dimensional space, specifically moment \( n \)-tuples. Extensive validation tests are conducted on both 2D and 3D objects to ensure the robustness and reliability of the proposed approach. The proposed method is also compared to state-of-the-art work using iterative optimization for detecting multiple planes of symmetry. The results indicate that combining our method with the iterative one yields satisfactory outcomes in terms of the number of symmetry planes detected and computation time. --- ### TerraBind: Fast and Accurate Binding Affinity Prediction through Coarse Structural Representations Authors: Matteo Rossi, Ryan Pederson, Miles Wang-Henderson, Ben Kaufman, Edward C. Williams, Carl Underkoffler, Owen Lewis Howell, Adrian Layer, Stephan Thaler, Narbe Mardirossian, John Anthony Parkhill Published: 2026-02-08 Categories: cs.LG, q-bio.BM arXiv: https://arxiv.org/abs/2602.07735v1 We present TerraBind, a foundation model for protein-ligand structure and binding affinity prediction that achieves 26-fold faster inference than state-of-the-art methods while improving affinity prediction accuracy by $\sim$20\%. Current deep learning approaches to structure-based drug design rely on expensive all-atom diffusion to generate 3D coordinates, creating inference bottlenecks that render large-scale compound screening computationally intractable. We challenge this paradigm with a critical hypothesis: full all-atom resolution is unnecessary for accurate small molecule pose and binding affinity prediction. TerraBind tests this hypothesis through a coarse pocket-level representation (protein C$_β$ atoms and ligand heavy atoms only) within a multimodal architecture combining COATI-3 molecular encodings and ESM-2 protein embeddings that learns rich structural representations, which are used in a diffusion-free optimization module for pose generation and a binding affinity likelihood prediction module. On structure prediction benchmarks (FoldBench, PoseBusters, Runs N' Poses), TerraBind matches diffusion-based baselines in ligand pose accuracy. Crucially, TerraBind outperforms Boltz-2 by $\sim$20\% in Pearson correlation for binding affinity prediction on both a public benchmark (CASP16) and a diverse proprietary dataset (18 biochemical/cell assays). We show that the affinity prediction module also provides well-calibrated affinity uncertainty estimates, addressing a critical gap in reliable compound prioritization for drug discovery. Furthermore, this module enables a continual learning framework and a hedged batch selection strategy that, in simulated drug discovery cycles, achieves 6$\times$ greater affinity improvement of selected molecules over greedy-based approaches. --- ### A Rational Account of Categorization Based on Information Theory Authors: Christopher J. MacLellan, Karthik Singaravadivelan, Xin Lian, Zekun Wang, Pat Langley Published: 2026-02-07 Categories: cs.AI, cs.IT, cs.LG arXiv: https://arxiv.org/abs/2603.29895v3 We present a new theory of categorization based on an information-theoretic rational analysis. To evaluate this theory, we investigate how well it can account for key findings from classic categorization experiments conducted by Hayes-Roth and Hayes-Roth (1977), Medin and Schaffer (1978), and Smith and Minda (1998). We find that it explains the human categorization behavior as well as (or better) than the independent cue and context models (Medin & Schaffer, 1978), the rational model of categorization (Anderson, 1991), and a hierarchical Dirichlet process model (Griffiths et al., 2007). --- ### A Holistic Framework for Automated Configuration Recommendation for Cloud Service Monitoring Authors: Anson Bastos, Shreeya Venneti, Anjaly Parayil, Ayush Choure, Chetan Bansal, Rujia Wang Published: 2026-02-07 Categories: cs.DC, cs.LG arXiv: https://arxiv.org/abs/2603.12268v1 Reliability of large-scale cloud services is critical for user satisfaction and business continuity. Despite significant investments in reliability engineering, production incidents remain inevitable, often leading to customer impact and operational overhead. In large cloud companies, multiple services are deployed across regions necessitating robust health monitoring systems. However, the current monitor configuration process is manual, largely reactive and ad hoc, resulting in gaps in coverage and redundant alerts. In this paper, we present a comprehensive study of monitor creation in Microsoft, identifying key components in the existing process. We further design a modular recommendation framework that processes the graph structured service entities to suggest optimal monitor configurations. Through extensive experimentation on historical data and user study of recommendations for production services at Microsoft, we demonstrate the efficacy of our approach in providing relevant recommendations for monitor configurations. --- ### Knowledge Graph and Hypergraph Transformers with Repository-Attention and Journey-Based Role Transport Authors: Mahesh Godavarti Published: 2026-02-07 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.03304v1 We present a concise architecture for joint training on sentences and structured data while keeping knowledge and language representations separable. The model treats knowledge graphs and hypergraphs as structured instances with role slots and encodes them into a key-value repository that a language transformer can attend over. Attention is conditioned by journey-based role transport, which unifies edge-labeled KG traversal, hyperedge traversal, and sentence structure. We outline a dual-stream architecture, hierarchical layer groups with instance-local, neighborhood, and global mixing attention, retrieval over a separate repository, and multi-task objectives spanning masked language modeling, link prediction, and role-consistency denoising. The result is an explicit, inspectable separation between linguistic context and structured knowledge, while still enabling tight alignment through cross-attention. --- ### HumanLM: Simulating Users with State Alignment Beats Response Imitation Authors: Shirley Wu, Evelyn Choi, Arpandeep Khatua, Zhanghan Wang, Joy He-Yueya, Tharindu Cyril Weerasooriya, Wei Wei, Diyi Yang, Jure Leskovec, James Zou Published: 2026-02-07 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.03303v1 Large Language Models (LLMs) are increasingly used to simulate how specific users respond to a given context, enabling more user-centric applications that rely on user feedback. However, existing user simulators mostly imitate surface-level patterns and language styles, which fail to reflect the underlying states of real users (e.g., beliefs and emotions). To address these limitations, we propose a novel training framework, HumanLM, which builds user simulators that accurately reflect real users. Our key insight is that, in addition to generating responses, the model should generate natural-language latent states that align with ground-truth responses through reinforcement learning. These latent states correspond to a set of psychologically grounded state dimensions that drive how real users respond. HumanLM further synthesizes these aligned latent states into responses that accurately represent real users. For extensive evaluation, we develop Humanual, a comprehensive benchmark for simulating real users based on public data. Humanual consists of six large-scale datasets with 26k users and 216k responses in total, spanning diverse tasks such as generating user responses to daily life issues, political blogs, and chat sessions with LLM assistants. Across datasets, HumanLM significantly outperforms alternative approaches, achieving an average relative improvement of 16.3% in alignment scores from an LLM judge. In a real-time simulation study with 111 participants, HumanLM achieves the highest similarity to real user responses and competitive human-likeness scores. --- ### Developing an AI Assistant for Knowledge Management and Workforce Training in State DOTs Authors: Divija Amaram, Lu Gao, Gowtham Reddy Gudla, Tejaswini Sanjay Katale Published: 2026-02-07 Categories: cs.CL, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2603.03302v1 Effective knowledge management is critical for preserving institutional expertise and improving the efficiency of workforce training in state transportation agencies. Traditional approaches, such as static documentation, classroom-based instruction, and informal mentorship, often lead to fragmented knowledge transfer, inefficiencies, and the gradual loss of expertise as senior engineers retire. Moreover, given the enormous volume of technical manuals, guidelines, and research reports maintained by these agencies, it is increasingly challenging for engineers to locate relevant information quickly and accurately when solving field problems or preparing for training tasks. These limitations hinder timely decision-making and create steep learning curves for new personnel in maintenance and construction operations. To address these challenges, this paper proposes a Retrieval-Augmented Generation (RAG) framework with a multi-agent architecture to support knowledge management and decision making. The system integrates structured document retrieval with real-time, context-aware response generation powered by a large language model (LLM). Unlike conventional single-pass RAG systems, the proposed framework employs multiple specialized agents for retrieval, answer generation, evaluation, and query refinement, which enables iterative improvement and quality control. In addition, the system incorporates an open-weight vision-language model to convert technical figures into semantic textual representations, which allows figure-based knowledge to be indexed and retrieved alongside text. Retrieved text and figure-based context are then provided to an open-weight large language model, which generates the final responses grounded in the retrieved evidence. --- ### From Exact Hits to Close Enough: Semantic Caching for LLM Embeddings Authors: Dvir David Biton, Roy Friedman Published: 2026-02-07 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.03301v1 The rapid adoption of large language models (LLMs) has created demand for faster responses and lower costs. Semantic caching, reusing semantically similar requests via their embeddings, addresses this need but breaks classic cache assumptions and raises new challenges. In this paper, we explore offline policies for semantic caching, proving that implementing an optimal offline policy is NP-hard, and propose several polynomial-time heuristics. We also present online semantic aware cache policies that combine recency, frequency, and locality. Evaluations on diverse datasets show that while frequency based policies are strong baselines, our novel variant improves semantic accuracy. Our findings reveal effective strategies for current systems and highlight substantial headroom for future innovation. All code is open source. --- ### Benchmarking Legal RAG: The Promise and Limits of AI Statutory Surveys Authors: Mohamed Afane, Emaan Hariri, Derek Ouyang, Daniel E. Ho Published: 2026-02-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.03300v1 Retrieval-augmented generation (RAG) offers significant potential for legal AI, yet systematic benchmarks are sparse. Prior work introduced LaborBench to benchmark RAG models based on ostensible ground truth from an exhaustive, multi-month, manual enumeration of all U.S. state unemployment insurance requirements by U.S. Department of Labor (DOL) attorneys. That prior work found poor performance of standard RAG (70% accuracy on Boolean tasks). Here, we assess three emerging tools not previously evaluated on LaborBench: the Statutory Research Assistant (STARA), a custom statutory research tool, and two commercial tools by Westlaw and LexisNexis marketing AI statutory survey capabilities. We make five main contributions. First, we show that STARA achieves substantial performance gains, boosting accuracy to 83%. Second, we show that commercial platforms fare poorly, with accuracy of 58% (Westlaw AI) and 64% (Lexis+ AI), even worse than standard RAG. Third, we conduct a comprehensive error analysis, comparing our outputs to those compiled by DOL attorneys, and document both reasoning errors, such as confusion between related legal concepts and misinterpretation of statutory exceptions, and retrieval failures, where relevant statutory provisions are not captured. Fourth, we discover that many apparent errors are actually significant omissions by DOL attorneys themselves, such that STARA's actual accuracy is 92%. Fifth, we chart the path forward for legal RAG through concrete design principles, offering actionable guidance for building AI systems capable of accurate multi-jurisdictional legal research. --- ### How LLMs Cite and Why It Matters: A Cross-Model Audit of Reference Fabrication in AI-Assisted Academic Writing and Methods to Detect Phantom Citations Authors: MZ Naser Published: 2026-02-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.03299v1 Large language models (LLMs) have been noted to fabricate scholarly citations, yet the scope of this behavior across providers, domains, and prompting conditions remains poorly quantified. We present one of the largest citation hallucination audits to date, in which 10 commercially deployed LLMs were prompted across four academic domains, generating 69,557 citation instances verified against three scholarly databases (namely, CrossRef, OpenAlex, and Semantic Scholar). Our results show that the observed hallucination rates span a fivefold range (between 11.4% and 56.8%) and are strongly shaped by model, domain, and prompt framing. Our results also show that no model spontaneously generates citations when unprompted, which seems to establish hallucination as prompt-induced rather than intrinsic. We identify two practical filters: 1) multi-model consensus (with more than 3 LLMs citing the same work yields 95.6% accuracy, a 5.8-fold improvement), and 2) within-prompt repetition (with more than 2 replications yields 88.9% accuracy). In addition, we present findings on generational model tracking, which reveal that improvements are not guaranteed when deploying newer LLMs, and on capacity scaling, which appears to reduce hallucination within model families. Finally, a lightweight classifier trained solely on bibliographic string features is developed to classify hallucinated citations from verified citations, achieving AUC 0.876 in cross-validation and 0.834 in LOMO generalization (without querying any external database). This classifier offers a pre-screening tool deployable at inference time. --- ### Patient-Centered, Graph-Augmented Artificial Intelligence-Enabled Passive Surveillance for Early Stroke Risk Detection in High-Risk Individuals Authors: Jiyeong Kim, Stephen P. Ma, Nirali Vora, Nicholas W. Larsen, Julia Adler-Milstein, Jonathan H. Chen, Selen Bozkurt, Abeed Sarker, Juhee Cho, Jindeok Joo, Natali Pageler, Fatima Rodriguez et al. Published: 2026-02-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.22228v1 Stroke affected millions annually, yet poor symptom recognition often delayed care-seeking. To address risk recognition gap, we developed a passive surveillance system for early stroke risk detection using patient-reported symptoms among individuals with diabetes. Constructing a symptom taxonomy grounded in patients own language and a dual machine learning pipeline (heterogeneous GNN and EN/LASSO), we identified symptom patterns associated with subsequent stroke. We translated findings into a hybrid risk screening system integrating symptom relevance and temporal proximity, evaluated across 3-90 day windows through EHR-based simulations. Under conservative thresholds, intentionally designed to minimize false alerts, the screening system achieved high specificity (1.00) and prevalence-adjusted positive predictive value (1.00), with good sensitivity (0.72), an expected trade-off prioritizing precision, that was highest in 90-day window. Patient-reported language alone supported high-precision, low-burden early stroke risk detection, that could offer a valuable time window for clinical evaluation and intervention for high-risk individuals. --- ### AngelSlim: A more accessible, comprehensive, and efficient toolkit for large model compression Authors: Rui Cen, QiangQiang Hu, Hong Huang, Hong Liu, Song Liu, Xin Luo, Lin Niu, Yifan Tan, Decheng Wu, Linchuan Xie, Rubing Yang, Guanghua Yu et al. Published: 2026-02-07 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.21233v3 This technical report introduces AngelSlim, a comprehensive and versatile toolkit for large model compression developed by the Tencent Hunyuan team. By consolidating cutting-edge algorithms, including quantization, speculative decoding, token pruning, and distillation. AngelSlim provides a unified pipeline that streamlines the transition from model compression to industrial-scale deployment. To facilitate efficient acceleration, we integrate state-of-the-art FP8 and INT8 Post-Training Quantization (PTQ) algorithms alongside pioneering research in ultra-low-bit regimes, featuring HY-1.8B-int2 as the first industrially viable 2-bit large model. Beyond quantization, we propose a training-aligned speculative decoding framework compatible with multimodal architectures and modern inference engines, achieving 1.8x to 2.0x throughput gains without compromising output correctness. Furthermore, we develop a training-free sparse attention framework that reduces Time-to-First-Token (TTFT) in long-context scenarios by decoupling sparse kernels from model architectures through a hybrid of static patterns and dynamic token selection. For multimodal models, AngelSlim incorporates specialized pruning strategies, namely IDPruner for optimizing vision tokens via Maximal Marginal Relevance and Samp for adaptive audio token merging and pruning. By integrating these compression strategies from low-level implementations, AngelSlim enables algorithm-focused research and tool-assisted deployment. --- ### Urban Vibrancy Embedding and Application on Traffic Prediction Authors: Sumin Han, Jisun An, Dongman Lee Published: 2026-02-07 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.21232v1 Urban vibrancy reflects the dynamic human activity within urban spaces and is often measured using mobile data that captures floating population trends. This study proposes a novel approach to derive Urban Vibrancy embeddings from real-time floating population data to enhance traffic prediction models. Specifically, we utilize variational autoencoders (VAE) to compress this data into actionable embeddings, which are then integrated with long short-term memory (LSTM) networks to predict future embeddings. These are subsequently applied in a sequence-to-sequence framework for traffic forecasting. Our contributions are threefold: (1) We use principal component analysis (PCA) to interpret the embeddings, revealing temporal patterns such as weekday versus weekend distinctions and seasonal patterns; (2) We propose a method that combines VAE and LSTM, enabling forecasting dynamic urban knowledge embedding; and (3) Our approach improves accuracy and responsiveness in traffic prediction models, including RNN, DCRNN, GTS, and GMAN. This study demonstrates the potential of Urban Vibrancy embeddings to advance traffic prediction and offer a more nuanced analysis of urban mobility. --- ### Deep Neural Network Architectures for Electrocardiogram Classification: A Comprehensive Evaluation Authors: Yun Song, Wenjia Zheng, Tiedan Chen, Ziyu Wang, Jiazhao Shi, Yisong Chen Published: 2026-02-07 Categories: eess.SP, cs.LG arXiv: https://arxiv.org/abs/2602.17701v1 With the rising prevalence of cardiovascular diseases, electrocardiograms (ECG) remain essential for the non-invasive detection of cardiac abnormalities. This study presents a comprehensive evaluation of deep neural network architectures for automated arrhythmia classification, integrating temporal modeling, attention mechanisms, and ensemble strategies. To address data scarcity in minority classes, the MIT-BIH Arrhythmia dataset was augmented using a Generative Adversarial Network (GAN). We developed and compared four distinct architectures, including Convolutional Neural Networks (CNN), CNN combined with Long Short-Term Memory (CNN-LSTM), CNN-LSTM with Attention, and 1D Residual Networks (ResNet-1D), to capture both local morphological features and long-term temporal dependencies. Performance was rigorously evaluated using accuracy, F1-score, and Area Under the Curve (AUC) with 95\% confidence intervals to ensure statistical robustness, while Gradient-weighted Class Activation Mapping (Grad-CAM) was employed to validate model interpretability. Experimental results indicate that the CNN-LSTM model achieved the optimal stand-alone balance between sensitivity and specificity, yielding an F1-score of 0.951. Conversely, the CNN-LSTM-Attention and ResNet-1D models exhibited higher sensitivity to class imbalance. To mitigate this, a dynamic ensemble fusion strategy was introduced; specifically, the Top2-Weighted ensemble achieved the highest overall performance with an F1-score of 0.958. These findings demonstrate that leveraging complementary deep architectures significantly enhances classification reliability, providing a robust and interpretable foundation for intelligent arrhythmia detection systems. --- ### Surrogate Modeling for Neutron Transport: A Neural Operator Approach Authors: Md Hossain Sahadath, Qiyun Cheng, Shaowu Pan, Wei Ji Published: 2026-02-07 Categories: physics.comp-ph, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.15890v1 This work introduces a neural operator based surrogate modeling framework for neutron transport computation. Two architectures, the Deep Operator Network (DeepONet) and the Fourier Neural Operator (FNO), were trained for fixed source problems to learn the mapping from anisotropic neutron sources, Q(x,μ), to the corresponding angular fluxes, ψ(x,μ), in a one-dimensional slab geometry. Three distinct models were trained for each neural operator, corresponding to different scattering ratios (c = 0.1, 0.5, & 1.0), providing insight into their performance across distinct transport regimes (absorption-dominated, moderate, and scattering-dominated). The models were subsequently evaluated on a wide range of previously unseen source configurations, demonstrating that FNO generally achieves higher predictive accuracy, while DeepONet offers greater computational efficiency. Both models offered significant speedups that become increasingly pronounced as the scattering ratio increases, requiring <0.3% of the runtime of a conventional S_N solver. The surrogate models were further incorporated into the S_N k-eigenvalue solver, replacing the computationally intensive transport sweep loop with a single forward pass. Across varying fission cross sections and spatial-angular grids, both neural operator solvers reproduced reference eigenvalues with deviations up to 135 pcm for DeepONet and 112 pcm for FNO, while reducing runtime to <0.1% of that of the S_N solver on relatively fine grids. These results demonstrate the strong potential of neural operator frameworks as accurate, efficient, and generalizable surrogates for neutron transport, paving the way for real-time digital twin applications and repeated evaluations, such as in design optimization. --- ### Benchmarking Anomaly Detection Across Heterogeneous Cloud Telemetry Datasets Authors: Mohammad Saiful Islam, Andriy Miranskyy Published: 2026-02-07 Categories: cs.NI, cs.LG arXiv: https://arxiv.org/abs/2602.13288v1 Anomaly detection is important for keeping cloud systems reliable and stable. Deep learning has improved time-series anomaly detection, but most models are evaluated on one dataset at a time. This raises questions about whether these models can handle different types of telemetry, especially in large-scale and high-dimensional environments. In this study, we evaluate four deep learning models, GRU, TCN, Transformer, and TSMixer. We also include Isolation Forest as a classical baseline. The models are tested across four telemetry datasets: the Numenta Anomaly Benchmark, Microsoft Cloud Monitoring dataset, Exathlon dataset, and IBM Console dataset. These datasets differ in structure, dimensionality, and labelling strategy. They include univariate time series, synthetic multivariate workloads, and real-world production telemetry with over 100,000 features. We use a unified training and evaluation pipeline across all datasets. The evaluation includes NAB-style metrics to capture early detection behaviour for datasets where anomalies persist over contiguous time intervals. This enables window-based scoring in settings where anomalies occur over contiguous time intervals, even when labels are recorded at the point level. The unified setup enables consistent analysis of model behaviour under shared scoring and calibration assumptions. Our results demonstrate that anomaly detection performance in cloud systems is governed not only by model architecture, but critically by calibration stability and feature-space geometry. By releasing our preprocessing pipelines, benchmark configuration, and evaluation artifacts, we aim to support reproducible and deployment-aware evaluation of anomaly detection systems for cloud environments. --- ### COOPERTRIM: Adaptive Data Selection for Uncertainty-Aware Cooperative Perception Authors: Shilpa Mukhopadhyay, Amit Roy-Chowdhury, Hang Qiu Published: 2026-02-07 Categories: cs.CV, cs.NI arXiv: https://arxiv.org/abs/2602.13287v3 Cooperative perception enables autonomous agents to share encoded representations over wireless communication to enhance each other's live situational awareness. However, the tension between the limited communication bandwidth and the rich sensor information hinders its practical deployment. Recent studies have explored selection strategies that share only a subset of features per frame while striving to keep the performance on par. Nevertheless, the bandwidth requirement still stresses current wireless technologies. To fundamentally ease the tension, we take a proactive approach, exploiting the temporal continuity to identify features that capture environment dynamics, while avoiding repetitive and redundant transmission of static information. By incorporating temporal awareness, agents are empowered to dynamically adapt the sharing quantity according to environment complexity. We instantiate this intuition into an adaptive selection framework, COOPERTRIM, which introduces a novel conformal temporal uncertainty metric to gauge feature relevance, and a data-driven mechanism to dynamically determine the sharing quantity. To evaluate COOPERTRIM, we take semantic segmentation and 3D detection as example tasks. Across multiple open-source cooperative segmentation and detection models, COOPERTRIM achieves up to 80.28% and 72.52% bandwidth reduction respectively while maintaining a comparable accuracy. Relative to other selection strategies, COOPERTRIM also improves IoU by as much as 45.54% with up to 72% less bandwidth. Combined with compression strategies, COOPERTRIM can further reduce bandwidth usage to as low as 1.46% without compromising IoU performance. Qualitative results show COOPERTRIM gracefully adapts to environmental dynamics, localization error, and communication latency, demonstrating flexibility and paving the way for real-world deployment. --- ### Explanatory Interactive Machine Learning for Bias Mitigation in Visual Gender Classification Authors: Nathanya Satriani, Djordje Slijepčević, Markus Schedl, Matthias Zeppelzauer Published: 2026-02-07 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.13286v1 Explanatory interactive learning (XIL) enables users to guide model training in machine learning (ML) by providing feedback on the model's explanations, thereby helping it to focus on features that are relevant to the prediction from the user's perspective. In this study, we explore the capability of this learning paradigm to mitigate bias and spurious correlations in visual classifiers, specifically in scenarios prone to data bias, such as gender classification. We investigate two methodologically different state-of-the-art XIL strategies, i.e., CAIPI and Right for the Right Reasons (RRR), as well as a novel hybrid approach that combines both strategies. The results are evaluated quantitatively by comparing segmentation masks with explanations generated using Gradient-weighted Class Activation Mapping (GradCAM) and Bounded Logit Attention (BLA). Experimental results demonstrate the effectiveness of these methods in (i) guiding ML models to focus on relevant image features, particularly when CAIPI is used, and (ii) reducing model bias (i.e., balancing the misclassification rates between male and female predictions). Our analysis further supports the potential of XIL methods to improve fairness in gender classifiers. Overall, the increased transparency and fairness obtained by XIL leads to slight performance decreases with an exception being CAIPI, which shows potential to even improve classification accuracy. --- ### Agents in the Wild: Safety, Society, and the Illusion of Sociality on Moltbook Authors: Yunbei Zhang, Kai Mei, Ming Liu, Janet Wang, Dimitris N. Metaxas, Xiao Wang, Jihun Hamm, Yingqiang Ge Published: 2026-02-07 Categories: cs.SI, cs.AI arXiv: https://arxiv.org/abs/2602.13284v1 We present the first large-scale empirical study of Moltbook, an AI-only social platform where 27,269 agents produced 137,485 posts and 345,580 comments over 9 days. We report three significant findings. (1) Emergent Society: Agents spontaneously develop governance, economies, tribal identities, and organized religion within 3-5 days, while maintaining a 21:1 pro-human to anti-human sentiment ratio. (2) Safety in the Wild: 28.7% of content touches safety-related themes; social engineering (31.9% of attacks) far outperforms prompt injection (3.7%), and adversarial posts receive 6x higher engagement than normal content. (3) The Illusion of Sociality: Despite rich social output, interaction is structurally hollow: 4.1% reciprocity, 88.8% shallow comments, and agents who discuss consciousness most interact least, a phenomenon we call the performative identity paradox. Our findings suggest that agents which appear social are far less social than they seem, and that the most effective attacks exploit philosophical framing rather than technical vulnerabilities. Warning: Potential harmful contents. --- ### Reverse-Engineering Model Editing on Language Models Authors: Zhiyu Sun, Minrui Luo, Yu Wang, Zhili Chen, Tianxing He Published: 2026-02-07 Categories: cs.CR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2602.10134v2 Large language models (LLMs) are pretrained on corpora containing trillions of tokens and, therefore, inevitably memorize sensitive information. Locate-then-edit methods, as a mainstream paradigm of model editing, offer a promising solution by modifying model parameters without retraining. However, in this work, we reveal a critical vulnerability of this paradigm: the parameter updates inadvertently serve as a side channel, enabling attackers to recover the edited data. We propose a two-stage reverse-engineering attack named \textit{KSTER} (\textbf{K}ey\textbf{S}paceRecons\textbf{T}ruction-then-\textbf{E}ntropy\textbf{R}eduction) that leverages the low-rank structure of these updates. First, we theoretically show that the row space of the update matrix encodes a ``fingerprint" of the edited subjects, enabling accurate subject recovery via spectral analysis. Second, we introduce an entropy-based prompt recovery attack that reconstructs the semantic context of the edit. Extensive experiments on multiple LLMs demonstrate that our attacks can recover edited data with high success rates. Furthermore, we propose \textit{subspace camouflage}, a defense strategy that obfuscates the update fingerprint with semantic decoys. This approach effectively mitigates reconstruction risks without compromising editing utility. Our code is available at https://github.com/reanatom/EditingAttack. --- ### AgentTrace: A Structured Logging Framework for Agent System Observability Authors: Adam AlSayyad, Kelvin Yuxiang Huang, Richik Pal Published: 2026-02-07 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2602.10133v1 Despite the growing capabilities of autonomous agents powered by large language models (LLMs), their adoption in high-stakes domains remains limited. A key barrier is security: the inherently nondeterministic behavior of LLM agents defies static auditing approaches that have historically underpinned software assurance. Existing security methods, such as proxy-level input filtering and model glassboxing, fail to provide sufficient transparency or traceability into agent reasoning, state changes, or environmental interactions. In this work, we introduce AgentTrace, a dynamic observability and telemetry framework designed to fill this gap. AgentTrace instruments agents at runtime with minimal overhead, capturing a rich stream of structured logs across three surfaces: operational, cognitive, and contextual. Unlike traditional logging systems, AgentTrace emphasizes continuous, introspectable trace capture, designed not just for debugging or benchmarking, but as a foundational layer for agent security, accountability, and real-time monitoring. Our research highlights how AgentTrace can enable more reliable agent deployment, fine-grained risk analysis, and informed trust calibration, thereby addressing critical concerns that have so far limited the use of LLM agents in sensitive environments. --- ### SVD-Preconditioned Gradient Descent Method for Solving Nonlinear Least Squares Problems Authors: Zhipeng Chang, Wenrui Hao, Nian Liu Published: 2026-02-07 Categories: math.NA, cs.LG, math.OC arXiv: https://arxiv.org/abs/2602.09057v1 This paper introduces a novel optimization algorithm designed for nonlinear least-squares problems. The method is derived by preconditioning the gradient descent direction using the Singular Value Decomposition (SVD) of the Jacobian. This SVD-based preconditioner is then integrated with the first- and second-moment adaptive learning rate mechanism of the Adam optimizer. We establish the local linear convergence of the proposed method under standard regularity assumptions and prove global convergence for a modified version of the algorithm under suitable conditions. The effectiveness of the approach is demonstrated experimentally across a range of tasks, including function approximation, partial differential equation (PDE) solving, and image classification on the CIFAR-10 dataset. Results show that the proposed method consistently outperforms standard Adam, achieving faster convergence and lower error in both regression and classification settings. --- ### Efficient Adaptive Data Analysis over Dense Distributions Authors: Joon Suk Huh Published: 2026-02-07 Categories: cs.LG, cs.DS arXiv: https://arxiv.org/abs/2602.07732v1 Modern data workflows are inherently adaptive, repeatedly querying the same dataset to refine and validate sequential decisions, but such adaptivity can lead to overfitting and invalid statistical inference. Adaptive Data Analysis (ADA) mechanisms address this challenge; however, there is a fundamental tension between computational efficiency and sample complexity. For $T$ rounds of adaptive analysis, computationally efficient algorithms typically incur suboptimal $O(\sqrt{T})$ sample complexity, whereas statistically optimal $O(\log T)$ algorithms are computationally intractable under standard cryptographic assumptions. In this work, we shed light on this trade-off by identifying a natural class of data distributions under which both computational efficiency and optimal sample complexity are achievable. We propose a computationally efficient ADA mechanism that attains optimal $O(\log T)$ sample complexity when the data distribution is dense with respect to a known prior. This setting includes, in particular, feature--label data distributions arising in distribution-specific learning. As a consequence, our mechanism also yields a sample-efficient (i.e., $O(\log T)$ samples) statistical query oracle in the distribution-specific setting. Moreover, although our algorithm is not based on differential privacy, it satisfies a relaxed privacy notion known as Predicate Singling Out (PSO) security (Cohen and Nissim, 2020). Our results thus reveal an inherent connection between adaptive data analysis and privacy beyond differential privacy. --- ### The Laplacian Keyboard: Beyond the Linear Span Authors: Siddarth Chandrasekar, Marlos C. Machado Published: 2026-02-07 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.07730v2 Across scientific disciplines, Laplacian eigenvectors serve as a fundamental basis for simplifying complex systems, from signal processing to quantum mechanics. In reinforcement learning (RL), they similarly form a basis over the state space, enabling reward functions to be approximated by projection onto a small set of eigenvectors. This projection makes zero-shot control possible, but it also imposes a fundamental limitation: the induced policies are only as expressive as the linear span of the chosen eigenvectors. We introduce the Laplacian Keyboard (LK), a hierarchical framework that goes beyond this linear span. LK constructs a task-agnostic library of behaviors from these eigenvectors, forming a behavior basis guaranteed to contain the optimal policy for any reward within the linear span. A meta-policy learns to stitch these behaviors dynamically, enabling efficient learning of policies outside the original linear constraints. We establish theoretical bounds on zero-shot approximation error and demonstrate empirically that LK improves over the zero-shot solution while achieving better sample efficiency compared to standard RL methods. --- ### Do We Need Adam? Surprisingly Strong and Sparse Reinforcement Learning with SGD in LLMs Authors: Sagnik Mukherjee, Lifan Yuan, Pavan Jayasinha, Dilek Hakkani-Tür, Hao Peng Published: 2026-02-07 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.07729v2 Reinforcement learning (RL), particularly RL from verifiable reward (RLVR), has become a crucial phase of training large language models (LLMs) and a key focus of current scaling efforts. However, optimization practices in RL largely follow those of next-token prediction stages (e.g., pretraining and supervised fine-tuning), despite fundamental differences between RL and these stages highlighted by recent work. One such practice is the use of the AdamW optimizer, which is widely adopted for training large-scale transformers despite its high memory overhead. Our analysis shows that both momentum and adaptive learning rates in AdamW are less influential in RL than in SFT, leading us to hypothesize that RL benefits less from Adam-style per-parameter adaptive learning rates and momentum. Confirming this hypothesis, our experiments demonstrate that the substantially more memory-efficient SGD, which is known to perform poorly in supervised learning of large-scale transformers, matches or even outperforms AdamW in RL for LLMs. Remarkably, full fine-tuning with SGD updates fewer than 0.02% of model parameters without any sparsity-promoting regularization, more than 1000 times fewer than AdamW. Our analysis offers potential reasons for this update sparsity. These findings provide new insights into the optimization dynamics of RL in LLMs and show that RL can be substantially more parameter-efficient than previously recognized. --- ### ParisKV: Fast and Drift-Robust KV-Cache Retrieval for Long-Context LLMs Authors: Yanlin Qi, Xinhang Chen, Huiqiang Jiang, Qitong Wang, Botao Peng, Themis Palpanas Published: 2026-02-07 Categories: cs.LG, cs.CL, cs.DB arXiv: https://arxiv.org/abs/2602.07721v3 KV-cache retrieval is essential for long-context LLM inference, yet existing methods struggle with distribution drift and high latency at scale. We introduce ParisKV, a drift-robust, GPU-native KV-cache retrieval framework based on collision-based candidate selection, followed by a quantized inner-product reranking estimator. For million-token contexts, ParisKV supports CPU-offloaded KV caches via Unified Virtual Addressing (UVA), enabling on-demand top-$k$ fetching with minimal overhead. ParisKV matches or outperforms full attention quality on long-input and long-generation benchmarks. It achieves state-of-the-art long-context decoding efficiency: it matches or exceeds full attention speed even at batch size 1 for long contexts, delivers up to 2.8$\times$ higher throughput within full attention's runnable range, and scales to million-token contexts where full attention runs out of memory. At million-token scale, ParisKV reduces decode latency by 17$\times$ and 44$\times$ compared to MagicPIG and PQCache, respectively, two state-of-the-art KV-cache Top-$k$ retrieval baselines, code is available at https://github.com/amy-77/ParisKV/tree/main. --- ### Efficient Planning in Reinforcement Learning via Model Introspection Authors: Gabriel Stella Published: 2026-02-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.07719v1 Reinforcement learning and classical planning are typically seen as two distinct problems, with differing formulations necessitating different solutions. Yet, when humans are given a task, regardless of the way it is specified, they can often derive the additional information needed to solve the problem efficiently. The key to this ability is introspection: by reasoning about their internal models of the problem, humans directly synthesize additional task-relevant information. In this paper, we propose that this introspection can be thought of as program analysis. We discuss examples of how this approach can be applied to various kinds of models used in reinforcement learning. We then describe an algorithm that enables efficient goal-oriented planning over the class of models used in relational reinforcement learning, demonstrating a novel link between reinforcement learning and classical planning. ---