# Research Papers — 2026-02 · bundle page 147 of 210 > Full-text markdown of papers #7301–7350 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/147 [← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/146.md) [Next bundle →](https://aipod.dev/papers/archive/2026-02/page/148.md) ### ViHERMES: A Graph-Grounded Multihop Question Answering Benchmark and System for Vietnamese Healthcare Regulations Authors: Long S. T. Nguyen, Quan M. Bui, Tin T. Ngo, Quynh T. N. Vo, Dung N. H. Le, Tho T. Quan Published: 2026-02-07 Categories: cs.CL, cs.IR arXiv: https://arxiv.org/abs/2602.07361v1 Question Answering (QA) over regulatory documents is inherently challenging due to the need for multihop reasoning across legally interdependent texts, a requirement that is particularly pronounced in the healthcare domain where regulations are hierarchically structured and frequently revised through amendments and cross-references. Despite recent progress in retrieval-augmented and graph-based QA methods, systematic evaluation in this setting remains limited, especially for low-resource languages such as Vietnamese, due to the lack of benchmark datasets that explicitly support multihop reasoning over healthcare regulations. In this work, we introduce the Vietnamese Healthcare Regulations-Multihop Reasoning Dataset (ViHERMES), a benchmark designed for multihop QA over Vietnamese healthcare regulatory documents. ViHERMES consists of high-quality question-answer pairs that require reasoning across multiple regulations and capture diverse dependency patterns, including amendment tracing, cross-document comparison, and procedural synthesis. To construct the dataset, we propose a controlled multihop QA generation pipeline based on semantic clustering and graph-inspired data mining, followed by large language model-based generation with structured evidence and reasoning annotations. We further present a graph-aware retrieval framework that models formal legal relations at the level of legal units and supports principled context expansion for legally valid and coherent answers. Experimental results demonstrate that ViHERMES provides a challenging benchmark for evaluating multihop regulatory QA systems and that the proposed graph-aware approach consistently outperforms strong retrieval-based baselines. The ViHERMES dataset and system implementation are publicly available at https://github.com/ura-hcmut/ViHERMES. --- ### W&D:Scaling Parallel Tool Calling for Efficient Deep Research Agents Authors: Xiaoqiang Lin, Jun Hao Liew, Silvio Savarese, Junnan Li Published: 2026-02-07 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.07359v1 Deep research agents have emerged as powerful tools for automating complex intellectual tasks through multi-step reasoning and web-based information seeking. While recent efforts have successfully enhanced these agents by scaling depth through increasing the number of sequential thinking and tool calls, the potential of scaling width via parallel tool calling remains largely unexplored. In this work, we propose the Wide and Deep research agent, a framework designed to investigate the behavior and performance of agents when scaling not only depth but also width via parallel tool calling. Unlike existing approaches that rely on complex multi-agent orchestration to parallelize workloads, our method leverages intrinsic parallel tool calling to facilitate effective coordination within a single reasoning step. We demonstrate that scaling width significantly improves performance on deep research benchmarks while reducing the number of turns required to obtain correct answers. Furthermore, we analyze the factors driving these improvements through case studies and explore various tool call schedulers to optimize parallel tool calling strategy. Our findings suggest that optimizing the trade-off between width and depth is a critical pathway toward high-efficiency deep research agents. Notably, without context management or other tricks, we obtain 62.2% accuracy with GPT-5-Medium on BrowseComp, surpassing the original 54.9% reported by GPT-5-High. --- ### UTOPIA: Unlearnable Tabular Data via Decoupled Shortcut Embedding Authors: Jiaming He, Fuming Luo, Hongwei Li, Wenbo Jiang, Wenshu Fan, Zhenbo Shi, Xudong Jiang, Yi Yu Published: 2026-02-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.07358v2 Unlearnable examples (UE) have emerged as a practical mechanism to prevent unauthorized model training on private vision data, while extending this protection to tabular data is nontrivial. Tabular data in finance and healthcare is highly sensitive, yet existing UE methods transfer poorly because tabular features mix numerical and categorical constraints and exhibit saliency sparsity, with learning dominated by a few dimensions. Under a Spectral Dominance condition, we show certified unlearnability is feasible when the poison spectrum overwhelms the clean semantic spectrum. Guided by this, we propose Unlearnable Tabular Data via DecOuPled Shortcut EmbeddIng (UTOPIA), which exploits feature redundancy to decouple optimization into two channels: high saliency features for semantic obfuscation and low saliency redundant features for embedding a hyper correlated shortcut, yielding constraint-aware dominant shortcuts while preserving tabular validity. Extensive experiments across tabular datasets and models show UTOPIA drives unauthorized training toward near random performance, outperforming strong UE baselines and transferring well across architectures. --- ### Controllable Value Alignment in Large Language Models through Neuron-Level Editing Authors: Yonghui Yang, Yihui Wang, Junwei Li, Jilong Liu, Fengbin Zhu, Weibiao Huang, Le Wu, Richang Hong, Tat-Seng Chua Published: 2026-02-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.07356v2 Aligning large language models (LLMs) with human values has become increasingly important as their influence on human behavior and decision-making expands. However, existing steering-based alignment methods suffer from limited controllability: steering a target value often unintentionally activates other, non-target values. To characterize this limitation, we introduce value leakage, a diagnostic notion that captures the unintended activation of non-target values during value steering, along with a normalized leakage metric grounded in Schwartz's value theory. In light of this analysis, we propose NeVA, a neuron-level editing framework for controllable value alignment in LLMs. NeVA identifies sparse, value-relevant neurons and performs inference-time activation editing, enabling fine-grained control without parameter updates or retraining. Experiments show that NeVA achieves stronger target value alignment while incurring smaller performance degradation on general capability. Moreover, NeVA significantly reduces the average leakage, with residual effects largely confined to semantically related value classes. Overall, NeVA offers a more controllable and interpretable mechanism for value alignment. --- ### Optimizing Few-Step Generation with Adaptive Matching Distillation Authors: Lichen Bai, Zikai Zhou, Shitong Shao, Wenliang Zhong, Shuo Yang, Shuo Chen, Bojun Chen, Zeke Xie Published: 2026-02-07 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2602.07345v2 Distribution Matching Distillation (DMD) is a powerful acceleration paradigm, yet its stability is often compromised in Forbidden Zone, regions where the real teacher provides unreliable guidance while the fake teacher exerts insufficient repulsive force. In this work, we propose a unified optimization framework that reinterprets prior art as implicit strategies to avoid these corrupted regions. Based on this insight, we introduce Adaptive Matching Distillation (AMD), a self-correcting mechanism that utilizes reward proxies to explicitly detect and escape Forbidden Zones. AMD dynamically prioritizes corrective gradients via structural signal decomposition and introduces Repulsive Landscape Sharpening to enforce steep energy barriers against failure mode collapse. Extensive experiments across image and video generation tasks (e.g., SDXL, Wan2.1) and rigorous benchmarks (e.g., VBench, GenEval) demonstrate that AMD significantly enhances sample fidelity and training robustness. For instance, AMD improves the HPSv2 score on SDXL from 30.64 to 31.25, outperforming state-of-the-art baselines. These findings validate that explicitly rectifying optimization trajectories within Forbidden Zones is essential for pushing the performance ceiling of few-step generative models. --- ### Seeing Roads Through Words: A Language-Guided Framework for RGB-T Driving Scene Segmentation Authors: Ruturaj Reddy, Hrishav Bakul Barua, Junn Yong Loo, Thanh Thi Nguyen, Ganesh Krishnasamy Published: 2026-02-07 Categories: cs.CV, cs.AI, cs.LG, cs.RO arXiv: https://arxiv.org/abs/2602.07343v2 Robust semantic segmentation of road scenes under adverse illumination, lighting, and shadow conditions remain a core challenge for autonomous driving applications. RGB-Thermal fusion is a standard approach, yet existing methods apply static fusion strategies uniformly across all conditions, allowing modality-specific noise to propagate throughout the network. Hence, we propose CLARITY that dynamically adapts its fusion strategy to the detected scene condition. Guided by vision-language model (VLM) priors, the network learns to modulate each modality's contribution based on the illumination state while leveraging object embeddings for segmentation, rather than applying a fixed fusion policy. We further introduce two mechanisms - one which preserves valid dark-object semantics that prior noise-suppression methods incorrectly discard, and a hierarchical decoder that enforces structural consistency across scales to sharpen boundaries on thin objects. Experiments on the MFNet dataset demonstrate that CLARITY establishes a new state-of-the-art (SOTA), achieving 62.3% mIoU and 77.5% mAcc. --- ### SupChain-Bench: Benchmarking Large Language Models for Real-World Supply Chain Management Authors: Shengyue Guan, Yihao Liu, Lang Cao Published: 2026-02-07 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.07342v2 Large language models (LLMs) have shown promise in complex reasoning and tool-based decision making, motivating their application to real-world supply chain management. However, supply chain workflows require reliable long-horizon, multi-step orchestration grounded in domain-specific procedures, which remains challenging for current models. To systematically evaluate LLM performance in this setting, we introduce SupChain-Bench, a unified real-world benchmark that assesses both supply chain domain knowledge and long-horizon tool-based orchestration grounded in standard operating procedures (SOPs). Our experiments reveal substantial gaps in execution reliability across models. We further propose SupChain-ReAct, an SOP-free framework that autonomously synthesizes executable procedures for tool use, achieving the strongest and most consistent tool-calling performance. Our work establishes a principled benchmark for studying reliable long-horizon orchestration in real-world operational settings and highlights significant room for improvement in LLM-based supply chain agents. --- ### Scalable Dexterous Robot Learning with AR-based Remote Human-Robot Interactions Authors: Yicheng Yang, Ruijiao Li, Lifeng Wang, Shuai Zheng, Shunzheng Ma, Keyu Zhang, Tuoyu Sun, Chenyun Dai, Jie Ding, Zhuo Zou Published: 2026-02-07 Categories: cs.LG, cs.RO arXiv: https://arxiv.org/abs/2602.07341v2 This paper focuses on the scalable robot learning for manipulation in the dexterous robot arm-hand systems, where the remote human-robot interactions via augmented reality (AR) are established to collect the expert demonstration data for improving efficiency. In such a system, we present a novel method to address the general manipulation task problem. Specifically, the proposed method consists of two phases: i) In the first phase for pretraining, the policy is created in a behavior cloning (BC) manner, through leveraging the learning data from our AR-based remote human-robot interaction system; ii) In the second phase, a contrastive learning empowered reinforcement learning (RL) method is developed to obtain more efficient and robust policy than the BC, and thus a projection head is designed to accelerate the learning progress. An event-driven augmented reward is adopted for enhancing the safety. To validate the proposed method, both the physics simulations via PyBullet and real-world experiments are carried out. The results demonstrate that compared to the baselines, our method not only significantly speeds up the training process, but also achieves much better performance in terms of the success rate for fulfilling the manipulation tasks. By conducting the ablation study, it is confirmed that the proposed RL with contrastive learning overcomes policy collapse. Supplementary demonstrations are available at https://cyberyyc.github.io/. --- ### Revisiting Robustness for LLM Safety Alignment via Selective Geometry Control Authors: Yonghui Yang, Wenjian Tao, Jilong Liu, Xingyu Zhu, Junfeng Fang, Weibiao Huang, Le Wu, Richang Hong, Tat-Sent Chua Published: 2026-02-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.07340v2 Safety alignment of large language models remains brittle under domain shift and noisy preference supervision. Most existing robust alignment methods focus on uncertainty in alignment data, while overlooking optimization-induced fragility in preference-based objectives. In this work, we revisit robustness for LLM safety alignment from an optimization geometry perspective, and argue that robustness failures cannot be addressed by data-centric methods alone. We propose \textit{ShaPO}, a geometry-aware preference optimization framework that enforces worst-case alignment objectives via selective geometry control over alignment-critical parameter subspace. By avoiding uniform geometry constraints, ShaPO mitigates the over-regularization that can harm robustness under distribution shift. We instantiate ShaPO at two levels: token-level ShaPO stabilizes likelihood-based surrogate optimization, while reward-level ShaPO enforces reward-consistent optimization under noisy supervision. Across diverse safety benchmarks and noisy preference settings, ShaPO consistently improves safety robustness over popular preference optimization methods. Moreover, ShaPO composes cleanly with data-robust objectives, yielding additional gains and empirically supporting the proposed optimization-geometry perspective. The code is available at https://github.com/liujilong0116/ShaPO. --- ### RAPiD: Reward-Guided Consistency Distillation of Diffusion Planners for Real-Time Autonomous Driving Authors: Ruturaj Reddy, Hrishav Bakul Barua, Junn Yong Loo, Thanh Thi Nguyen, Ganesh Krishnasamy Published: 2026-02-07 Categories: cs.AI, cs.LG, cs.RO arXiv: https://arxiv.org/abs/2602.07339v2 Diffusion-based trajectory planners can model multi-modal driving behavior, but their iterative denoising process introduces a latency bottleneck for real-time closed-loop deployment. We present RAPiD, a reward-guided consistency distillation framework that distills a pretrained DiffusionPlanner into a few-step consistency student while retaining multi-modal trajectory generation. The student is trained using deterministic teacher denoising steps from the frozen diffusion planner, together with a low-noise data anchor that keeps generated trajectories grounded in expert demonstrations. To make distillation safety-aware, we train an Implicit Q-Learning critic on a balanced mixture of ground-truth log-replay and DiffusionPlanner rollout trajectories, each scored using a modified PDM-style reward, providing trajectory-level supervision beyond conventional imitation learning. During deployment, the 2-step student generates K trajectories, and the trained critic performs best-of-K trajectory selection conditioned on the latent state. On nuPlan, RAPiD maintains comparable performance to the diffusion teacher on non-reactive closed-loop splits and remains competitive on reactive splits, while reducing complete-pipeline inference latency from 100.91 ms to 18.41 ms, corresponding to a 5.5x speedup. On interPlan, RAPiD achieves the highest aggregate score among learning-based methods, demonstrating competitive generalization in interactive long-tail scenarios. These results show that reward-guided consistency distillation can convert a pretrained diffusion planner into a few-step closed-loop planner that substantially reduces inference cost while preserving safety-oriented trajectory selection. The official website of this work is: https://github.com/ruturajreddy/RAPiD --- ### Intent Mismatch Causes LLMs to Get Lost in Multi-Turn Conversation Authors: Geng Liu, Fei Zhu, Rong Feng, Changyi Ma, Shiqi Wang, Gaofeng Meng Published: 2026-02-07 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.07338v1 Multi-turn conversation has emerged as a predominant interaction paradigm for Large Language Models (LLMs). Users often employ follow-up questions to refine their intent, expecting LLMs to adapt dynamically. However, recent research reveals that LLMs suffer a substantial performance drop in multi-turn settings compared to single-turn interactions with fully specified instructions, a phenomenon termed ``Lost in Conversation'' (LiC). While this prior work attributes LiC to model unreliability, we argue that the root cause lies in an intent alignment gap rather than intrinsic capability deficits. In this paper, we first demonstrate that LiC is not a failure of model capability but rather a breakdown in interaction between users and LLMs. We theoretically show that scaling model size or improving training alone cannot resolve this gap, as it arises from structural ambiguity in conversational context rather than representational limitations. To address this, we propose to decouple intent understanding from task execution through a Mediator-Assistant architecture. By utilizing an experience-driven Mediator to explicate user inputs into explicit, well-structured instructions based on historical interaction patterns, our approach effectively bridges the gap between vague user intent and model interpretation. Experimental results demonstrate that this method significantly mitigates performance degradation in multi-turn conversations across diverse LLMs. --- ### High Fidelity Textual User Representation over Heterogeneous Sources via Reinforcement Learning Authors: Rajat Arora, Ye Tao, Jianqiang Shen, Ping Liu, Muchen Wu, Qianqi Shen, Benjamin Le, Fedor Borisyuk, Jingwei Wu, Wenjing Zhang Published: 2026-02-07 Categories: cs.IR, cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2602.07333v1 Effective personalization on large-scale job platforms requires modeling members based on heterogeneous textual sources, including profiles, professional data, and search activity logs. As recommender systems increasingly adopt Large Language Models (LLMs), creating unified, interpretable, and concise representations from heterogeneous sources becomes critical, especially for latency-sensitive online environments. In this work, we propose a novel Reinforcement Learning (RL) framework to synthesize a unified textual representation for each member. Our approach leverages implicit user engagement signals (e.g., clicks, applies) as the primary reward to distill salient information. Additionally, the framework is complemented by rule-based rewards that enforce formatting and length constraints. Extensive offline experiments across multiple LinkedIn products, one of the world's largest job platforms, demonstrate significant improvements in key downstream business metrics. This work provides a practical, labeling-free, and scalable solution for constructing interpretable user representations that are directly compatible with LLM-based systems. --- ### Action-to-Action Flow Matching Authors: Jindou Jia, Gen Li, Xiangyu Chen, Tuo An, Yuxuan Hu, Jingliang Li, Xinying Guo, Jianfei Yang Published: 2026-02-07 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2602.07322v2 Diffusion-based policies have recently achieved remarkable success in robotics by formulating action prediction as a conditional denoising process. However, the standard practice of sampling from random Gaussian noise often requires multiple iterative steps to produce clean actions, leading to high inference latency that incurs a major bottleneck for real-time control. In this paper, we challenge the necessity of uninformed noise sampling and propose Action-to-Action flow matching (A2A), a novel policy paradigm that shifts from random sampling to initialization informed by the previous proprioceptive action. Unlike existing methods that treat proprioceptive action feedback as static conditions, A2A leverages historical proprioceptive sequences, embedding them into a high-dimensional latent space as the starting point for action generation. This design bypasses costly iterative denoising while effectively capturing the robot's physical dynamics and temporal continuity. Extensive experiments demonstrate that A2A exhibits high training efficiency, fast inference speed, and improved generalization. Notably, A2A enables high-quality action generation in as few as a single inference step, and exhibits superior robustness to visual perturbations and enhanced generalization to unseen configurations. Lastly, we also extend A2A to video generation, demonstrating its broader versatility in temporal modeling. Project site: https://lorenzo-0-0.github.io/A2A_Flow_Matching. --- ### Incorruptible Neural Networks: Training Models that can Generalize to Large Internal Perturbations Authors: Philip Jacobson, Ben Feinberg, Suhas Kumar, Sapan Agarwal, T. Patrick Xiao, Christopher Bennett Published: 2026-02-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.07320v1 Flat regions of the neural network loss landscape have long been hypothesized to correlate with better generalization properties. A closely related but distinct problem is training models that are robust to internal perturbations to their weights, which may be an important need for future low-power hardware platforms. In this paper, we explore the usage of two methods, sharpness-aware minimization (SAM) and random-weight perturbation (RWP), to find minima robust to a variety of random corruptions to weights. We consider the problem from two angles: generalization (how do we reduce the noise-robust generalization gap) and optimization (how do we maximize performance from optimizers when subject to strong perturbations). First, we establish, both theoretically and empirically, that an over-regularized RWP training objective is optimal for noise-robust generalization. For small-magnitude noise, we find that SAM's adversarial objective further improves performance over any RWP configuration, but performs poorly for large-magnitude noise. We link the cause of this to a vanishing-gradient effect, caused by unevenness in the loss landscape, affecting both SAM and RWP. Lastly, we demonstrate that dynamically adjusting the perturbation strength to match the evolution of the loss landscape improves optimizing for these perturbed objectives. --- ### Beyond Accuracy: Risk-Sensitive Evaluation of Hallucinated Medical Advice Authors: Savan Doshi Published: 2026-02-07 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.07319v2 Large language models are increasingly being used in patient-facing medical question answering, where hallucinated outputs can vary widely in potential harm. However, existing hallucination standards and evaluation metrics focus primarily on factual correctness, treating all errors as equally severe. This obscures clinically relevant failure modes, particularly when models generate unsupported but actionable medical language. We propose a risk-sensitive evaluation framework that quantifies hallucinations through the presence of risk-bearing language, including treatment directives, contraindications, urgency cues, and mentions of high-risk medications. Rather than assessing clinical correctness, our approach evaluates the potential impact of hallucinated content if acted upon. We further combine risk scoring with a relevance measure to identify high-risk, low-grounding failures. We apply this framework to three instruction-tuned language models using controlled patient-facing prompts designed as safety stress tests. Our results show that models with similar surface-level behavior exhibit substantially different risk profiles and that standard evaluation metrics fail to capture these distinctions. These findings highlight the importance of incorporating risk sensitivity into hallucination evaluation and suggest that evaluation validity is critically dependent on task and prompt design. --- ### LUCID-SAE: Learning Unified Vision-Language Sparse Codes for Interpretable Concept Discovery Authors: Difei Gu, Yunhe Gao, Gerasimos Chatzoudis, Zihan Dong, Guoning Zhang, Bangwei Guo, Yang Zhou, Mu Zhou, Dimitris Metaxas Published: 2026-02-07 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.07311v1 Sparse autoencoders (SAEs) offer a natural path toward comparable explanations across different representation spaces. However, current SAEs are trained per modality, producing dictionaries whose features are not directly understandable and whose explanations do not transfer across domains. In this study, we introduce LUCID (Learning Unified vision-language sparse Codes for Interpretable concept Discovery), a unified vision-language sparse autoencoder that learns a shared latent dictionary for image patch and text token representations, while reserving private capacity for modality-specific details. We achieve feature alignment by coupling the shared codes with a learned optimal transport matching objective without the need of labeling. LUCID yields interpretable shared features that support patch-level grounding, establish cross-modal neuron correspondence, and enhance robustness against the concept clustering problem in similarity-based evaluation. Leveraging the alignment properties, we develop an automated dictionary interpretation pipeline based on term clustering without manual observations. Our analysis reveals that LUCID's shared features capture diverse semantic categories beyond objects, including actions, attributes, and abstract concepts, demonstrating a comprehensive approach to interpretable multimodal representations. --- ### Optimization of Precipitate Segmentation Through Linear Genetic Programming of Image Processing Authors: Kyle Williams, Andrew Seltzman Published: 2026-02-07 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2602.07310v1 Current analysis of additive manufactured niobium-based copper alloys relies on hand annotation due to varying contrast, noise, and image artifacts present in micrographs, slowing iteration speed in alloy development. We present a filtering and segmentation algorithm for detecting precipitates in FIB cross-section micrographs, optimized using linear genetic programming (LGP), which accounts for the various artifacts. To this end, the optimization environment uses a domain-specific language for image processing to iterate on solutions. Programs in this language are a list of image-filtering blocks with tunable parameters that sequentially process an input image, allowing for reliable generation and mutation by a genetic algorithm. Our environment produces optimized human-interpretable MATLAB code representing an image filtering pipeline. Under ideal conditions--a population size of 60 and a maximum program length of 5 blocks--our system was able to find a near-human accuracy solution with an average evaluation error of 1.8% when comparing segmentations pixel-by-pixel to a human baseline using an XOR error evaluation. Our automation work enabled faster iteration cycles and furthered exploration of the material composition and processing space: our optimized pipeline algorithm processes a 3.6 megapixel image in about 2 seconds on average. This ultimately enables convergence on strong, low-activation, precipitation hardened copper alloys for additive manufactured fusion reactor parts. --- ### Semantic Search At LinkedIn Authors: Fedor Borisyuk, Sriram Vasudevan, Muchen Wu, Guoyao Li, Benjamin Le, Shaobo Zhang, Qianqi Kay Shen, Yuchin Juan, Kayhan Behdin, Liming Dong, Kaixu Yang, Shusen Jing et al. Published: 2026-02-07 Categories: cs.IR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.07309v1 Semantic search with large language models (LLMs) enables retrieval by meaning rather than keyword overlap, but scaling it requires major inference efficiency advances. We present LinkedIn's LLM-based semantic search framework for AI Job Search and AI People Search, combining an LLM relevance judge, embedding-based retrieval, and a compact Small Language Model trained via multi-teacher distillation to jointly optimize relevance and engagement. A prefill-oriented inference architecture co-designed with model pruning, context compression, and text-embedding hybrid interactions boosts ranking throughput by over 75x under a fixed latency constraint while preserving near-teacher-level NDCG, enabling one of the first production LLM-based ranking systems with efficiency comparable to traditional approaches and delivering significant gains in quality and user engagement. --- ### Adaptive Scaffolding for Cognitive Engagement in an Intelligent Tutoring System Authors: Sutapa Dey Tithi, Nazia Alam, Tahreem Yasir, Yang Shi, Xiaoyi Tian, Min Chi, Tiffany Barnes Published: 2026-02-07 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.07308v1 The ICAP framework defines four cognitive engagement levels: Passive, Active, Constructive, and Interactive, where increased cognitive engagement can yield improved learning. However, personalizing learning activities that elicit the optimal level of cognitive engagement remains a key challenge in intelligent tutoring systems (ITS). In this work, we develop and evaluate a system that adaptively scaffolds cognitive engagement by dynamically selecting worked examples in two different ICAP modes: (active) Guided examples and (constructive) Buggy examples. We compare Bayesian Knowledge Tracing (BKT) and Deep Reinforcement Learning (DRL) as adaptive methods against a non-adaptive baseline method for selecting example type in a logic ITS. Our experiment with 113 students demonstrates that both adaptive policies significantly improved student performance on test problems. BKT yielded the largest improvement in posttest scores for low prior knowledge students, helping them catch up with their high prior knowledge peers, whereas DRL yielded significantly higher posttest scores among high prior knowledge students. This paper contributes new insights into the complex interactions of cognitive engagement and adaptivity and their results on learning outcomes. --- ### LIT-GRAPH: Evaluating Deep vs. Shallow Graph Embeddings for High-Quality Text Recommendation in Domain-Specific Knowledge Graphs Authors: Nirmal Gelal, Chloe Snow, Kathleen M. Jagodnik, Ambyr Rios, Hande Küçük McGinty Published: 2026-02-07 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2602.07307v1 This study presents LIT-GRAPH (Literature Graph for Recommendation and Pedagogical Heuristics), a novel knowledge graph-based recommendation system designed to scaffold high school English teachers in selecting diverse, pedagogically aligned instructional literature. The system is built upon an ontology for English literature, addressing the challenge of curriculum stagnation, where we compare four graph embedding paradigms: DeepWalk, Biased Random Walk (BRW), Hybrid (concatenated DeepWalk and BRW vectors), and the deep model Relational Graph Convolutional Network (R-GCN). Results reveal a critical divergence: while shallow models excelled in structural link prediction, R-GCN dominated semantic ranking. By leveraging relation-specific message passing, the deep model prioritizes pedagogical relevance over raw connectivity, resulting in superior, high-quality, domain-specific recommendations. --- ### Parallel Track Transformers: Enabling Fast GPU Inference with Reduced Synchronization Authors: Chong Wang, Nan Du, Tom Gunter, Tao Lei, Kulin Seth, Senyu Tong, Jianyu Wang, Guoli Yin, Xiyou Zhou, Kelvin Zou, Ruoming Pang Published: 2026-02-07 Categories: cs.DC, cs.LG arXiv: https://arxiv.org/abs/2602.07306v1 Efficient large-scale inference of transformer-based large language models (LLMs) remains a fundamental systems challenge, frequently requiring multi-GPU parallelism to meet stringent latency and throughput targets. Conventional tensor parallelism decomposes matrix operations across devices but introduces substantial inter-GPU synchronization, leading to communication bottlenecks and degraded scalability. We propose the Parallel Track (PT) Transformer, a novel architectural paradigm that restructures computation to minimize cross-device dependencies. PT achieves up to a 16x reduction in synchronization operations relative to standard tensor parallelism, while maintaining competitive model quality in our experiments. We integrate PT into two widely adopted LLM serving stacks-Tensor-RT-LLM and vLLM-and report consistent improvements in serving efficiency, including up to 15-30% reduced time to first token, 2-12% reduced time per output token, and up to 31.90% increased throughput in both settings. --- ### KRONE: Scalable LLM-Augmented Log Anomaly Detection via Hierarchical Abstraction Authors: Lei Ma, Jinyang Liu, Tieying Zhang, Peter M. VanNostrand, Dennis M. Hofmann, Lei Cao, Elke A. Rundensteiner, Jianjun Chen Published: 2026-02-07 Categories: cs.DB, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2602.07303v3 Log anomaly detection is crucial for uncovering system failures and security risks. Although logs originate from nested component executions with clear boundaries, this structure is lost when stored as flat sequences. As a result, state-of-the-art methods often miss true dependencies within executions while learning spurious correlations across unrelated events. We propose KRONE, the first hierarchical anomaly detection framework that automatically derives execution hierarchies from flat logs to enable modular, multi-level anomaly detection. At its core, the KRONE Log Abstraction Model extracts application-specific semantic hierarchies, which are used to recursively decompose log sequences into coherent execution units, referred to as KRONE Seqs. This transforms sequence-level detection into a set of modular KRONE Seq-level detection tasks. For each test KRONE Seq, KRONE adopts a hybrid modular detection strategy that routes between an efficient level-independent Local-Context detector for rapid filtering and a Nested-Aware detector that captures cross-level semantic dependencies, augmented with LLM-based anomaly detection and explanation. KRONE further optimizes detection through cached result reuse and early-exit strategies along the hierarchy. Experiments on three public benchmarks and one industrial dataset from ByteDance Cloud demonstrate that KRONE achieves substantial improvements in accuracy (42.49% to 87.98%), F1 score, data efficiency (117.3x reduction), resource efficiency (43.7x reduction), and interpretability. KRONE improves F1-score by 10.07% (82.76% to 92.83%) over prior methods while reducing LLM usage to only 1.1% to 3.3% of the test data. Code: https://github.com/LeiMa0324/KRONE Demo: https://leima0324.github.io/KRONE_Demo_official/ --- ### Diabetic Retinopathy Lesion Segmentation through Attention Mechanisms Authors: Aruna Jithesh, Chinmayi Karumuri, Venkata Kiran Reddy Kotha, Meghana Doddapuneni, Taehee Jeong Published: 2026-02-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.07301v1 Diabetic Retinopathy (DR) is an eye disease which arises due to diabetes mellitus. It might cause vision loss and blindness. To prevent irreversible vision loss, early detection through systematic screening is crucial. Although researchers have developed numerous automated deep learning-based algorithms for DR screening, their clinical applicability remains limited, particularly in lesion segmentation. Our method provides pixel-level annotations for lesions, which practically supports Ophthalmologist to screen DR from fundus images. In this work, we segmented four types of DR-related lesions: microaneurysms, soft exudates, hard exudates, and hemorrhages on 757 images from DDR dataset. To enhance lesion segmentation, an attention mechanism was integrated with DeepLab-V3+. Compared to the baseline model, the Attention-DeepLab model increases mean average precision (mAP) from 0.3010 to 0.3326 and the mean Intersection over Union (IoU) from 0.1791 to 0.1928. The model also increased microaneurysm detection from 0.0205 to 0.0763, a clinically significant improvement. The detection of microaneurysms is the earliest visible symptom of DR. --- ### Optimizing Chlorination in Water Distribution Systems via Surrogate-assisted Neuroevolution Authors: Rivaaj Monsia, Daniel Young, Olivier Francon, Risto Miikkulainen Published: 2026-02-07 Categories: cs.NE, eess.SY arXiv: https://arxiv.org/abs/2602.07299v2 Ensuring the microbiological safety of large, heterogeneous water distribution systems (WDS) typically requires managing appropriate levels of disinfectant residuals including chlorine. WDS include complex fluid interactions that are nonlinear and noisy, making such maintenance a challenging problem for traditional control algorithms. This paper proposes an evolutionary framework to this problem based on neuroevolution, multi-objective optimization, and surrogate modeling. Neural networks were evolved with NEAT to inject chlorine at strategic locations in the distribution network at select times. NSGA-II was employed to optimize four objectives: minimizing the total amount of chlorine injected, keeping chlorine concentrations homogeneous across the network, ensuring that maximum concentrations did not exceed safe bounds, and distributing the injections regularly over time. Each network was evaluated against a surrogate model, i.e.\ a neural network trained to emulate EPANET, an industry-level hydraulic WDS simulator that is accurate but infeasible in terms of computational cost to support machine learning. The evolved controllers produced a diverse range of Pareto-optimal policies that could be implemented in practice, outperforming PPO, a standard reinforcement learning method. The results thus suggest a pathway toward improving urban water systems, and highlight the potential of using evolution with surrogate modeling to optimize complex real-world systems. --- ### Principled Synthetic Data Enables the First Scaling Laws for LLMs in Recommendation Authors: Benyu Zhang, Qiang Zhang, Jianpeng Cheng, Hong-You Chen, Qifei Wang, Wei Sun, Shen Li, Jia Li, Jiahao Wu, Qunshu Zhang, Neeraj Bhatia, Xiangjun Fan et al. Published: 2026-02-07 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2602.07298v3 Large Language Models (LLMs) represent a promising frontier for recommender systems, yet their development has been impeded by the absence of predictable scaling laws, which are crucial for guiding research and optimizing resource allocation. We hypothesize that this may be attributed to the inherent noise, bias, and incompleteness of raw user interaction data in prior continual pre-training (CPT) efforts. This paper introduces a novel, layered framework for generating high-quality synthetic data that circumvents such issues by creating a curated, pedagogical curriculum for the LLM. We provide powerful, direct evidence for the utility of our curriculum by showing that standard sequential models trained on our principled synthetic data significantly outperform ($+130\%$ on recall@100 for SasRec) models trained on real data in downstream ranking tasks, demonstrating its superiority for learning generalizable user preference patterns. Building on this, we empirically demonstrate, for the first time, robust power-law scaling for an LLM that is continually pre-trained on our high-quality, recommendation-specific data. Our experiments reveal consistent and predictable perplexity reduction across multiple synthetic data modalities. These findings establish a foundational methodology for reliable scaling LLM capabilities in the recommendation domain, thereby shifting the research focus from mitigating data deficiencies to leveraging high-quality, structured information. --- ### Progressive Searching for Retrieval in RAG Authors: Taehee Jeong, Xingzhe Zhao, Peizu Li, Markus Valvur, Weihua Zhao Published: 2026-02-07 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2602.07297v1 Retrieval Augmented Generation (RAG) is a promising technique for mitigating two key limitations of large language models (LLMs): outdated information and hallucinations. RAG system stores documents as embedding vectors in a database. Given a query, search is executed to find the most related documents. Then, the topmost matching documents are inserted into LLMs' prompt to generate a response. Efficient and accurate searching is critical for RAG to get relevant information. We propose a cost-effective searching algorithm for retrieval process. Our progressive searching algorithm incrementally refines the candidate set through a hierarchy of searches, starting from low-dimensional embeddings and progressing into a higher, target-dimensionality. This multi-stage approach reduces retrieval time while preserving the desired accuracy. Our findings demonstrate that progressive search in RAG systems achieves a balance between dimensionality, speed, and accuracy, enabling scalable and high-performance retrieval even for large databases. --- ### Fin-RATE: A Real-world Financial Analytics and Tracking Evaluation Benchmark for LLMs on SEC Filings Authors: Yidong Jiang, Junrong Chen, Eftychia Makri, Jialin Chen, Peiwen Li, Ali Maatouk, Leandros Tassiulas, Eliot Brenner, Bing Xiang, Rex Ying Published: 2026-02-07 Categories: cs.CE, cs.AI arXiv: https://arxiv.org/abs/2602.07294v4 With the increasing deployment of Large Language Models (LLMs) in the finance domain, LLMs are increasingly expected to parse complex regulatory disclosures. However, existing benchmarks often focus on isolated details, failing to reflect the complexity of professional analysis that requires synthesizing information across multiple documents, reporting periods, and corporate entities. Furthermore, these benchmarks do not disentangle whether errors arise from retrieval failures, generation inaccuracies, domain-specific reasoning mistakes, or misinterpretation of the query or context, making it difficult to precisely diagnose performance bottlenecks. To bridge these gaps, we introduce Fin-RATE, a benchmark built on U.S. Securities and Exchange Commission (SEC) filings and mirroring financial analyst workflows through three pathways: detail-oriented reasoning within individual disclosures, cross-entity comparison under shared topics, and longitudinal tracking of the same firm across reporting periods. We benchmark 17 leading LLMs, spanning open-source, closed-source, and finance-specialized models, under both ground-truth context and retrieval-augmented settings. Results show substantial performance degradation, with accuracy dropping by 18.60% and 14.35% as tasks shift from single-document reasoning to longitudinal and cross-entity analysis. This degradation is associated with increased comparison hallucinations, temporal and entity mismatches, and is further reflected in declines in reasoning quality and factual consistency--limitations that existing benchmarks have yet to formally categorize or quantify. --- ### Fair Decisions from Calibrated Scores: Achieving Optimal Classification While Satisfying Sufficiency Authors: Etam Benger, Katrina Ligett Published: 2026-02-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.07285v2 Binary classification based on predicted probabilities (scores) is a fundamental task in supervised machine learning. While thresholding scores is Bayes-optimal in the unconstrained setting, using a single threshold generally violates statistical group fairness constraints. Under independence (statistical parity) and separation (equalized odds), such thresholding suffices when the scores already satisfy the corresponding criterion. However, this does not extend to sufficiency: even perfectly group-calibrated scores -- including true class probabilities -- violate predictive parity after thresholding. In this work, we present an exact solution for optimal binary (randomized) classification under sufficiency, assuming finite sets of group-calibrated scores. We provide a geometric characterization of the feasible pairs of positive predictive value (PPV) and false omission rate (FOR) achievable by such classifiers, and use it to derive a simple post-processing algorithm that attains the optimal classifier using only group-calibrated scores and group membership. Finally, since sufficiency and separation are generally incompatible, we identify the classifier that minimizes deviation from separation subject to sufficiency, and show that it can also be obtained by our algorithm, often achieving performance comparable to the optimum. --- ### Imagining the Alien: Human Projections and Cognitive Limitations Authors: S. G. Djorgovski Published: 2026-02-07 Categories: astro-ph.IM, cs.AI, physics.pop-ph arXiv: https://arxiv.org/abs/2602.07284v1 Imagining what life on other planets, and intelligent life in particular, may be like is a long-running theme in human culture. It is a manifestation of the innate human curiosity about the Cosmos, and it has inspired numerous works of art and folklore, including whole literary and other media genres. It is a profound question, with philosophical and existential implications. There is also an obvious connection with religious beliefs, as gods and other superhuman beings were imagined in the heavens. Speculations about alien beings grew in time, and today, it is a scientific subject of astrobiology, and it is pursued through serious searches for life and intelligence in the universe. However, almost all imaginings of the alien map terrestrial life forms and human cultural, historical, and psychological phenomena to the putative aliens. This lack of individual and collective imagination may reflect our biological and cultural evolution, as our minds are formed through our experiences, perceptions of the world, and interactions with our terrestrial and human environments. As such, imagining aliens is mainly a cultural phenomenon and may reflect the intrinsic cognitive limitations of the human mind. Interestingly, we did create what is effectively an alien intelligence on this planet in the form of now rapidly evolving Artificial Intelligence (AI). As its capabilities grow, it may give us new insights into what extraterrestrial advanced intelligences may be like. --- ### VertCoHiRF: Decentralized Vertical Clustering Beyond k-means Authors: Bruno Belucci, Karim Lounici, Vladimir R. Kostic, Katia Meziani Published: 2026-02-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.07279v1 Vertical Federated Learning (VFL) enables collaborative analysis across parties holding complementary feature views of the same samples, yet existing approaches are largely restricted to distributed variants of $k$-means, requiring centralized coordination or the exchange of feature-dependent numerical statistics, and exhibiting limited robustness under heterogeneous views or adversarial behavior. We introduce VertCoHiRF, a fully decentralized framework for vertical federated clustering based on structural consensus across heterogeneous views, allowing each agent to apply a base clustering method adapted to its local feature space in a peer-to-peer manner. Rather than exchanging feature-dependent statistics or relying on noise injection for privacy, agents cluster their local views independently and reconcile their proposals through identifier-level consensus. Consensus is achieved via decentralized ordinal ranking to select representative medoids, progressively inducing a shared hierarchical clustering across agents. Communication is limited to sample identifiers, cluster labels, and ordinal rankings, providing privacy by design while supporting overlapping feature partitions and heterogeneous local clustering methods, and yielding an interpretable shared Cluster Fusion Hierarchy (CFH) that captures cross-view agreement at multiple resolutions.We analyze communication complexity and robustness, and experiments demonstrate competitive clustering performance in vertical federated settings. --- ### Laplacian-LoRA: Delaying Oversmoothing in Deep GCNs via Spectral Low-Rank Adaptation Authors: Sai Vamsi Alisetti Published: 2026-02-07 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.07278v1 Oversmoothing is a fundamental limitation of deep graph convolutional networks (GCNs), causing node representations to collapse as depth increases. While many prior approaches mitigate this effect through architectural modifications or residual mechanisms, the underlying spectral cause of oversmoothing is often left implicit. We propose Laplacian-LoRA, a simple and interpretable low-rank spectral adaptation of standard GCNs. Rather than redesigning message passing, Laplacian-LoRA introduces a learnable, spectrally anchored correction to the fixed Laplacian propagation operator, selectively weakening contraction while preserving stability and the low-pass inductive bias. Across multiple benchmark datasets and depths, Laplacian-LoRA consistently delays the onset of oversmoothing, extending the effective depth of GCNs by up to a factor of two. Embedding variance diagnostics confirm that these gains arise from delayed representational collapse, while learned spectral analysis demonstrates that the correction is smooth, bounded, and well behaved. Our results show that oversmoothing is a depth-dependent spectral phenomenon that can be systematically delayed through modest, low-rank adaptation of the graph propagation operator. --- ### Cross-View World Models Authors: Rishabh Sharma, Gijs Hogervorst, Wayne E. Mackey, David J. Heeger, Stefano Martiniani Published: 2026-02-07 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2602.07277v1 World models enable agents to plan by imagining future states, but existing approaches operate from a single viewpoint, typically egocentric, even when other perspectives would make planning easier; navigation, for instance, benefits from a bird's-eye view. We introduce Cross-View World Models (XVWM), trained with a cross-view prediction objective: given a sequence of frames from one viewpoint, predict the future state from the same or a different viewpoint after an action is taken. Enforcing cross-view consistency acts as geometric regularization: because the input and output views may share little or no visual overlap, to predict across viewpoints, the model must learn view-invariant representations of the environment's 3D structure. We train on synchronized multi-view gameplay data from Aimlabs, an aim-training platform providing precisely aligned multi-camera recordings with high-frequency action labels. The resulting model gives agents parallel imagination streams across viewpoints, enabling planning in whichever frame of reference best suits the task while executing from the egocentric view. Our results show that multi-view consistency provides a strong learning signal for spatially grounded representations. Finally, predicting the consequences of one's actions from another viewpoint may offer a foundation for perspective-taking in multi-agent settings. --- ### Steer2Adapt: Dynamically Composing Steering Vectors Elicits Efficient Adaptation of LLMs Authors: Pengrui Han, Xueqiang Xu, Keyang Xuan, Peiyang Song, Siru Ouyang, Runchu Tian, Yuqing Jiang, Cheng Qian, Pengcheng Jiang, Jiashuo Sun, Junxia Cui, Ming Zhong et al. Published: 2026-02-07 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2602.07276v1 Activation steering has emerged as a promising approach for efficiently adapting large language models (LLMs) to downstream behaviors. However, most existing steering methods rely on a single static direction per task or concept, making them inflexible under task variation and inadequate for complex tasks that require multiple coordinated capabilities. To address this limitation, we propose STEER2ADAPT, a lightweight framework that adapts LLMs by composing steering vectors rather than learning new ones from scratch. In many domains (e.g., reasoning or safety), tasks share a small set of underlying concept dimensions. STEER2ADAPT captures these dimensions as a reusable, low-dimensional semantic prior subspace, and adapts to new tasks by dynamically discovering a linear combination of basis vectors from only a handful of examples. Experiments across 9 tasks and 3 models in both reasoning and safety domains demonstrate the effectiveness of STEER2ADAPT, achieving an average improvement of 8.2%. Extensive analyses further show that STEER2ADAPT is a data-efficient, stable, and transparent inference-time adaptation method for LLMs. --- ### VenusBench-Mobile: A Challenging and User-Centric Benchmark for Mobile GUI Agents with Capability Diagnostics Authors: Yichen Gong, Zhuohan Cai, Sunhao Dai, Yuqi Zhou, Zhangxuan Gu, Changhua Meng, Shuheng Shen Published: 2026-02-06 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2604.06182v1 Existing online benchmarks for mobile GUI agents remain largely app-centric and task-homogeneous, failing to reflect the diversity and instability of real-world mobile usage. To this end, we introduce VenusBench-Mobile, a challenging online benchmark for evaluating general-purpose mobile GUI agents under realistic, user-centric conditions. VenusBench-Mobile builds two core evaluation pillars: defining what to evaluate via user-intent-driven task design that reflects real mobile usage, and how to evaluate through a capability-oriented annotation scheme for fine-grained agent behavior analysis. Extensive evaluation of state-of-the-art mobile GUI agents reveals large performance gaps relative to prior benchmarks, indicating that VenusBench-Mobile poses substantially more challenging and realistic tasks and that current agents remain far from reliable real-world deployment. Diagnostic analysis further shows that failures are dominated by deficiencies in perception and memory, which are largely obscured by coarse-grained evaluations. Moreover, even the strongest agents exhibit near-zero success under environment variations, highlighting their brittleness in realistic settings. Based on these insights, we believe VenusBench-Mobile provides an important stepping stone toward robust real-world deployment of mobile GUI agents. Code and data are available at https://github.com/inclusionAI/UI-Venus/tree/VenusBench-Mobile. --- ### Performance Evaluation of LLMs in Automated RDF Knowledge Graph Generation Authors: Ioana Ramona Martin, Tudor Cioara, Ionut Anghel, Gabriel Arcas Published: 2026-02-06 Categories: cs.IR, cs.AI, cs.DC arXiv: https://arxiv.org/abs/2603.29878v1 Cloud systems generate large, heterogeneous log data containing critical infrastructure, application, and security information. Transforming these logs into RDF triples enables their integration into knowledge graphs, improving interpretability, root-cause analysis, and cross-service reasoning beyond what raw logs allow. Large Language Models (LLMs) offer a promising approach to automate RDF knowledge graph generation; however, their effectiveness on complex cloud logs remains largely unexplored. In this paper, we evaluate multiple LLM architectures and prompting strategies for automated RDF extraction using a controlled framework with two pipelines for systematically processing semi-structured log data. The extraction pipeline integrates multiple LLMs to identify relevant entities and relationships, automatically generating subject-predicate-object triples. These outputs are evaluated using a dedicated validation pipeline with both syntactic and semantic metrics to assess accuracy, completeness, and quality. Due to the lack of public ground-truth datasets, we created a reference Log-to-KG dataset from OpenStack logs using manual annotation and ontology-driven methods, enabling objective baseline. Our analysis shows that Few-Shot learning is the most effective strategy, with Llama achieving a 99.35% F1 score and 100% valid RDF output while Qwen, NuExtract, and Gemma also perform well under Few-Shot prompting, with Chain-of-Thought approaches maintaining similar accuracy. One-Shot prompting offers a lighter but effective alternative, while Zero-Shot and advanced strategies such as Tree-of-Thought, Self-Critique, and Generate-Multiple perform substantially worse. These results highlight the importance of contextual examples and prompt design for accurate RDF extraction and reveal model-specific limitations across LLM architectures. --- ### UnWeaving the knots of GraphRAG -- turns out VectorRAG is almost enough Authors: Ryszard Tuora, Mateusz Galiński, Michał Godziszewski, Michał Karpowicz, Mateusz Czyżnikiewicz, Adam Kozakiewicz, Tomasz Ziętkiewicz Published: 2026-02-06 Categories: cs.IR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.29875v3 One of the key problems in Retrieval-augmented generation (RAG) systems is that chunk-based retrieval pipelines represent the source chunks as atomic objects, mixing the information contained within such a chunk into a single vector. These vector representations are then fundamentally treated as isolated, independent and self-sufficient, with no attempt to represent possible relations between them. Such an approach has no dedicated mechanisms for handling multi-hop questions. Graph-based RAG systems aimed to ameliorate this problem by modeling information as knowledge-graphs, with entities represented by nodes being connected by robust relations, and forming hierarchical communities. This approach however suffers from its own issues with some of them being: orders of magnitude increased componential complexity in order to create graph-based indices, and reliance on heuristics for performing retrieval. We propose UnWeaver, a novel RAG framework simplifying the idea of GraphRAG. UnWeaver disentangles the contents of the documents into entities which can occur across multiple chunks using an LLM. In the retrieval process entities are used as an intermediate way of recovering original text chunks hence preserving fidelity to the source material. We argue that entity-based decomposition yields a more distilled representation of original information, and additionally serves to reduce noise in the indexing, and generation process. Furthermore we experimentally show that on end to end QA evaluation VectorRAG performs better than standard GraphRAG and almost as good as current SOTA graph-based solutions, for a fraction of the cost. --- ### Automatic Method Illustration Generation for AI Scientific Papers via Drawing Middleware Creation, Evolution, and Orchestration Authors: Zhuoling Li, Jiarui Zhang, Ping Hu, Jason Kuen, Jiuxiang Gu, Hossein Rahmani, Jun Liu Published: 2026-02-06 Categories: cs.GR, cs.AI arXiv: https://arxiv.org/abs/2603.29590v2 Method illustrations (MIs) play a crucial role in conveying the core ideas of scientific papers, yet their generation remains a labor-intensive process. Here, we take inspiration from human authors' drawing practices and correspondingly propose \textbf{FigAgent}, a novel multi-agent framework for high-quality automatic MI generation. Our FigAgent distills drawing experiences from similar components across MIs and encapsulates them into reusable drawing middlewares that can be orchestrated for MI generation, while evolving these middlewares to adapt to dynamically evolving drawing requirements. Besides, a novel Explore-and-Select drawing strategy is introduced to mimic the human-like trial-and-error manner for gradually constructing MIs with complex structures. Extensive experiments show the efficacy of our method. --- ### GhazalBench: Canonical Verse Access in LLMs across Persian Ghazals and Shakespearean Sonnets Authors: Ghazal Kalhor, Yadollah Yaghoobzadeh Published: 2026-02-06 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.09979v3 Persian poetry plays an active role in Iranian cultural practice, where verses by canonical poets such as Hafez and Saadi are frequently quoted, paraphrased, or completed from incomplete cues. Supporting such interactions requires language models to reliably access canonical verses from semantic and lexical information. We introduce GhazalBench, a benchmark for evaluating how large language models (LLMs) access the canonical surface forms of Persian ghazal under usage-grounded conditions. Unlike prior work that primarily treats memorization as a liability, GhazalBench studies settings in which access to exact wording is functionally important. The benchmark evaluates completion and recognition under varied semantic and lexical cues. Across proprietary and open-weight multilingual LLMs, exact completion remains challenging, while recognition is substantially stronger. Performance also varies across poets and model families. Parallel experiments on Shakespearean sonnets yield markedly higher completion for several models, consistent with differences in exposure to canonical texts. {Additional experiments suggest that post-training may reduce direct continuation-based access to canonical text.} Our findings motivate evaluation frameworks that distinguish production from recognition and assess access to culturally significant canonical texts. GhazalBench is available at https://github.com/kalhorghazal/GhazalBench. --- ### GhazalBench: Evaluating LLM Understanding and Canonical Surface-Form Access in Persian Ghazals Authors: Ghazal Kalhor, Yadollah Yaghoobzadeh Published: 2026-02-06 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.09979v2 Persian poetry plays an active role in Iranian cultural practice, where verses by canonical poets such as Hafez are frequently quoted, paraphrased, or completed from partial cues. Supporting such interactions requires language models to engage not only with poetic meaning but also with culturally canonical surface form. We introduce GhazalBench, a benchmark for evaluating how large language models (LLMs) interact with Persian ghazals under usage-grounded conditions. Unlike prior work that primarily studies memorization as a liability, GhazalBench examines settings where access to exact surface form is functionally important for culturally grounded interaction. The benchmark evaluates two complementary abilities: poem-to-prose understanding and canonical surface-form access under varying semantic and lexical cues. Across several proprietary and open-weight multilingual LLMs, we observe a consistent dissociation: models generally capture poetic meaning but struggle to produce exact verse completions in open-ended settings, while recognition-based settings substantially reduce this gap. Parallel experiments on English sonnets show markedly stronger completion performance, suggesting that these limitations are tied more to differences in training exposure than to inherent architectural constraints. Our findings highlight the need for evaluation frameworks that jointly assess meaning, form, and cue-dependent access to culturally significant texts. GhazalBench is available at https://anonymous.4open.science/r/GhazalBench/. --- ### Design Conductor: An agent autonomously builds a 1.5 GHz Linux-capable RISC-V CPU Authors: The Verkor Team, Ravi Krishna, Suresh Krishna, David Chin Published: 2026-02-06 Categories: cs.AR, cs.AI arXiv: https://arxiv.org/abs/2603.08716v1 Design Conductor (DC) is an autonomous agent which applies the capabilities of frontier models to build semiconductors end-to-end -- that is, from concept to verified, tape-out ready GDSII (layout CAD file). In 12 hours and fully autonomously, DC was able to build several micro-architecture variations of a complete RISC-V CPU (which we dub VerCore) that meet timing at 1.48 GHz (rv32i-zmmul; using the ASAP7 PDK), starting from a 219-word requirements document. The VerCore achieves a CoreMark score of 3261. For historical context, this is roughly equivalent to an Intel Celeron SU2300 from mid-2011 (which ran at 1.2 GHz). To our knowledge, this is the first time an autonomous agent has built a complete, working CPU from spec to GDSII. This report is organized as follows. We first review DC's design and its key components. We then describe the methodology that DC followed to build VerCore -- including RTL implementation, testbench implementation, frontend debugging, optimization to achieve timing closure, and interacting with backend tools. We review the key characteristics of the resulting VerCore. Finally, we highlight how frontier models could improve to better enable this application, and our lessons learned as to how chips will be built in the future enabled by the capabilities of systems like DC. --- ### Attention's Gravitational Field:A Power-Law Interpretation of Positional Correlation Authors: Edward Zhang Published: 2026-02-06 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.04805v1 This paper explores the underlying principles of positional relationships and encodings within Large Language Models (LLMs) and introduces the concept of the Attention Gravitational Field (AGF). By decoupling positional encodings from semantic embeddings, we optimize the model architecture and achieve superior accuracy compared to prevailing encoding methods. Furthermore, we provide an in-depth analysis of AGF, demonstrating its intrinsic consistency with learning and stability curves, as well as its empirical alignment with Newton's Law of Universal Gravitation. By offering a rigorous theoretical exploration of these phenomena, this work represents a significant step toward interpreting the Attention mechanism and unlocks new possibilities for future research in model optimization and interpretability. --- ### TATRA: Training-Free Instance-Adaptive Prompting Through Rephrasing and Aggregation Authors: Bartosz Dziuba, Kacper Kuchta, Paweł Batorski, Przemysław Spurek, Paul Swoboda Published: 2026-02-06 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.03298v1 Large Language Models (LLMs) have improved substantially alignment, yet their behavior remains highly sensitive to prompt phrasing. This brittleness has motivated automated prompt engineering, but most existing methods (i) require a task-specific training set, (ii) rely on expensive iterative optimization to produce a single dataset-level prompt, and (iii) must be rerun from scratch for each new task. We introduce TATRA, a dataset-free prompting method that constructs instance-specific few-shot prompts by synthesizing on-the-fly examples to accompany a user-provided instruction. TATRA requires no labeled training data and avoids task-specific optimization loops, while retaining the benefits of demonstration-based prompting. Across standard text classification benchmarks, TATRA matches or improves over strong prompt-optimization baselines that depend on training data and extensive search. On mathematical reasoning benchmarks, TATRA achieves state-of-the-art performance on GSM8K and DeepMath, outperforming methods that explicitly optimize prompts on those tasks. Our results suggest that per-instance construction of effective in-context examples is more important than running long, expensive optimization loops to produce a single prompt per task. We will make all code publicly available upon acceptance of the paper. Code is available at https://github.com/BMD223/TATRA --- ### TTSR: Test-Time Self-Evolving via Reflection Authors: Haoyang He, Zihua Rong, Yunjia Zhao, Lan Yang, Jian Chang, Honggang Zhang Published: 2026-02-06 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.03297v3 Test-time training (TTT) adapts large language models (LLMs) during inference using only unlabeled test inputs. Existing methods, however, face two major bottlenecks on hard reasoning tasks: (1) \emph{lack of learnable samples}, as self-generated pseudo-labels on difficult questions are often noisy and yield unstable rewards; and (2) \emph{inefficient exploration}, as performance gains depend on repeatedly sampling many rollouts without explicit diagnosis of why previous attempts fail. We propose \textbf{TTSR} (\textbf{T}est-\textbf{T}ime \textbf{S}elf-\textbf{R}eflection), a self-evolving framework based on a \emph{reflect-then-synthesize} paradigm. A single pretrained model alternates between a \textit{Student} role and a \textit{Teacher} role: the Student solves test questions and updates, while the Teacher analyzes failed trajectories and synthesizes targeted variant questions closer to the Student's capability frontier. TTSR further maintains a cross-iteration \textit{weakness memory} and compiles persistent weaknesses into a lightweight \textit{strategy note} prepended to subsequent Student inputs, so diagnostic knowledge can guide exploration and gradually fade as weaknesses are resolved. Experiments on challenging mathematical reasoning benchmarks show consistent test-time improvements, strong cross-backbone generalization, and transfer to general-domain reasoning tasks. --- ### TTSR: Test-Time Self-Reflection for Continual Reasoning Improvement Authors: Haoyang He, Zihua Rong, Liangjie Zhao, Yunjia Zhao, Lan Yang, Honggang Zhang Published: 2026-02-06 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.03297v1 Test-time Training enables model adaptation using only test questions and offers a promising paradigm for improving the reasoning ability of large language models (LLMs). However, it faces two major challenges: test questions are often highly difficult, making self-generated pseudo-labels unreliable, and existing methods lack effective mechanisms to adapt to a model's specific reasoning weaknesses, leading to inefficient learning. To address these issues, we propose \textbf{TTSR}, a self-reflective test-time self-evolving training framework. TTSR employs a single pretrained language model that alternates between the roles of a \textit{Student} and a \textit{Teacher} at test time. The Student focuses on solving problems and learning from synthesized variant questions, while the Teacher analyzes the Student's failed reasoning trajectories, summarizes recurring reasoning weaknesses, and synthesizes targeted variant questions accordingly. This process guides the model to improve within a learnable regime through a continual self-evolving loop. Experimental results on multiple challenging mathematical reasoning benchmarks show that TTSR consistently improves reasoning performance and generalizes well across different model backbones and general-domain reasoning tasks. These findings suggest that teacher-mediated self-reflection provides an effective pathway for stable and continual reasoning improvement at test time. --- ### PlugMem: A Task-Agnostic Plugin Memory Module for LLM Agents Authors: Ke Yang, Zixi Chen, Xuan He, Jize Jiang, Michel Galley, Chenglong Wang, Jianfeng Gao, Jiawei Han, ChengXiang Zhai Published: 2026-02-06 Categories: cs.CL, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2603.03296v1 Long-term memory is essential for large language model (LLM) agents operating in complex environments, yet existing memory designs are either task-specific and non-transferable, or task-agnostic but less effective due to low task-relevance and context explosion from raw memory retrieval. We propose PlugMem, a task-agnostic plugin memory module that can be attached to arbitrary LLM agents without task-specific redesign. Motivated by the fact that decision-relevant information is concentrated as abstract knowledge rather than raw experience, we draw on cognitive science to structure episodic memories into a compact, extensible knowledge-centric memory graph that explicitly represents propositional and prescriptive knowledge. This representation enables efficient memory retrieval and reasoning over task-relevant knowledge, rather than verbose raw trajectories, and departs from other graph-based methods like GraphRAG by treating knowledge as the unit of memory access and organization instead of entities or text chunks. We evaluate PlugMem unchanged across three heterogeneous benchmarks (long-horizon conversational question answering, multi-hop knowledge retrieval, and web agent tasks). The results show that PlugMem consistently outperforms task-agnostic baselines and exceeds task-specific memory designs, while also achieving the highest information density under a unified information-theoretic analysis. Code and data are available at https://github.com/TIMAN-group/PlugMem. --- ### Language Model Goal Selection Differs from Humans' in a Self-Directed Learning Task Authors: Gaia Molinaro, Dave August, Danielle Perszyk, Anne G. E. Collins Published: 2026-02-06 Categories: cs.CL, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2603.03295v2 Whether in agentic workflows, social studies, or chat settings, large language models (LLMs) are increasingly being asked to replace humans in choosing which goals to pursue, rather than completing predefined tasks. However, the assumption that LLMs accurately reflect human preferences for goal setting remains largely untested. We assess the validity of LLMs as proxies for human goal selection in a controlled, self-directed learning task borrowed from cognitive science. Across five models (GPT-5, Gemini 2.5 Pro, Claude Sonnet 4.5, Qwen3 32B, and Centaur), we find substantial divergence from human behavior. While people gradually explore and learn to achieve goals with diversity across individuals, most models exploit a single identified solution or show surprisingly low performance, with distinct patterns across models and little variability across instances of the same model. Chain-of-thought reasoning and persona steering provide limited improvements, and our conclusions hold across experimental settings. While they await confirmation in applied settings, these findings highlight the uniqueness of human goal selection and caution against its replacement with current models. --- ### Fine-Tuning and Evaluating Conversational AI for Agricultural Advisory Authors: Sanyam Singh, Naga Ganesh, Vineet Singh, Lakshmi Pedapudi, Ritesh Kumar, SSP Jyothi, Archana Karanam, Waseem Pasha, Ekta Kumari, C. Yashoda, Mettu Vijaya Rekha Reddy, Shesha Phani Debbesa et al. Published: 2026-02-06 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.03294v2 Large Language Models show promise for agricultural advisory, yet vanilla models exhibit unsupported recommendations, generic advice lacking specific, actionable detail, and communication styles misaligned with smallholder farmer needs. In high stakes agricultural contexts, where recommendation accuracy has direct consequences for farmer outcomes, these limitations pose challenges for responsible deployment. We present a hybrid LLM architecture that decouples factual retrieval from conversational delivery: supervised fine-tuning with LoRA on expert-curated GOLDEN FACTS (atomic, verified units of agricultural knowledge) optimizes fact recall, while a separate stitching layer transforms retrieved facts into culturally appropriate, safety-aware responses. Our evaluation framework, DG-EVAL, performs atomic fact verification (measuring recall, precision, and contradiction detection) against expert-curated ground truth rather than Wikipedia or retrieved documents. Experiments across multiple model configurations on crops and queries from Bihar, India show that fine-tuning on curated data substantially improves fact recall and F1, while maintaining high relevance. Using a fine-tuned smaller model achieves comparable or better factual quality at a fraction of the cost of frontier models. A stitching layer further improves safety subscores while maintaining high conversational quality. We release the farmerchat-prompts library to enable reproducible development of domain-specific agricultural AI. --- ### SE-Search: Self-Evolving Search Agent via Memory and Dense Reward Authors: Jian Li, Yizhang Jin, Dongqi Liu, Hang Ding, Jiafu Wu, Dongsheng Chen, Yunhang Shen, Yulei Qin, Ying Tai, Chengjie Wang, Xiaotong Yuan, Yabiao Wang Published: 2026-02-06 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.03293v1 Retrieval augmented generation (RAG) reduces hallucinations and factual errors in large language models (LLMs) by conditioning generation on retrieved external knowledge. Recent search agents further cast RAG as an autonomous, multi-turn information-seeking process. However, existing methods often accumulate irrelevant or noisy documents and rely on sparse reinforcement learning signals. We propose \textbf{S}elf-\textbf{E}volving \textbf{Search}, a Self-Evolving Search agent that improves online search behavior through three components, memory purification, atomic query training, and dense rewards. SE-Search follows a \textit{Think-Search-Memorize} strategy that retains salient evidence while filtering irrelevant content. Atomic query training promotes shorter and more diverse queries, improving evidence acquisition. Dense rewards provide fine-grained feedback that speeds training. Experiments on single-hop and multi-hop question answering benchmarks show that \texttt{SE-Search-3B} outperforms strong baselines, yielding a $10.8$ point absolute improvement and a $33.8\%$ relative gain over Search-R1.\footnote{We will make the code and model weights publicly available upon acceptance.} --- ### From Conflict to Consensus: Boosting Medical Reasoning via Multi-Round Agentic RAG Authors: Wenhao Wu, Zhentao Tang, Yafu Li, Shixiong Kai, Mingxuan Yuan, Zhenhong Sun, Chunlin Chen, Zhi Wang Published: 2026-02-06 Categories: cs.CL, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2603.03292v3 Large Language Models (LLMs) exhibit high reasoning capacity in medical question-answering, but their tendency to produce hallucinations and outdated knowledge poses critical risks in healthcare fields. While Retrieval-Augmented Generation (RAG) mitigates these issues, existing methods rely on noisy token-level signals and lack the multi-round refinement required for complex reasoning. In this paper, we propose MA-RAG (Multi-Round Agentic RAG), a framework that facilitates test-time scaling for complex medical reasoning by iteratively evolving both external evidence and internal reasoning history within an agentic refinement loop. At each round, the agent transforms semantic conflict among candidate responses into actionable queries to retrieve external evidence, while optimizing history reasoning traces to mitigate long-context degradation. MA-RAG extends the self-consistency principle by leveraging the lack of consistency as a proactive signal for multi-round agentic reasoning and retrieval, and mirrors a boosting mechanism that iteratively minimizes the residual error toward a stable, high-fidelity medical consensus. Extensive evaluations across 7 medical Q&A benchmarks show that MA-RAG consistently surpasses competitive inference-time scaling and RAG baselines, delivering substantial +6.8 points on average accuracy over the backbone model. Our code is available at https://github.com/NJU-RL/MA-RAG. --- ### One Bias After Another: Mechanistic Reward Shaping and Persistent Biases in Language Reward Models Authors: Daniel Fein, Max Lamparth, Violet Xiang, Mykel J. Kochenderfer, Nick Haber Published: 2026-02-06 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.03291v2 Reward Models (RMs) are crucial for online alignment of language models (LMs) with human preferences. However, RM-based preference-tuning is vulnerable to reward hacking, whereby LM policies learn undesirable behaviors from flawed RMs. By systematically measuring biases in five high-quality RMs, including the state-of-the-art, we find that issues persist despite prior work with respect to length, sycophancy, and overconfidence. We also discover new issues related to bias toward model-specific ``styles'' and answer-order. We categorize RM failures as tractable or resistant to linear intervention and propose a simple post-hoc intervention to mitigate low-complexity biases that arise from spurious correlations. Our proposed mechanistic reward shaping reduces targeted biases without degrading reward quality and while using minimal labeled data. The method is extensible to new biases, model-internal, and generalizes out-of-distribution. ---