# Research Papers — 2026-02 · bundle page 119 of 210 > Full-text markdown of papers #5901–5950 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/119 [← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/118.md) [Next bundle →](https://aipod.dev/papers/archive/2026-02/page/120.md) ### Distributionally Robust Geometric Joint Chance-Constrained Optimization: Neurodynamic Approaches Authors: Ange Valli, Siham Tassouli, Abdel Lisser Published: 2026-02-10 Categories: cs.NE, cs.AI, math.OC, math.PR arXiv: https://arxiv.org/abs/2603.06597v2 This paper proposes a two-time scale neurodynamic duplex approach to solve distributionally robust geometric joint chance-constrained optimization problems. The probability distributions of the row vectors are not known in advance and belong to a certain distributional uncertainty set. In our paper, we study three uncertainty sets for the unknown distributions. The neurodynamic duplex is designed based on three projection equations. The main contribution of our work is to propose a neural network-based method to solve distributionally robust joint chance-constrained optimization problems that converges in probability to the global optimum without the use of standard state-of-the-art solving methods. We show that neural networks can be used to solve multiple instances of a problem. In the numerical experiments, we apply the proposed approach to solve a problem of shape optimisation and a telecommunication problem. --- ### PulseLM: A Foundation Dataset and Benchmark for PPG-Text Learning Authors: Hung Manh Pham, Jinyang Wu, Xiao Ma, Yiming Zhang, Yixin Xu, Aaqib Saeed, Bin Zhu, Zhou Pan, Dong Ma Published: 2026-02-10 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.03331v2 Photoplethysmography (PPG) is a widely used non-invasive sensing modality for continuous cardiovascular and physiological monitoring across clinical, laboratory, and wearable settings. While existing PPG datasets support a broad range of downstream tasks, they typically provide supervision in the form of numerical measurements or task-specific labels, limiting their compatibility with language-based interfaces and multimodal foundation models. In this work, we introduce PulseLM, a large-scale PPG-text question-answering dataset that bridges raw PPG waveforms and natural language through a unified question-answering (QA) formulation. PulseLM aggregates PPG recordings from sixteen publicly available sources and harmonizes heterogeneous annotations into 12 downstream tasks. The dataset comprises over 1 million standardized 10-second PPG segments, associated with nearly 2.5 million question-answer pairs. We further define reproducible data pipeline, training, and evaluation protocols and establish baseline benchmarks using multimodal PPG-aware large language models. PulseLM provides a standardized foundation for studying language-grounded physiological inference, cross-dataset generalization, and scalable benchmarking of PPG-based multimodal models. We publicly release the dataset and code at https://huggingface.co/datasets/Manhph2211/PulseLM and https://github.com/manhph2211/PULSE-LM, respectively. --- ### Certainty robustness: Evaluating LLM stability under self-challenging prompts Authors: Mohammadreza Saadat, Steve Nemzer Published: 2026-02-10 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.03330v1 Large language models (LLMs) often present answers with high apparent confidence despite lacking an explicit mechanism for reasoning about certainty or truth. While existing benchmarks primarily evaluate single-turn accuracy, truthfulness or confidence calibration, they do not capture how models behave when their responses are challenged in interactive settings. We introduce the Certainty Robustness Benchmark, a two-turn evaluation framework that measures how LLMs balance stability and adaptability under self-challenging prompts such as uncertainty ("Are you sure?") and explicit contradiction ("You are wrong!"), alongside numeric confidence elicitation. Using 200 reasoning and mathematics questions from LiveBench, we evaluate four state-of-the-art LLMs and distinguish between justified self-corrections and unjustified answer changes. Our results reveal substantial differences in interactive reliability that are not explained by baseline accuracy alone: some models abandon correct answers under conversational pressure, while others demonstrate strong resistance to challenge and better alignment between confidence and correctness. These findings identify certainty robustness as a distinct and critical dimension of LLM evaluation, with important implications for alignment, trustworthiness and real-world deployment. --- ### AutoHarness: improving LLM agents by automatically synthesizing a code harness Authors: Xinghua Lou, Miguel Lázaro-Gredilla, Antoine Dedieu, Carter Wendelken, Wolfgang Lehrach, Kevin P. Murphy Published: 2026-02-10 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.03329v1 Despite significant strides in language models in the last few years, when used as agents, such models often try to perform actions that are not just suboptimal for a given state, but are strictly prohibited by the external environment. For example, in the recent Kaggle GameArena chess competition, 78% of Gemini-2.5-Flash losses were attributed to illegal moves. Often people manually write "harnesses" around LLMs to prevent such failures. In this paper, we demonstrate that Gemini-2.5-Flash can automatically synthesize such a code harness, using a small number of rounds of iterative code refinement given feedback from the (game) environment. The resulting harness prevents all illegal moves in 145 different TextArena games (both 1-player and 2-player), enabling the smaller Gemini-2.5-Flash model to outperform larger models, such as Gemini-2.5-Pro. Pushing our technique to the limit, we can get Gemini-2.5-Flash to generate the entire policy in code, thus eliminating the need to use the LLM at decision making time. The resulting code-policy receives a higher average reward than Gemini-2.5-Pro and GPT-5.2-High on 16 TextArena 1-player games. Our results show that using a smaller model to synthesize a custom code harness (or entire policy) can outperform a much larger model, while also being more cost effective. --- ### StructLens: A Structural Lens for Language Models via Maximum Spanning Trees Authors: Haruki Sakajo, Frederikus Hudi, Yusuke Sakai, Hidetaka Kamigaito, Taro Watanabe Published: 2026-02-10 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.03328v2 Language exhibits inherent structures, a property that explains both language acquisition and language change. Given this characteristic, we expect language models to manifest their own internal structures as well. While interpretability research has investigated how models compute representations mechanistically through attention patterns and Sparse AutoEncoders, the organization of the resulting representations is overlooked. To address this gap, we introduce StructLens, a framework to analyze representations through a holistic structural view. StructLens constructs maximum spanning trees based on the semantic representations in residual streams, inspired by tree representation in dependency parsing, and provides summaries of token relationships in representation space. We analyze how contiguous tokens are also nearby in representation space and find that middle layers show the strongest local-span organization. Moreover, analysis of pre-training checkpoints reveals that smaller local units become detectable earlier in pre-training, and larger units later. Our findings demonstrate that StructLens provides insights into how models organize token representations across layers and training. Our code is available at https://github.com/naist-nlp/structlens. --- ### A benchmark for joint dialogue satisfaction, emotion recognition, and emotion state transition prediction Authors: Jing Bian, Haoxiang Su, Liting Jiang, Di Wu, Ruiyu Fang, Xiaomeng Huang, Yanbing Li, Shuangyong Song, Hao Huang Published: 2026-02-10 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.03327v1 User satisfaction is closely related to enterprises, as it not only directly reflects users' subjective evaluation of service quality or products, but also affects customer loyalty and long-term business revenue. Monitoring and understanding user emotions during interactions helps predict and improve satisfaction. However, relevant Chinese datasets are limited, and user emotions are dynamic; relying on single-turn dialogue cannot fully track emotional changes across multiple turns, which may affect satisfaction prediction. To address this, we constructed a multi-task, multi-label Chinese dialogue dataset that supports satisfaction recognition, as well as emotion recognition and emotional state transition prediction, providing new resources for studying emotion and satisfaction in dialogue systems. --- ### Controllable and explainable personality sliders for LLMs at inference time Authors: Florian Hoppe, David Khachaturov, Robert Mullins, Mark Huasong Meng Published: 2026-02-10 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.03326v1 Aligning Large Language Models (LLMs) with specific personas typically relies on expensive and monolithic Supervised Fine-Tuning (SFT) or RLHF. While effective, these methods require training distinct models for every target personality profile. Inference-time activation steering offers a parameter-efficient alternative, yet naive approaches fail to control multiple traits simultaneously due to destructive vector interference. In this work, we propose a modular framework for continuous, multi-dimensional personality control. Our key innovation is Sequential Adaptive Steering (SAS): a method that orthogonalizes steering vectors by training subsequent probes on the residual stream shifted by prior interventions. This approach transforms steering vectors into reusable primitives, allowing users to instantly synthesize complex, high-fidelity personality profiles by simply adjusting coefficients alpha. We validate our framework on the Big Five personality traits, demonstrating that it outperforms naive baselines in both goal adherence and coherence, enabling precise, holistic personality modulation without updating model parameters. --- ### IntPro: A Proxy Agent for Context-Aware Intent Understanding via Retrieval-conditioned Inference Authors: Guanming Liu, Meng Wu, Peng Zhang, Yu Zhang, Yubo Shu, Xianliang Huang, Kainan Tu, Ning Gu, Liuxin Zhang, Qianying Wang, Tun Lu Published: 2026-02-10 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.03325v1 Large language models (LLMs) have become integral to modern Human-AI collaboration workflows, where accurately understanding user intent serves as a crucial step for generating satisfactory responses. Context-aware intent understanding, which involves inferring user intentions from situational environments, is inherently challenging because it requires reasoning over both the immediate context and the user's underlying motivations that drive their behavior. Moreover, existing approaches often treat intent understanding as a static recognition task, overlooking users' accumulated intent patterns that could provide valuable references for more accurate and generalizable understanding. To address this gap, we propose IntPro, a proxy agent that learns to adapt to individual users via retrieval-conditioned intent inference. We design intent explanations that abstract how contextual signals connect to expressed intents, and store them in an individual intent history library for retrieval. We train IntPro through supervised fine-tuning on retrieval-conditioned trajectories and multi-turn Group Relative Policy Optimization (GRPO) with tool-aware reward functions, enabling the agent to learn when to leverage historical intent patterns and when to infer directly. Experiments across three diverse scenarios (Highlight-Intent, MIntRec2.0, and Weibo Post-Sync) demonstrate that IntPro achieves strong intent understanding performance with effective context-aware reasoning capabilities across different scenarios and model types. --- ### Controlling Chat Style in Language Models via Single-Direction Editing Authors: Zhenyu Xu, Victor S. Sheng Published: 2026-02-10 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.03324v1 Controlling stylistic attributes in large language models (LLMs) remains challenging, with existing approaches relying on either prompt engineering or post-training alignment. This paper investigates this challenge through the lens of representation engineering, testing the hypothesis that distinct stylistic attributes - from emotional tone to linguistic structure - are encoded as linear directions in the model's activation space. We provide strong empirical evidence for this hypothesis across a wide range of styles and, based on this finding, present a lightweight, training-free method for precise style control. Our approach supports linear style composition, enhances safety by ablating undesirable behaviors, and, as confirmed by experiments on over a dozen models, achieves high style adherence while preserving core capabilities at minimal computational cost. --- ### Discern Truth from Falsehood: Reducing Over-Refusal via Contrastive Refinement Authors: Yuxiao Lu, Lin Xu, Yang Sun, Wenjun Li, Jie Shi Published: 2026-02-10 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.03323v1 Large language models (LLMs) aligned for safety often suffer from over-refusal, the tendency to reject seemingly toxic or benign prompts by misclassifying them as toxic. This behavior undermines models' helpfulness and restricts usability in sensitive or nuanced contexts. While prior work has proposed mitigation strategies such as data augmentation and activation steering, these approaches often face a trade-off: reducing over-refusal typically degrades the model's ability to reject genuinely harmful content. We argue that this issue arises from the ambiguous influence of toxic and seemingly toxic prompts on the model's learning dynamics. To address it, we introduce a preceding alignment stage, DCR: Discernment via Contrastive Refinement. Both theoretically and empirically, we demonstrate that contrastive refinement improves an LLM's capacity to distinguish truly toxic prompts from superficially toxic ones. Evaluation across diverse benchmarks shows that our method effectively reduces over-refusal while preserving the safety benefits of alignment. Importantly, it achieves this with minimal degradation of general capabilities, offering a more principled and robust direction for safety alignment. --- ### Can Large Language Models Derive New Knowledge? A Dynamic Benchmark for Biological Knowledge Discovery Authors: Chaoqun Yang, Xinyu Lin, Shulin Li, Wenjie Wang, Ruihan Guo, Fuli Feng, Tat-Seng Chua Published: 2026-02-10 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.03322v2 Recent advancements in Large Language Model (LLM) agents have demonstrated remarkable potential in automatic knowledge discovery. However, rigorously evaluating an AI's capacity for knowledge discovery remains a critical challenge. Existing benchmarks predominantly rely on static datasets, leading to inevitable data contamination where models have likely seen the evaluation knowledge during training. Furthermore, the rapid release cycles of modern LLMs render static benchmarks quickly outdated, failing to assess the ability to discover truly new knowledge. To address these limitations, we propose DBench-Bio, a dynamic and fully automated benchmark designed to evaluate AI's biological knowledge discovery ability. DBench-Bio employs a three-stage pipeline: (1) data acquisition of rigorous, authoritative paper abstracts; (2) QA extraction utilizing LLMs to synthesize scientific hypothesis questions and corresponding discovery answers; and (3) QA filter to ensure quality based on relevance, clarity, and centrality. We instantiate this pipeline to construct a monthly-updated benchmark covering 12 biomedical sub-domains. Extensive evaluations of SOTA models reveal current limitations in discovering new knowledge. Our work provides the first dynamic, automatic framework for assessing the new knowledge discovery capabilities of AI systems, establishing a living, evolving resource for AI research community to catalyze the development of knowledge discovery. --- ### DIALEVAL: Automated Type-Theoretic Evaluation of LLM Instruction Following Authors: Nardine Basta, Dali Kaafar Published: 2026-02-10 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.03321v1 Evaluating instruction following in Large Language Models requires decomposing instructions into verifiable requirements and assessing satisfaction--tasks currently dependent on manual annotation and uniform criteria that do not align with human judgment patterns. We present DIALEVAL, a type-theoretic framework using dual LLM agents to automate instruction decomposition into typed predicates and implement type-specific satisfaction semantics. The framework enforces formal atomicity and independence constraints during automated extraction, then applies differentiated evaluation criteria--semantic equivalence for content predicates, exact precision for numerical predicates--mirroring empirically observed human assessment patterns. Extended to multi-turn dialogues through history-aware satisfaction functions, DIALEVAL enables evaluation in conversational contexts where single-turn methods fail. Validation demonstrates 90.38% accuracy (26.45% error reduction over baselines) and substantially stronger correlation with human judgment for complex instructions. --- ### From We to Me: Theory Informed Narrative Shift with Abductive Reasoning Authors: Jaikrishna Manojkumar Patil, Divyagna Bavikadi, Kaustuv Mukherji, Ashby Steward-Nolan, Peggy-Jean Allin, Tumininu Awonuga, Joshua Garland, Paulo Shakarian Published: 2026-02-10 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.03320v2 Effective communication often relies on aligning a message with an audience's narrative and worldview. Narrative shift involves transforming text to reflect a different narrative framework while preserving its original core message--a task we demonstrate is significantly challenging for current Large Language Models (LLMs). To address this, we propose a neurosymbolic approach grounded in social science theory and abductive reasoning. Our method automatically extracts rules to abduce the specific story elements needed to guide an LLM through a consistent and targeted narrative transformation. Across multiple LLMs, abduction-guided transformed stories shifted the narrative while maintaining the fidelity with the original story. For example, with GPT-4o we outperform the zero-shot LLM baseline by 55.88% for collectivistic to individualistic narrative shift while maintaining superior semantic similarity with the original stories (40.4% improvement in KL divergence). For individualistic to collectivistic transformation, we achieve comparable improvements. We show similar performance across both directions for Llama-4, and Grok-4 and competitive performance for Deepseek-R1. --- ### Subspace Geometry Governs Catastrophic Forgetting in Low-Rank Adaptation Authors: Brady Steele Published: 2026-02-10 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.02224v1 Low-Rank Adaptation (LoRA) has emerged as a parameter-efficient approach for adapting large pre-trained models, yet its behavior under continual learning remains poorly understood. We present a geometric theory characterizing catastrophic forgetting in LoRA through the lens of gradient subspace interactions. Our central finding is that forgetting is governed by a simple geometric law: $\mathcal{F} = α(1 - \cos^2θ_{\min}) + β$, where $θ_{\min}$ is the minimum principal angle between task gradient subspaces. This formulation reveals an approximate rank-invariance property, at high subspace angles, forgetting becomes largely independent of the adapter rank (coefficient of variation $\approx 0.8\%$ in controlled synthetic settings; CV $\approx 10$-$19\%$ on real benchmarks, suggesting this is regime-dependent rather than absolute). We validate our theory on synthetic tasks ($r=0.994$ correlation), Split-CIFAR100 with ViT-LoRA, and sequential GLUE with RoBERTa-LoRA. Our analysis reconciles seemingly contradictory findings in the literature: we show that rank affects forgetting only when task subspaces are similar (low angle), while orthogonal methods like O-LoRA provide minimal benefit when natural orthogonality is already high. These insights provide principled guidance for continual learning with parameter-efficient fine-tuning. --- ### Characterizing and Predicting Wildfire Evacuation Behavior: A Dual-Stage ML Approach Authors: Sazzad Bin Bashar Polock, Anandi Dutta, Subasish Das Published: 2026-02-10 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.02223v1 Wildfire evacuation behavior is highly variable and influenced by complex interactions among household resources, preparedness, and situational cues. Using a large-scale MTurk survey of residents in California, Colorado, and Oregon, this study integrates unsupervised and supervised machine learning methods to uncover latent behavioral typologies and predict key evacuation outcomes. Multiple Correspondence Analysis, K-Modes clustering, and Latent Class Analysis reveal consistent subgroups differentiated by vehicle access, disaster planning, technological resources, pet ownership, and residential stability. Complementary supervised models show that transportation mode can be predicted with high reliability from household characteristics, whereas evacuation timing remains difficult to classify due to its dependence on dynamic, real-time fire conditions. These findings advance data-driven understanding of wildfire evacuation behavior and demonstrate how machine learning can support targeted preparedness strategies, resource allocation, and equitable emergency planning. --- ### MedCalc-Bench Doesn't Measure What You Think: A Benchmark Audit and the Case for Open-Book Evaluation Authors: Artus Krohn-Grimberghe Published: 2026-02-10 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.02222v1 MedCalc-Bench is a widely used benchmark for evaluating LLM performance on clinical calculator tasks, with state-of-the-art direct prompting scores plateauing around 35% on the Verified split (HELM MedHELM leaderboard) and the best published approach-RL with verifiable rewards-reaching 74%. We present three contributions that challenge the benchmark's current framing. First, we conduct a systematic audit of the benchmark's calculator implementations, identifying and fixing over 20 errors ranging from critical formula inaccuracies to runtime bugs in a NeurIPS-published dataset. Second, we show that a simple intervention-providing the model with the calculator specification at inference time ("open-book" prompting)-raises accuracy from ~52% to 81-85% on GLM-4.6V and GLM-4.7, surpassing all published results including RL-trained systems, without any fine-tuning. Third, we establish an upper bound of 95-97% using GPT-5.2-Thinking, with residual errors attributable primarily to ground-truth issues and dataset ambiguities. Our findings suggest that MedCalc-Bench predominantly measures formula memorization and arithmetic precision rather than clinical reasoning, and would be better framed as a tool-use evaluation. --- ### MedFeat: Model-Aware and Explainability-Driven Feature Engineering with LLMs for Clinical Tabular Prediction Authors: Zizheng Zhang, Yiming Li, Justin Xu, Jinyu Wang, Rui Wang, Lei Song, Jiang Bian, David W Eyre, Jingjing Fu Published: 2026-02-10 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.02221v2 In clinical tabular prediction, classical machine learning models with feature engineering often outperform neural methods. LLMs are increasingly used to automate this process, acting as domain experts that propose diverse feature transformations to boost downstream performance. However, existing LLM-based methods decouple feature generation from the downstream model: the LLM receives no signal about which features currently drive predictions or where the model's representational capacity falls short, so proposals are neither targeted to promising regions of the feature space nor tailored to the learner's inductive bias. This shortcoming is amplified in healthcare data, which simultaneously exhibits class imbalance, heterogeneous feature spaces, and strict interpretability requirements. In this paper, we propose MedFeat, the first feature engineering framework inspired by the workflow of machine learning practitioners, leveraging model-awareness and feature importance signals to iteratively guide feature discovery for clinical tabular learning. We evaluate MedFeat on a broad range of challenging real-world clinical tasks and show that it statistically significantly outperforms state-of-the-art baselines, with an average improvement of more than 10% over the baseline across models with distinct inductive biases. --- ### Forecasting as Rendering: A 2D Gaussian Splatting Framework for Time Series Forecasting Authors: Yixin Wang, Yifan Hu, Peiyuan Liu, Naiqi Li, Tao Dai, Shu-Tao Xia Published: 2026-02-10 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2603.02220v2 Time series forecasting remains a challenging problem due to the intricate entanglement of intra-period fluctuations and inter-period trends. While recent advances have attempted to reshape 1D sequences into 2D period-phase representations, they suffer from two principal limitations. Firstly, treating reshaped tensors as static images results in a topological mismatch, as standard spatial operators sever chronological continuity at grid boundaries. Secondly, relying on uniform fixed-size representations allocates modeling capacity inefficiently and fails to provide the adaptive resolution required for compressible, non-stationary temporal patterns. To address these limitations, we introduce TimeGS, a novel framework that fundamentally shifts the forecasting paradigm from regression to 2D generative rendering. By reconceptualizing the future sequence as a latent 2D temporal surface, TimeGS utilizes the inherent anisotropy of Gaussian kernels to adaptively model complex variations with flexible geometric alignment. To realize this, we introduce a Multi-Basis Gaussian Kernel Generation (MB-GKG) block that synthesizes kernels from a fixed dictionary to stabilize optimization, and a Multi-Period Chronologically Continuous Rasterization (MP-CCR) block that enforces strict temporal continuity across periodic boundaries. Comprehensive experiments on standard benchmark datasets demonstrate that TimeGS attains state-of-the-art or competitive performance. The code is at https://github.com/yixinwang1/TimeGS. --- ### NExT-Guard: Training-Free Streaming Safeguard without Token-Level Labels Authors: Junfeng Fang, Nachuan Chen, Houcheng Jiang, Dan Zhang, Fei Shen, Xiang Wang, Xiangnan He, Tat-Seng Chua Published: 2026-02-10 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.02219v1 Large language models are increasingly deployed in streaming scenarios, rendering conventional post-hoc safeguards ineffective as they fail to interdict unsafe content in real-time. While streaming safeguards based on token-level supervised training could address this, they necessitate expensive annotations and suffer from severe overfitting. In this work, we challenge the paradigm that streaming safety must rely on token-level supervised training. Instead, it is an inherent capability of well-trained post-hoc safeguards, as they already encode token-level risk signals in hidden representations. Hence, we introduce NExT-Guard, a training-free framework that achieves streaming safeguards by monitoring interpretable latent features from Sparse Autoencoders (SAEs). It uses pretrained SAEs from publicly available base LLMs, enabling flexible, low-cost deployment without token-level supervision. Experimental results show that NExT-Guard outperforms both post-hoc and streaming safeguards based on supervised training, with superior robustness across models, SAE variants, and risk scenarios. These results make NExT-Guard a universal and scalable paradigm for real-time safety, accelerating the practical deployment of streaming safeguards. --- ### Self-Play Only Evolves When Self-Synthetic Pipeline Ensures Learnable Information Gain Authors: Wei Liu, Siya Qi, Yali Du, Yulan He Published: 2026-02-10 Categories: cs.LG, cs.AI, cs.CL, cs.IT arXiv: https://arxiv.org/abs/2603.02218v2 Large language models (LLMs) make it plausible to build systems that improve through self-evolving loops, but many existing proposals are better understood as self-play and often plateau quickly. A central failure mode is that the loop synthesises more data without increasing learnable information for the next iteration. Through experiments on a self-play coding task, we reveal that sustainable self-evolution requires a self-synthesised data pipeline with learnable information that increases across iterations. We identify triadic roles that self-evolving LLMs play: the Proposer, which generates tasks; the Solver, which attempts solutions; and the Verifier, which provides training signals, and we identify three system designs that jointly target learnable information gain from this triadic roles perspective. Asymmetric co-evolution closes a weak-to-strong-to-weak loop across roles. Capacity growth expands parameter and inference-time budgets to match rising learnable information. Proactive information seeking introduces external context and new task sources that prevent saturation. Together, these modules provide a measurable, system-level path from brittle self-play dynamics to sustained self-evolution. --- ### Is Retraining-Free Enough? The Necessity of Router Calibration for Efficient MoE Compression Authors: Sieun Hyeon, Jaeyoung Do Published: 2026-02-10 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.02217v1 Mixture-of-Experts (MoE) models scale capacity efficiently, but their massive parameter footprint creates a deployment-time memory bottleneck. We organize retraining-free MoE compression into three paradigms - Expert Pruning, Expert Editing, and Expert Merging - and show that persistent post-compression degradation largely stems from a neglected factor: router-expert mismatch when experts are changed but the router is left untouched. We argue that effective retraining-free compression should avoid updating expert parameters while allowing lightweight router calibration. To this end, we propose Router Knowledge Distillation (Router KD), which updates only a tiny fraction of parameters (the router) by distilling the original model's next-token distribution on unlabeled calibration data. Experiments across representative methods in all three paradigms demonstrate consistent performance recovery, with substantially larger gains in fine-grained MoEs (many small experts) than in coarse-grained MoEs due to their more complex routing decision boundaries. --- ### ATPO: Adaptive Tree Policy Optimization for Multi-Turn Medical Dialogue Authors: Ruike Cao, Shaojie Bai, Fugen Yao, Liang Dong, Jian Xu, Li Xiao Published: 2026-02-10 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.02216v1 Effective information seeking in multi-turn medical dialogues is critical for accurate diagnosis, especially when dealing with incomplete information. Aligning Large Language Models (LLMs) for these interactive scenarios is challenging due to the uncertainty inherent in user-agent interactions, which we formulate as a Hierarchical Markov Decision Process (H-MDP). While conventional Reinforcement Learning (RL) methods like Group Relative Policy Optimization (GRPO) struggle with long-horizon credit assignment and Proximal Policy Optimization (PPO) suffers from unstable value estimation in this context, we propose a novel uncertainty-aware Adaptive Tree Policy Optimization (ATPO) algorithm. Our method adaptively allocates the rollout budget to states with high uncertainty, quantified by a composite metric of Bellman error and action-value variance. This strategy enables more accurate value estimation, while fostering more efficient and diverse exploration. To mitigate the high computational cost of tree-based RL, we introduce two key optimizations: an uncertainty-guided pruning mechanism to minimize the number of rollouts, and an asynchronous search architecture that leverages KV cache reuse to maximize inference throughput. Extensive experiments on three public medical dialogue benchmarks demonstrate that our algorithm significantly outperforms several strong baselines, culminating in Qwen3-8B model surpassing the much larger GPT-4o ($+0.92\%$ accuracy). --- ### RxnNano:Training Compact LLMs for Chemical Reaction and Retrosynthesis Prediction via Hierarchical Curriculum Learning Authors: Ran Li, Shimin Di, Haowei LI, Luanshi Bu, Jiachuan Wang, Wangze Ni, Lei Chen Published: 2026-02-10 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.02215v1 Chemical reaction prediction is pivotal for accelerating drug discovery and synthesis planning. Despite advances in data-driven models, current approaches are hindered by an overemphasis on parameter and dataset scaling. Some methods coupled with evaluation techniques that bypass fundamental challenges in reaction representation and fail to capture deep chemical intuition like reaction common sense and {topological atom mapping logic}. We argue that the core challenge lies in instilling these knowledge into the models. To this end, we propose a unified framework that prioritizes chemical understanding over scale through three key innovations: (1) a {Latent Chemical Consistency} objective that models reactions as movements on a continuous chemical manifold, ensuring reversible and physically plausible transformations; (2) a {Hierarchical Cognitive Curriculum} that trains the model through progressive stages, from syntax mastery to semantic reasoning, building robust chemical intuition; (3) {Atom-Map Permutation Invariance (AMPI)}, which force the model to learn invariant relational topology and balance multi-task learning. (4)and structured plan-based reasoning to improve the performance of the LLMs. Our compact {0.5B-parameter model}, \textbf{RxnNano} significantly outperforms fine-tuned LLMs ten times larger (>7B) and all the domain baselines, achieving a 23.5\% Top-1 accuracy improvement on rigorous benchmarks without test-time augmentation. https://github.com/rlisml/RxnNano. --- ### Certainty-Validity: A Diagnostic Framework for Discrete Commitment Systems Authors: Datorien L. Anderson Published: 2026-02-10 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2603.00070v1 Standard evaluation metrics for machine learning -- accuracy, precision, recall, and AUROC -- assume that all errors are equivalent: a confident incorrect prediction is penalized identically to an uncertain one. For discrete commitment systems (architectures that select committed states {-W, 0, +W}), this assumption is epistemologically flawed. We introduce the Certainty-Validity (CVS) Framework, a diagnostic method that decomposes model performance into a 2x2 matrix distinguishing high/low certainty from valid/invalid predictions. This framework reveals a critical failure mode hidden by standard accuracy: Confident-Incorrect (CI) behavior, where models hallucinate structure in ambiguous data. Through ablation experiments on Fashion-MNIST, EMNIST, and IMDB, we analyze the "83% Ambiguity Ceiling" -- a stopping point where this specific discrete architecture consistently plateaus on noisy benchmarks. Unlike continuous models that can surpass this ceiling by memorizing texture or statistical noise, the discrete model refuses to commit to ambiguous samples. We show that this refusal is not a failure but a feature: the model stops where structural evidence ends. However, standard training on ambiguous data eventually forces Benign Overfitting, causing a pathological migration from Uncertain-Incorrect (appropriate doubt) to Confident-Incorrect (hallucination). We propose that "good training" for reasoning systems must be defined not by accuracy, but by maximizing the Certainty-Validity Score (CVS) -- ensuring the model knows where to stop. --- ### The Global Landscape of Environmental AI Regulation: From the Cost of Reasoning to a Right to Green AI Authors: Kai Ebert, Boris Gamazaychikov, Philipp Hacker, Sasha Luccioni Published: 2026-02-10 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2603.00068v2 Artificial intelligence (AI) systems impose substantial and growing environmental costs, yet transparency about these impacts has declined even as their deployment has accelerated. This paper makes three contributions. First, we collate empirical evidence that generative Web search and reasoning models - which have proliferated in 2025 - come with much higher cumulative environmental impacts than previous generations of AI approaches. Second, we map the global regulatory landscape across eleven jurisdictions and find that the manner in which environmental governance operates (predominantly at the facility-level rather than the model-level, with a focus on training rather than inference, with limited AI-specific energy disclosure requirements outside the EU) limits its applicability. Third, to address this, we propose a three-pronged policy response: mandatory model-level transparency that covers inference consumption, benchmarks, and compute locations; user rights to opt out of unnecessary generative AI integration and to select environmentally optimized models; and international coordination to prevent regulatory arbitrage. We conclude with concrete legislative proposals - including amendments to the EU AI Act, Consumer Rights Directive, and Digital Services Act - that could serve as templates for other jurisdictions. --- ### A Representation-Consistent Gated Recurrent Framework for Robust Medical Time-Series Classification Authors: Maitri Krishna Sai Published: 2026-02-10 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.00067v1 Medical time-series data are characterized by irregular sampling, high noise levels, missing values, and strong inter-feature dependencies. Recurrent neural networks (RNNs), particularly gated architectures such as Long Short-Term Memory (LSTM) and Gated Recurrent Units (GRU), are widely used for modeling such data due to their ability to capture temporal dependencies. However, standard gated recurrent models do not explicitly constrain the evolution of latent representations over time, leading to representation drift and instability under noisy or incomplete inputs. In this work, we propose a representation-consistent gated recurrent framework (RC-GRF) that introduces a principled regularization strategy to enforce temporal consistency in hidden-state representations. The proposed framework is model-agnostic and can be integrated into existing gated recurrent architectures without modifying their internal gating mechanisms. We provide a theoretical analysis demonstrating how the consistency constraint bounds hidden-state divergence and improves stability. Extensive experiments on medical time-series classification benchmarks show that the proposed approach improves robustness, reduces variance, and enhances generalization performance, particularly in noisy and low-sample settings. --- ### Contesting Artificial Moral Agents Authors: Aisha Aijaz Published: 2026-02-10 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2603.00066v1 There has been much discourse on the ethics of AI, to the extent that there are now systems that possess inherent moral reasoning. Such machines are now formally known as Artificial Moral Agents or AMAs. However, there is a requirement for a dedicated framework that can contest the morality of these systems. This paper proposes a 5E framework for contesting AMAs based on five grounds: ethical, epistemological, explainable, empirical, and evaluative. It further includes the spheres of ethical influences at individual, local, societal, and global levels. Lastly, the framework contributes a provisional timeline that indicates where developers of AMA technologies may anticipate contestation, or may self-contest in order to adhere to value-aligned development of truly moral AI systems. --- ### Self-Service or Not? How to Guide Practitioners in Classifying AI Systems Under the EU AI Act Authors: Ronald Schnitzer, Maximilian Hoeving, Sonja Zillner Published: 2026-02-10 Categories: cs.CY, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2603.00065v1 In August 2024, the EU Artificial Intelligence Act (AIA) came into force, marking the world's first large-scale regulatory framework for AI. Central to the AIA is a risk-based approach, aligning regulatory obligations with the potential harm posed by AI systems. To operationalize this, the AIA defines a Risk Classification Scheme (RCS), categorizing systems into four levels of risk. While this aligns with the theoretical foundations of risk-based regulations, the practical application of the RCS is complex and requires expertise across legal, technical, and domain-specific areas. Despite increasing academic discussion, little empirical research has explored how practitioners apply the RCS in real-world contexts. This study addresses this gap by evaluating how industrial practitioners apply the RCS using a self-service, web-based decision-support tool. Following a Design Science Research (DSR) approach, two evaluation phases involving 78 practitioners across diverse domains were conducted. Our findings highlight critical challenges in interpreting legal definitions and regulatory scope, and show that targeted support, such as clear explanations and practical examples, can significantly enhance the risk classification process. The study provides actionable insights for tool designers and policymakers aiming to support AIA compliance in practice. --- ### The minimal width of universal $p$-adic ReLU neural networks Authors: Sándor Z. Kiss, Ambrus Pál Published: 2026-02-10 Categories: math.NT, cs.LG arXiv: https://arxiv.org/abs/2603.00064v1 We determine the minimal width of $p$-adic neural networks with the universal approximation property for continuous $\mathbb Q_p$-valued functions on compact open subsets with respect to the $L_q$ norms and the $C_1$ norm, where the activation function is a natural $p$-adic analogue of the ReLU function. --- ### Measuring What AI Systems Might Do: Towards A Measurement Science in AI Authors: Konstantinos Voudouris, Mirko Thalmann, Alex Kipnis, José Hernández-Orallo, Eric Schulz Published: 2026-02-10 Categories: cs.CY, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.00063v1 Scientists, policy-makers, business leaders, and members of the public care about what modern artificial intelligence systems are disposed to do. Yet terms such as capabilities, propensities, skills, values, and abilities are routinely used interchangeably and conflated with observable performance, with AI evaluation practices rarely specifying what quantity they purport to measure. We argue that capabilities and propensities are dispositional properties - stable features of systems characterised by counterfactual relationships between contextual conditions and behavioural outputs. Measuring a disposition requires (i) hypothesising which contextual properties are causally relevant, (ii) independently operationalising and measuring those properties, and (iii) empirically mapping how variation in those properties affects the probability of the behaviour. Dominant approaches to AI evaluation, from benchmark averages to data-driven latent-variable models such as Item Response Theory, bypass these steps entirely. Building on ideas from philosophy of science, measurement theory, and cognitive science, we develop a principled account of AI capabilities and propensities as dispositions, show why prevailing evaluation practices fail to measure them, and outline what disposition-respecting, scientifically defensible AI evaluation would require. --- ### The Hidden Costs of Domain Fine-Tuning: Pii-Bearing Data Degrades Safety and Increases Leakage Authors: Jayesh Choudhari, Piyush Kumar Singh Published: 2026-02-10 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2603.00061v1 Domain fine-tuning is a common path to deploy small instruction-tuned language models as customer-support assistants, yet its effects on safety-aligned behavior and privacy are not well understood. In real deployments, such assistants receive a mixture of benign in-domain requests and out-of-domain user queries that are emotional, philosophical, or adversarial. Even when the target domain is benign, specialization may shift model behavior in ways that weaken refusal, increase harmful compliance, and induce privacy leakage. We present a controlled empirical study of how training data composition (presence vs.\ removal of PII) and fine-tuning configuration (role-swapping (RS)) shape safety and out-of-domain behavior in open-source chat models up to 8B parameters. We fine-tune each model on 5{,}000 real booking-support message pairs under three settings: \textsc{NoPII-NoRS}, \textsc{PII-NoRS}, and \textsc{PII-RS} (role-swapped). We evaluate safety using \textsc{SORRY-Bench}~\cite{xie2024sorry} adversarial prompts and assess out-of-domain behavior using a suite of philosophical questions~\cite{betley2025emergent}. Across models, domain fine-tuning causes a large distributional shift from high-quality refusals toward harmful compliance on \textsc{SORRY-Bench}, with the most severe degradation when PII is present in the fine-tuning data. For example, macro-averaged strong refusal drops from $42.6\%$ in base models to single digits after fine-tuning, while PII-bearing runs additionally exhibit double-digit rates of harmful responses with PII leakage. On philosophical queries, fine-tuned models frequently exhibit domain anchoring and, when trained with PII, leak sensitive identifiers in irrelevant contexts. Role-swapping partially mitigates PII leakage but does not reliably restore refusal behavior. --- ### Learning Under Extreme Data Scarcity: Subject-Level Evaluation of Lightweight CNNs for fMRI-Based Prodromal Parkinsons Detection Authors: Naimur Rahman Published: 2026-02-10 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.00060v1 Deep learning is often applied in settings where data are limited, correlated, and difficult to obtain, yet evaluation practices do not always reflect these constraints. Neuroimaging for prodromal Parkinsons disease is one such case, where subject numbers are small and individual scans produce many highly related samples. This work examines prodromal Parkinsons detection from resting-state fMRI as a machine learning problem centered on learning under extreme data scarcity. Using fMRI data from 40 subjects, including 20 prodromal Parkinsons cases and 20 healthy controls, ImageNet-pretrained convolutional neural networks are fine-tuned and evaluated under two different data partitioning strategies. Results show that commonly used image-level splits allow slices from the same subject to appear in both training and test sets, leading to severe information leakage and near-perfect accuracy. When a strict subject-level split is enforced, performance drops substantially, yielding test accuracies between 60 and 81 percent. Models with different capacity profiles are compared, including VGG19, Inception V3, Inception ResNet V2, and the lightweight MobileNet V1. Under subject-level evaluation, MobileNet demonstrates the most reliable generalization, outperforming deeper architectures despite having significantly fewer parameters. These results indicate that in extreme low-data regimes, evaluation strategy and model capacity have a greater impact on performance than architectural depth. Although the analysis is limited to a single cohort of 40 subjects and does not include external validation or cross-validation, it provides a concrete case study and practical recommendations for evaluating deep learning models under severe data scarcity. --- ### Stochastic Parrots or Singing in Harmony? Testing Five Leading LLMs for their Ability to Replicate a Human Survey with Synthetic Data Authors: Jason Miklian, Kristian Hoelscher, John E. Katsos Published: 2026-02-10 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2603.00059v3 How well can AI-derived synthetic research data replicate the responses of human participants? An emerging literature has begun to engage with this question, which carries deep implications for organizational research practice. This article presents a comparison between a human-respondent survey of 420 Silicon Valley coders and developers and synthetic survey data designed to simulate real survey takers generated by five leading Generative AI Large Language Models: ChatGPT Thinking 5 Pro, Claude Sonnet 4.5 Pro plus Claude CoWork 1.123, Gemini Advanced 2.5 Pro, Incredible 1.0, and DeepSeek 3.2. Our findings reveal that while AI agents produced technically plausible results that lean more towards replicability and harmonization than assumed, none were able to capture the counterintuitive insights that made the human survey valuable. Moreover, deviations grouped together for all models, leaving the real data as the outlier. Our key finding is that while leading LLMs are increasingly being used to scale, replicate and replace human survey responses in research, these advances only show an increased capacity to parrot conventional wisdom in harmony with each other rather than revealing novel findings. If synthetic respondents are used in future research, we need more replicable validation protocols and reporting standards for when and where synthetic survey data can be used responsibly, a gap that this paper fills. Our results suggest that synthetic survey responses cannot meaningfully model real human social beliefs within organizations, particularly in contexts lacking previously documented evidence. We conclude that synthetic survey-based research should be cast not as a substitute for rigorous survey methods, but as an increasingly reliable pre- or post-fieldwork instrument for identifying societal assumptions, conventional wisdoms, and other expectations about research populations. --- ### PaperRepro: Automated Computational Reproducibility Assessment for Social Science Papers Authors: Linhao Zhang, Tong Xia, Jinghua Piao, Lizhen Cui, Yong Li Published: 2026-02-10 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2603.00058v1 Computational reproducibility is essential for the credibility of scientific findings, particularly in the social sciences, where findings often inform real-world decisions. Manual reproducibility assessment is costly and time-consuming, as it is nontrivial to reproduce the reported findings using the authors' released code and data. Recent advances in large models (LMs) have inspired agent-based approaches for automated reproducibility assessment. However, existing approaches often struggle due to limited context capacity, inadequate task-specific tooling, and insufficient result capture. To address these, we propose PaperRepro, a novel two-stage, multi-agent approach that separates execution from evaluation. In the execution stage, agents execute the reproduction package and edit the code to capture reproduced results as explicit artifacts. In the evaluation stage, agents evaluate reproducibility using explicit evidence. PaperRepro assigns distinct responsibilities to agents and equips them with task-specific tools and expert prompts, mitigating context and tooling limitations. It further maximizes the LM's coding capability to enable more complete result capture for evaluation. On REPRO-Bench, a social science reproducibility assessment benchmark, PaperRepro achieves the best overall performance, with a 21.9% relative improvement in score-agreement accuracy over the strongest prior baseline. We further refine the benchmark and introduce REPRO-Bench-S, a benchmark stratified by execution difficulty for more diagnostic evaluation of automated reproducibility assessment systems. Our code and data are publicly available --- ### "Bespoke Bots": Diverse Instructor Needs for Customizing Generative AI Classroom Chatbots Authors: Irene Hou, Zeyu Xiong, Philip J. Guo, April Yi Wang Published: 2026-02-10 Categories: cs.CY, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2603.00057v1 Instructors are increasingly experimenting with AI chatbots for classroom support. To investigate how instructors adapt chatbots to their own contexts, we first analyzed existing resources that provide prompts for educational purposes. We identified ten common categories of customization, such as persona, guardrails, and personalization. We then conducted interviews with ten university STEM instructors and asked them to card-sort the categories into priorities. We found that instructors consistently prioritized the ability to customize chatbot behavior to align with course materials and pedagogical strategies and de-prioritized customizing persona/tone. However, their prioritization of other categories varied significantly by course size, discipline, and teaching style, even across courses taught by the same individual, highlighting that no single design can meet all contexts. These findings suggest that modular AI chatbots may provide a promising path forward. We offer design implications for educational developers building the next generation of customizable classroom AI systems. --- ### How effective are VLMs in assisting humans in inferring the quality of mental models from Multimodal short answers? Authors: Pritam Sil, Durgaprasad Karnam, Vinay Reddy Venumuddala, Pushpak Bhattacharyya Published: 2026-02-10 Categories: cs.CY, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.00056v2 STEM Mental models can play a critical role in assessing students' conceptual understanding of a topic. They not only offer insights into what students know but also into how effectively they can apply, relate to, and integrate concepts across various contexts. Thus, students' responses are critical markers of the quality of their understanding and not entities that should be merely graded. However, inferring these mental models from student answers is challenging as it requires deep reasoning skills. We propose MMGrader, an approach that infers the quality of students' mental models from their multimodal responses using concept graphs as an analytical framework. In our evaluation with 9 openly available models, we found that the best-performing models fall short of human-level performance. This is because they only achieved an accuracy of approximately 40%, a prediction error of 1.1 units, and a scoring distribution fairly aligned with human scoring patterns. With improved accuracy, these can be highly effective assistants to teachers in inferring the mental models of their entire classrooms, enabling them to do so efficiently and help improve their pedagogies more effectively by designing targeted help sessions and lectures that strengthen areas where students collectively demonstrate lower proficiency. --- ### How effective are VLMs in assisting humans in inferring the quality of mental models from Multimodal short answers? Authors: Pritam Sil, Durgaprasad Karnam, Vinay Reddy Venumuddala, Pushpak Bhattacharyya Published: 2026-02-10 Categories: cs.CY, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.00056v1 STEM Mental models can play a critical role in assessing students' conceptual understanding of a topic. They not only offer insights into what students know but also into how effectively they can apply, relate to, and integrate concepts across various contexts. Thus, students' responses are critical markers of the quality of their understanding and not entities that should be merely graded. However, inferring these mental models from student answers is challenging as it requires deep reasoning skills. We propose MMGrader, an approach that infers the quality of students' mental models from their multimodal responses using concept graphs as an analytical framework. In our evaluation with 9 openly available models, we found that the best-performing models fall short of human-level performance. This is because they only achieved an accuracy of approximately 40%, a prediction error of 1.1 units, and a scoring distribution fairly aligned with human scoring patterns. With improved accuracy, these can be highly effective assistants to teachers in inferring the mental models of their entire classrooms, enabling them to do so efficiently and help improve their pedagogies more effectively by designing targeted help sessions and lectures that strengthen areas where students collectively demonstrate lower proficiency. --- ### M3-AD: Reflection-aware Multi-modal, Multi-category, and Multi-dimensional Benchmark and Framework for Industrial Anomaly Detection Authors: Chao Huang, Yanhui Li, Yunkang Cao, Wei Wang, Hongxi Huang, Jie Wen, Wenqi Ren, Xiaochun Cao Published: 2026-02-10 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.00055v1 Although multimodal large language models (MLLMs) have advanced industrial anomaly detection toward a zero-shot paradigm, they still tend to produce high-confidence yet unreliable decisions in fine-grained and structurally complex industrial scenarios, and lack effective self-corrective mechanisms. To address this issue, we propose M3-AD, a unified reflection-aware multimodal framework for industrial anomaly detection. M3-AD comprises two complementary data resources: M3-AD-FT, designed for reflection-aligned fine-tuning, and M3-AD-Bench, designed for systematic cross-category evaluation, together providing a foundation for reflection-aware learning and reliability assessment. Building upon this foundation, we propose RA-Monitor, which models reflection as a learnable decision revision process and guides models to perform controlled self-correction when initial judgments are unreliable, thereby improving decision robustness. Extensive experiments conducted on M3-AD-Bench demonstrate that RA-Monitor outperforms multiple open-source and commercial MLLMs in zero-shot anomaly detection and anomaly analysis tasks. Code will be released at https://github.com/Yanhui-Lee/M3-AD. --- ### Expert Divergence Learning for MoE-based Language Models Authors: Jiaang Li, Haibin Chen, Langming Liu, Yujin Yuan, Yadao Wang, Yizhen Zhang, Chengting Yu, Xin Tong, Weidong Zhang, Shilei Liu, Wenbo Su, Bo Zheng Published: 2026-02-10 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.00054v1 The Mixture-of-Experts (MoE) architecture is a powerful technique for scaling language models, yet it often suffers from expert homogenization, where experts learn redundant functionalities, thereby limiting MoE's full potential. To address this, we introduce Expert Divergence Learning, a novel pre-training strategy that explicitly encourages functional specialization among experts. Our method incorporates a label-driven auxiliary loss that leverages domain labels inherent in pre-training corpora to maximize the Jensen-Shannon Divergence between the expert routing distributions of different data domains. This optimization objective guides the model to develop diverged routing policies for varied domains and closer routing policies for the same domain, which leads to emergent and organized expert specialization. We validate our approach by pre-training MoE models of up to 15 billion parameters from scratch. Experimental results demonstrate that models trained with Expert Divergence Learning not only achieve a lower language modeling loss but also exhibit significant performance improvements across a diverse range of downstream benchmarks. Further analysis confirms that our method effectively mitigates expert homogenization and brings greater functional specialization, all with negligible computational overhead during training. --- ### Mag-Mamba: Modeling Coupled spatiotemporal Asymmetry for POI Recommendation Authors: Zhuoxuan Li, Tangwei Ye, Jieyuan Pei, Haina Liang, Zhongyuan Lai, Zihan Liu, Yiming Wu, Qi Zhang, Liang Hu Published: 2026-02-10 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.00053v1 Next Point-of-Interest (POI) recommendation is a critical task in location-based services, yet it faces the fundamental challenge of coupled spatiotemporal asymmetry inherent in urban mobility. Specifically, transition intents between locations exhibit high asymmetry and are dynamically conditioned on time. Existing methods, typically built on graph or sequence backbones, rely on symmetric operators or real-valued aggregations, struggling to unify the modeling of time-varying global directionality. To address this limitation, we propose Mag-Mamba, a framework whose core insight lies in modeling spatiotemporal asymmetry as phase-driven rotational dynamics in the complex domain. Based on this, we first devise a Time-conditioned Magnetic Phase Encoder that constructs a time-conditioned Magnetic Laplacian on the geographic adjacency graph, utilizing edge phase differences to characterize the globally evolving spatial directionality. Subsequently, we introduce a Complex-valued Mamba module that generalizes traditional scalar state decay into joint decay-rotation dynamics, explicitly modulated by both time intervals and magnetic geographic priors. Extensive experiments on three real-world datasets demonstrate that Mag-Mamba achieves significant performance improvements over state-of-the-art baselines. --- ### Knowledge-guided generative surrogate modeling for high-dimensional design optimization under scarce data Authors: Bingran Wang, Seongha Jeong, Sebastiaan P. C. van Schie, Dongyeon Han, Jaeho Min, John T. Hwang Published: 2026-02-10 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.00052v1 Surrogate models are widely used in mechanical design and manufacturing process optimization, where high-fidelity computational models may be unavailable or prohibitively expensive. Their effectiveness, however, is often limited by data scarcity, as purely data-driven surrogates struggle to achieve high predictive accuracy in such situations. Subject matter experts (SMEs) frequently possess valuable domain knowledge about functional relationships, yet few surrogate modeling techniques can systematically integrate this information with limited data. We address this challenge with RBF-Gen, a knowledge-guided surrogate modeling framework that combines scarce data with domain knowledge. This method constructs a radial basis function (RBF) space with more centers than training samples and leverages the null space via a generator network, inspired by the principle of maximum information preservation. The introduced latent variables provide a principled mechanism to encode structural relationships and distributional priors during training, thereby guiding the surrogate toward physically meaningful solutions. Numerical studies demonstrate that RBF-Gen significantly outperforms standard RBF surrogates on 1D and 2D structural optimization problems in data-scarce settings, and achieves superior predictive accuracy on a real-world semiconductor manufacturing dataset. These results highlight the potential of combining limited experimental data with domain expertise to enable accurate and practical surrogate modeling in mechanical and process design problems. --- ### LitBench: A Graph-Centric Large Language Model Benchmarking Tool For Literature Tasks Authors: Andreas Varvarigos, Ali Maatouk, Jiasheng Zhang, Ngoc Bui, Jialin Chen, Leandros Tassiulas, Rex Ying Published: 2026-02-10 Categories: cs.DL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.00051v1 While large language models (LLMs) have become the de facto framework for literature-related tasks, they still struggle to function as domain-specific literature agents due to their inability to connect pieces of knowledge and reason across domain-specific contexts, terminologies, and nomenclatures. This challenge underscores the need for a tool that facilitates such domain-specific adaptation and enables rigorous benchmarking across literature tasks. To that end, we introduce LitBench, a benchmarking tool designed to enable the development and evaluation of domain-specific LLMs tailored to literature-related tasks. At its core, LitBench uses a data curation process that generates domain-specific literature sub-graphs and constructs training and evaluation datasets based on the textual attributes of the resulting nodes and edges. The tool is designed for flexibility, supporting the curation of literature graphs across any domain chosen by the user, whether high-level fields or specialized interdisciplinary areas. In addition to dataset curation, LitBench defines a comprehensive suite of literature tasks, ranging from node and edge level analyses to advanced applications such as related work generation. These tasks enable LLMs to internalize domain-specific knowledge and relationships embedded in the curated graph during training, while also supporting rigorous evaluation of model performance. Our results show that small domain-specific LLMs trained and evaluated on LitBench datasets achieve competitive performance compared to state-of-the-art models like GPT-4o and DeepSeek-R1. To enhance accessibility and ease of use, we open-source the tool along with an AI agent tool that streamlines data curation, model training, and evaluation. --- ### AI-Generated Letters from the Future: A Randomized Test of Personalized Climate Communication Authors: Nattavudh Powdthavee, Pat Pataranutaporn, Sandra J. Geiger, Louisa Richter, Mathew P. White Published: 2026-02-10 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2603.00050v1 We examined whether personalized, AI-generated letters from the future can increase public engagement with climate action. In a preregistered online experiment with 1,654 U.S. parents, participants were randomly assigned to receive either a fact-based climate report, an AI-generated letter from a generic future person, or an AI-generated letter framed as written by their future child. Although both narrative conditions increased empathic concern for future generations, neither had a detectable effect on stated climate policy support or donations to an environmental charity. Personalizing the message as coming from one's future child did not enhance its impact. Exploratory analyses suggest that both narratives led to more emotionally differentiated appraisals of future scenarios, yet also made desirable climate outcomes seem less likely. These findings highlight key constraints on the effectiveness of AI-generated narrative interventions and underscore the importance of balancing emotional resonance with perceived credibility in climate communication. --- ### BiJEPA: Bi-directional Joint Embedding Predictive Architecture for Symmetric Representation Learning Authors: Yongchao Huang Published: 2026-02-10 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.00049v1 Self-Supervised Learning (SSL) has shifted from pixel-level reconstruction to latent space prediction, spearheaded by the Joint Embedding Predictive Architecture (JEPA). While effective, standard JEPA models typically rely on a uni-directional prediction mechanism (e.g. Context $\to$ Target), potentially neglecting the informative signal inherent in the inverse relationship, degrading its performance. In this work, we propose \textbf{BiJEPA}, a \textit{Bi-Directional Joint Embedding Predictive Architecture} that enforces cycle-consistent predictability between data segments. We address the inherent instability of symmetric prediction (representation explosion) by introducing a critical norm regularization mechanism on the representation vectors. We evaluate BiJEPA on three distinct modalities: synthetic periodic signals, chaotic Lorenz attractor trajectories, and high-dimensional image data (MNIST). Our results demonstrate that BiJEPA achieves stable convergence without collapse, captures the semantic structure of chaotic systems, and learns robust temporal and spatial representations capable of generation and generalisation, offering a more holistic approach to representation learning. --- ### Red Teaming LLMs as Socio-Technical Practice: From Exploration and Data Creation to Evaluation Authors: Adriana Alvarado Garcia, Ruyuan Wan, Ozioma C. Oguine, Karla Badillo-Urquiola Published: 2026-02-10 Categories: cs.CY, cs.AI, cs.CL, cs.HC arXiv: https://arxiv.org/abs/2602.18483v1 Recently, red teaming, with roots in security, has become a key evaluative approach to ensure the safety and reliability of Generative Artificial Intelligence. However, most existing work emphasizes technical benchmarks and attack success rates, leaving the socio-technical practices of how red teaming datasets are defined, created, and evaluated under-examined. Drawing on 22 interviews with practitioners who design and evaluate red teaming datasets, we examine the data practices and standards that underpin this work. Because adversarial datasets determine the scope and accuracy of model evaluations, they are critical artifacts for assessing potential harms from large language models. Our contributions are first, empirical evidence of practitioners conceptualizing red teaming and developing and evaluating red teaming datasets. Second, we reflect on how practitioners' conceptualization of risk leads to overlooking the context, interaction type, and user specificity. We conclude with three opportunities for HCI researchers to expand the conceptualization and data practices for red-teaming. --- ### Boltzmann Generators for Condensed Matter via Riemannian Flow Matching Authors: Emil Hoffmann, Maximilian Schebek, Leon Klein, Frank Noé, Jutta Rogal Published: 2026-02-10 Categories: physics.comp-ph, cond-mat.stat-mech, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2602.18482v2 Sampling equilibrium distributions is fundamental to statistical mechanics. While flow matching has emerged as scalable state-of-the-art paradigm for generative modeling, its potential for equilibrium sampling in condensed-phase systems remains largely unexplored. We address this by incorporating the periodicity inherent to these systems into continuous normalizing flows using Riemannian flow matching. The high computational cost of exact density estimation intrinsic to continuous normalizing flows is mitigated by using Hutchinson's trace estimator, utilizing a crucial bias-correction step based on cumulant expansion to render the stochastic estimates suitable for rigorous thermodynamic reweighting. Our approach is validated on monatomic ice, demonstrating the ability to train on systems of unprecedented size and obtain highly accurate free energy estimates without the need for traditional multistage estimators. --- ### AlphaForgeBench: Benchmarking End-to-End Trading Strategy Design with Large Language Models Authors: Wentao Zhang, Mingxuan Zhao, Jincheng Gao, Jieshun You, Huaiyu Jia, Yilei Zhao, Bo An, Shuo Sun Published: 2026-02-10 Categories: q-fin.TR, cs.AI arXiv: https://arxiv.org/abs/2602.18481v2 The rapid advancement of Large Language Models (LLMs) has led to a surge of financial benchmarks, evolving from static knowledge evaluation toward interactive trading simulations. However, existing frameworks for evaluating real-time trading largely overlook a critical failure mode: the severe behavioral instability of LLMs in sequential decision-making under financial uncertainty. Through extensive experiments, we show that when deployed as trading agents, LLMs exhibit extreme run-to-run variance, generate inconsistent action sequences even under deterministic decoding, and frequently produce irrational action flipping across adjacent time steps. We attribute these behaviors to the stateless autoregressive nature of LLMs, which lack persistent memory of prior actions, together with their sensitivity to continuous-to-discrete action mappings in portfolio allocation tasks. These deficiencies fundamentally undermine the reliability and reproducibility of many existing online and offline trading benchmarks. To address these limitations, we propose AlphaForgeBench, a principled evaluation framework that redefines LLMs as quantitative researchers rather than stochastic trading agents. Instead of producing discrete trading actions, AlphaForgeBench requires models to generate executable alpha factors and compose factor-based trading strategies grounded in financial knowledge. This paradigm decouples reasoning from execution mechanics, enabling deterministic and reproducible evaluation while remaining aligned with real-world quantitative research workflows. Extensive experiments across multiple state-of-the-art LLMs demonstrate that AlphaForgeBench eliminates execution-induced instability and provides a rigorous benchmark for evaluating financial reasoning, strategy formulation, and alpha discovery. Webpage at https://finbrain-lab-hkustgz.github.io/AlphaForgeBench --- ### AgentCAT: An LLM Agent for Extracting and Analyzing Catalytic Reaction Data from Chemical Engineering Literature Authors: Wei Yang, Zihao Liu, Tao Tan, Xiao Hu, Hong Xie, Lulu Li Xin Li, Jianyu Han, Defu Lian, Mao Ye Published: 2026-02-10 Categories: physics.chem-ph, cs.AI, cs.DL arXiv: https://arxiv.org/abs/2602.18479v1 This paper presents a large language model (LLM) agent named AgentCAT, which extracts and analyzes catalytic reaction data from chemical engineering papers, %and supports natural language based interactive analysis of the extracted data. AgentCAT serves as an alternative to overcome the long-standing data bottleneck in chemical engineering field, and its natural language based interactive data analysis functionality is friendly to the community. AgentCAT also presents a formal abstraction and challenge analysis of the catalytic reaction data extraction task in an artificial intelligence-friendly manner. This abstraction would help the artificial intelligence community understand this problem and in turn would attract more attention to address it. Technically, the complex catalytic process leads to complicated dependency structure in catalytic reaction data with respect to elementary reaction steps, molecular behaviors, measurement evidence, etc. This dependency structure makes it challenging to guarantee the correctness and completeness of data extraction, as well as representing them for analysis. AgentCAT addresses this challenge and it makes four folds of technical contributions: (1) a schema-governed extraction pipeline with progressive schema evolution, enabling robust data extraction from chemical engineering papers; (2) a dependency-aware reaction-network knowledge graph that links catalysts/active sites, synthesis-derived descriptors, mechanistic claims with evidence, and macroscopic outcomes, preserving process coupling and traceability; (3) a general querying module that supports natural-language exploration and visualization over the constructed graph for cross-paper analysis; (4) an evaluation on $\sim$800 peer-reviewed chemical engineering publications demonstrating the effectiveness of AgentCAT. --- ### Parallel Complex Diffusion for Scalable Time Series Generation Authors: Rongyao Cai, Yuxi Wan, Kexin Zhang, Ming Jin, Zhiqiang Ge, Qingsong Wen, Yong Liu Published: 2026-02-10 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.17706v2 Diffusion models learn data distributions indirectly through denoising, making the difficulty of generative modeling closely tied to the dependency structure of data. For time series, strong temporal dependence forces the noise / score estimator to recover highly entangled cross-time relationships, leading to the curse of entanglement. We mitigate this burden by changing the topology of the diffusion space: the Discrete Fourier Transform (DFT) decomposes temporal dependencies into spectral modes, diagonalizing second-order dependency structure and better aligning the data manifold with isotropic Gaussian noise and homogeneous diffusion dynamics. However, existing frequency-aware diffusion methods mainly use the DFT to design estimator blocks under temporal DDPM/SDE frameworks, while frequency-native diffusion paths face a mathematical barrier from complex-valued dynamics. We propose PaCoDi (Parallel Complex Diffusion), a frequency-native diffusion framework that constructs the diffusion path in the spectral domain while replacing the complex-valued estimator with parallel real-valued estimators for real and imaginary components. Theoretically, we prove the statistical orthogonality of spectral Gaussian noise, establish quadrature forward transitions and conditional reverse factorization, and extend discrete PaCoDi to continuous-time spectral SDEs through a Spectral Wiener Process. We further introduce a Mean Field Theory approximation with an Interactive Correction Branch to handle marginal coupling, and exploit Hermitian symmetry to reduce 50% attention FLOPs without information loss. Extensive experiments on unconditional and conditional time series generation demonstrate superior generative quality and computational efficiency against 5 SOTA baselines in 5 benchmarks, respectively. Code is available at https://github.com/RongyaoCai/PaCoDi. --- ### GPU-Accelerated Algorithms for Graph Vector Search: Taxonomy, Empirical Study, and Research Directions Authors: Yaowen Liu, Xuejia Chen, Anxin Tian, Haoyang Li, Qinbin Li, Xin Zhang, Alexander Zhou, Chen Jason Zhang, Qing Li, Lei Chen Published: 2026-02-10 Categories: cs.DB, cs.AI arXiv: https://arxiv.org/abs/2602.16719v1 Approximate Nearest Neighbor Search (ANNS) underpins many large-scale data mining and machine learning applications, with efficient retrieval increasingly hinging on GPU acceleration as dataset sizes grow. Although graph-based approaches represent the state of the art in approximate nearest neighbor search, there is a lack of systematic understanding regarding their optimization for modern GPU architectures and their end-to-end effectiveness in practical scenarios. In this work, we present a comprehensive survey and experimental study of GPU-accelerated graph-based vector search algorithms. We establish a detailed taxonomy of GPU optimization strategies and clarify the mapping between algorithmic tasks and hardware execution units within GPUs. Through a thorough evaluation of six leading algorithms on eight large-scale benchmark datasets, we assess both graph index construction and query search performance. Our analysis reveals that distance computation remains the primary computational bottleneck, while data transfer between the host CPU and GPU emerges as the dominant factor influencing real-world latency at large scale. We also highlight key trade-offs in scalability and memory usage across different system designs. Our findings offer clear guidelines for designing scalable and robust GPU-powered approximate nearest neighbor search systems, and provide a comprehensive benchmark for the knowledge discovery and data mining community. ---