Recent advances in Reinforcement Learning (RL) have substantially improved the capabilities of autonomous search agents, enabling sophisticated planning, and iterative retrieval over dynamic information sources. However, optimizing language models for specialized search behaviors often incurs an alignment tax, where gains in search performance come at the expense of general-purpose capabilities, limiting their effectiveness as universal assistants.
Brain tissue microstructure estimation with machine learning provides higher computational efficiency than conventional fitting. However, machine learning still presents important limitations that hamper its clinical utility.
Extending the neural-operator element method from individually trained, fixed-geometry neural elements to a library of reusable, geometry-parameterized element types fails structurally: a field-predicting operator trained by value regression induces an energy whose assembled Hessian is indefinite, and Newton converges to spurious minima (247% error) even with 1%-accurate field predictions. We introduce convex neural energy elements: each element exports a scalar energy E(g,U), architecturally convex in its boundary degrees of freedom U and smoothly parameterized by its geometry g, realized as a hypernetwork-generated positive-semidefinite quadratic form (an input-convex correction is reserved for non-quadratic physics).
Large language models (LLMs) are increasingly used across diverse tasks in K-12 education, yet existing safety evaluations rarely examine how harmful or inappropriate content appears in interactions between LLMs and students or teachers. To address this, we present EduZone, an evaluation framework for LLM safety across diverse educational scenarios.
Multi-agent large language model (LLM) systems can expose protected state through internal messages, tool arguments, logs, and persistent memory even when their public outputs appear innocuous. Existing privacy prompts, redaction methods, and source-level access controls restrict surface content or data access, but do not specify what a legitimately informed agent should disclose or how that disclosure may be reused downstream.
However, whether these judges truly evaluate the scientific substance of ideas or are influenced by superficial stylistic presentation remains an open question. To address this question, we propose SciStyleBench, a unified three-component benchmark for diagnosing and mitigating stylistic bias in LLM-based idea evaluation: (i) First, SciStyleStage, a three-stage evaluation environment that applies controlled stylistic perturbations to fixed scientific content across three settings no context, fixed-domain context, and open-domain retrieval context, covering 600 scientific ideas and 15 style variants, with 9,000 evaluation instances per setting; (ii) Second, SciStyleMetrics, a set of quantitative measures, including Style Bias Index (SBI), Substance Recognition Rate (SRR), and Adversarial Win Rate (AWR), to characterize how stylistic variation affects scoring stability, substance discrimination, and ranking robustness; (iii) Third, SciStyleExtractor, a plug-and-play evaluation module that separates presentation style from scientific content by predicting style type and deviation before style-conditioned evaluation, enabling us to assess whether style awareness reduces stylistic bias.
arXiv:2607. 28639v1 Announce Type: cross Abstract: We show that knowledge distillation in small instruction-tuned language models has asymmetric effects on bias.
By Plawan Kumar Rath
arXiv:2605. 15100v2 Announce Type: replace Abstract: Large Language Models (LLMs) have demonstrated remarkable abilities in reasoning.
By Rongman Xu, Yifei Li, Tianzhe Zhao, Yanrui Wu, Bo Li, Hang Yan
arXiv:2604. 10475v2 Announce Type: replace Abstract: Modeling household-level decisions is central to many real-world applications, including trip planning, residential mobility and migration, disaster management, etc.
By Yuran Sun, Mustafa Sameen, Yaotian Zhang, Rongguan Gu, Mrunal Vibhute, Chia-yu Wu, Yuanyuan Lei, Xilei Zhao
arXiv:2410. 06665v4 Announce Type: replace-cross Abstract: This paper explores the characterization of equivariant linear layers for representations of permutations and related groups.
By Yonatan Sverdlov, Ido Springer, Nadav Dym
arXiv:2512. 03438v3 Announce Type: replace Abstract: Agentic reasoning models trained with multimodal reinforcement learning (MMRL) have become increasingly capable, yet they are almost universally optimized using sparse, outcome-based rewards computed based on the final answers.
By Reuben Tan, Baolin Peng, Zhengyuan Yang, Hao Cheng, Oier Mees, Theodore Zhao, Andrea Tupini, Isar Meijer, Qianhui Wu, Yuncong Yang, Lars Liden, Yu Gu, Sheng Zhang, Xiaodong Liu, Lijuan Wang, Marc Pollefeys, Yong Jae Lee, Jianfeng Gao
arXiv:2607. 28916v1 Announce Type: cross Abstract: Multistep credit assignment is critical for sample-efficient reinforcement learning, yet managing off-policy bias in Q-learning remains a fundamental challenge.
By Brett Daley
arXiv:2607. 29169v1 Announce Type: cross Abstract: Vision-language-action (VLA) policies achieve strong performance in robotic manipulation but remain vulnerable to runtime disturbances that break the temporal alignment among visual observations, robot states, and executed actions.
By Wenda Yu, Tianshi Wang, Fengling Li, Xin Li, Jingjing Li, Lei Zhu
arXiv:2511. 11902v2 Announce Type: replace-cross Abstract: Bidirectional Associative Memory (BAM) trained with Bidirectional Backpropagation (B-BP) often suffers from poor robustness and high sensitivity to noise and adversarial attacks.
By Ci Lin, Tet Yeap, Iluju Kiringa
arXiv:2607. 28968v1 Announce Type: cross Abstract: Renault, Bergeaud, and Bosquet (hereafter RBB) argue that dating LLM adoption as the first month in which an author's abstract is flagged induces a stopping-time selection that can produce a positive event-study path even when there is no causal effect.
By Keigo Kusumegi, Xinyu Yang, Paul Ginsparg, Mathijs de Vaan, Toby Stuart, Yian Yin
arXiv:2607. 28986v1 Announce Type: cross Abstract: Zero-shot image captioning (ZIC) describes images without paired image-caption supervision during captioner training, relying on text-only corpora and frozen pretrained image-text scorers.
By Duy Tran Thanh, Thien-Phuc Doan, Long Nguyen-Vu, Ngo Tan Vu Khanh
arXiv:2607. 29077v1 Announce Type: new Abstract: Counterfactual explanations (CEs) enhance the interpretability of machine learning models by identifying the smallest change to an input required to obtain a desired output.
By Keita Kinjo
arXiv:2605. 07699v2 Announce Type: replace-cross Abstract: LLM-based agents are increasingly deployed for routine but consequential tasks in real-world domains, where their behavior is governed by inherently ambiguous domain policies that admit multiple valid interpretations.
By Hsuvas Borkakoty, Sebastian Pohl, Cheng Wang, Bei Chen, Yufang Hou
arXiv:2605. 06938v2 Announce Type: replace-cross Abstract: Recently Brown et al.
By Brian Charles Brown, Mauricio Munoz, Robert Bridges, David Grimsman, Sean Warnick
arXiv:2601. 14300v4 Announce Type: replace Abstract: Hard-label black-box attacks, relying solely on top-1 predictions, represent one of the most challenging yet practically threat models.
By Jun Liu, Leo Yu Zhang, Fengpeng Li, Isao Echizen, Jiantao Zhou