Ax Xingze Zou, Jing Wang, Yuhua Zheng, Xueyi Chen, Haolei Bai, Lingcheng Kong, Syed A. R. Abu-Bakar, Zhaode Wang, Chengfei Lv, Haoji Hu, Huan Wang 3/13/2026

MobileKernelBench: Can LLMs Write Efficient Kernels for Mobile Devices?

MobileKernelBench evaluates whether LLMs can generate efficient compute kernels for mobile devices, introducing benchmark dataset for systematic investigation.

Ax Zikang Ding, Haomiao Yang, Meng Hao, Wenbo Jiang, Kunlan Xiang, Runmeng Du, Yijing Liu, Ruichen Zhang, Dusit Niyato 3/13/2026

Delayed Backdoor Attacks: Exploring the Temporal Dimension as a New Attack Surface in Pre-Trained Models

Introduces delayed backdoor attacks against pre-trained models where malicious behavior activation is temporally decoupled from trigger exposure.

Ax Jiayue Pu, Zhongxiang Sun, Zilu Zhang, Xiao Zhang, Jun Xu 3/13/2026

HomeSafe-Bench: Evaluating Vision-Language Models on Unsafe Action Detection for Embodied Agents in Household Scenarios

HomeSafe-Bench: evaluation benchmark for vision-language models detecting unsafe actions in household robot scenarios.

Ax Ilias Aarab 3/13/2026

BTZSC: A Benchmark for Zero-Shot Text Classification Across Cross-Encoders, Embedding Models, Rerankers and LLMs

BTZSC benchmark comparing zero-shot text classification methods across cross-encoders, embeddings, rerankers, and instruction-tuned LLMs.

Ax Maximilian Schmidt, Swantje Plambeck, Markus Knitt, Hendrik Rose, Goerschwin Fey, Jan Christian Wieck, Stephan Balduin 3/13/2026

Flowcean - Model Learning for Cyber-Physical Systems

Flowcean: automated data-driven model generation framework for cyber-physical systems focusing on modularity and usability.

Ax Thennal D K, Chris Biemann, Hans Ole Hatzel 3/13/2026

Just Use XML: Revisiting Joint Translation and Label Projection

Framework for joint machine translation and cross-lingual label projection using XML tags; addresses degraded translation quality in prior combined approaches.

Ax Sarbartha Banerjee, Prateek Sahu, Anjo Vahldiek-Oberwagner, Jose Sanchez Vicarte, Mohit Tiwari 3/13/2026

Cascade: Composing Software-Hardware Attack Gadgets for Adversarial Threat Amplification in Compound AI Systems

Security analysis of compound AI systems combining LLMs, software tools, and databases; identifies vulnerabilities from traditional software stack and hardware layers.

Ax Xingyu Xie, Zhaochen Yu, Yue Liao, Tao Wang, Kim-Chuan Toh, Shuicheng Yan 3/13/2026

Slow-Fast Inference: Training-Free Inference Acceleration via Within-Sentence Support Stability

Slow-Fast Inference: training-free decoding acceleration leveraging stable attention support patterns within semantic spans during autoregressive generation.

Ax Sophie Jaffard, Ivo F. Sbalzarini 3/13/2026

Chemical Reaction Networks Learn Better than Spiking Neural Networks

Mathematical proof that chemical reaction networks without hidden layers outperform spiking neural networks on certain classification tasks.

Ax Zhaoyang Jiang, Zhizhong Fu, David McAllister, Yunsoo Kim, Honghan Wu 3/13/2026

Paper Title: LoV3D: Grounding Cognitive Prognosis Reasoning in Longitudinal 3D Brain MRI via Regional Volume Assessments

LoV3D: vision-language pipeline for cognitive prognosis from longitudinal brain MRI via regional volume assessments and grounded reasoning.

Ax Xiaojie Gu, Dmitry Ignatov, Radu Timofte 3/13/2026

Resource-Efficient Iterative LLM-Based NAS with Feedback Memory

LLM-based neural architecture search with feedback memory: closed-loop pipeline for iterative CNN design on consumer GPU without fine-tuning.

Ax Dimitri Staufer, Kirsten Morehouse, David Hartmann, Bettina Berendt 3/13/2026

Human-Centred LLM Privacy Audits: Findings and Frictions

LMP2: browser-based self-audit tool for inspecting LLM associations with individuals, with user study findings on privacy and model behavior.

Ax Taeho Lee, Donghwan Lee 3/13/2026

Taming the Adversary: Stable Minimax Deep Deterministic Policy Gradient via Fractional Objectives

Minimax deep deterministic policy gradient: RL algorithm for stable performance under external disturbances using fractional objectives.

Ax William Brach, Tomas Bedej, Jacob Nielsen, Jacob Pichna, Juraj Bedej, Eemeli Saarensilta, Julie Dupouy, Gianluca Barmina, Andrea Blasi N\'u\~nez, Peter Schneider-Kamp, Kristian Ko\v{s}\v{t}\'al, Michal Ries, Lukas Galke Poech 3/13/2026

SommBench: Assessing Sommelier Expertise of Language Models

SommBench: multilingual benchmark assessing LLM capabilities in sommelier expertise, evaluating cultural knowledge beyond linguistic encoding.

Ax Seth Karten, Rahul Dev Appapogu, Chi Jin 3/13/2026

Automatic Generation of High-Performance RL Environments

Agent-assisted code generation for translating complex RL environments into high-performance implementations with iterative repair and verification.

Ax Zhoujun Cheng, Yutao Xie, Yuxiao Qu, Amrith Setlur, Shibo Hao, Varad Pimpalkhute, Tongtong Liang, Feng Yao, Zhengzhong Liu, Eric Xing, Virginia Smith, Ruslan Salakhutdinov, Zhiting Hu, Taylor Killian, Aviral Kumar 3/13/2026

IsoCompute Playbook: Optimally Scaling Sampling Compute for LLM RL

IsoCompute Playbook: scaling laws for optimal compute allocation in LLM reinforcement learning post-training across rollouts, batches, and update steps.

Ax Zexuan Yan, Jiarui Jin, Yue Ma, Shijian Wang, Jiahui Hu, Wenxiang Jiao, Yuan Lu, Linfeng Zhang 3/13/2026

GlyphBanana: Advancing Precise Text Rendering Through Agentic Workflows

GlyphBanana: agentic workflow for precise text and formula rendering in generative models, addressing out-of-distribution instruction-following challenges.

Ax Krishnakumar Balasubramanian, Shiva Prasad Kasiviswanathan 3/13/2026

A Quantitative Characterization of Forgetting in Post-Training

Theoretical analysis of catastrophic forgetting in continual post-training of generative models, formalizing mass forgetting and component drift mechanisms.

Ax Jingyang Ke, Weihan Li, Amartya Pradhan, Jeffrey Markowitz, Anqi Wu 3/13/2026

BehaviorVLM: Unified Finetuning-Free Behavioral Understanding with Vision-Language Reasoning

BehaviorVLM: vision-language framework for animal pose estimation and behavioral understanding without human annotation using finetuning-free approach.

Ax {\L}ukasz Borchmann, Jordy Van Landeghem, Micha{\l} Turski, Shreyansh Padarha, Ryan Othniel Kearns, Adam Mahdi, Niels Rogge, Cl\'ementine Fourrier, Siwei Han, Huaxiu Yao, Artemis Llabr\'es, Yiming Xu, Dimosthenis Karatzas, Hao Zhang, Anupam Datta 3/13/2026

Strategic Navigation or Stochastic Search? How Agents and Humans Reason Over Document Collections

MADQA: benchmark with 2,250 questions over 800 PDFs evaluating whether multimodal agents use strategic reasoning or stochastic search in document-intensive workflows.

Ax Priyanka Kargupta, Shuhaib Mehri, Dilek Hakkani-Tur, Jiawei Han 3/13/2026

Sparking Scientific Creativity via LLM-Driven Interdisciplinary Inspiration

LLM-driven system for advancing interdisciplinary scientific research through exploration and reasoning rather than rapid experiment design.

Ax Yulu Gan, Phillip Isola 3/13/2026

Neural Thickets: Diverse Task Experts Are Dense Around Pretrained Weights

Neural Thickets shows task-specific expert solutions exist near pretrained weights and can be discovered through structured optimization.

Ax Ninghui Li, Kaiyuan Zhang, Kyle Polley, Jerry Ma 3/13/2026

Security Considerations for Artificial Intelligence Agents

Perplexity's security analysis and recommendations for frontier AI agents based on operating general-purpose agentic systems at scale.

Ax Raya Elsaleh, Liam Davis, Haoze Wu, Guy Katz 3/13/2026

Incremental Neural Network Verification via Learned Conflicts

Method to accelerate neural network verification by reusing learned conflicts across related queries instead of solving each independently.

Ax Ziyu Chen, Yilun Zhao, Chengye Wang, Rilyn Han, Manasi Patwardhan, Arman Cohan 3/13/2026

SciMDR: Benchmarking and Advancing Scientific Multimodal Document Reasoning

SciMDR benchmark and synthesize-and-reground framework for scientific multimodal document reasoning datasets balancing scale, faithfulness, and realism.

Ax Min Cheng, Fatemeh Doudi, Dileep Kalathil, Mohammad Ghavamzadeh, Panganamala R. Kumar 3/13/2026

Diffusion Blend: Inference-Time Multi-Preference Alignment for Diffusion Models

Inference-time approach for aligning diffusion models with multiple conflicting objectives and varying user preferences without retraining.

Ax Jonathan Leung, Yongjie Wang, Zhiqi Shen 3/13/2026

From Entity-Centric to Goal-Oriented Graphs: Enhancing LLM Knowledge Retrieval in Minecraft

Goal-Oriented Graphs framework enhancing LLM procedural reasoning in interactive environments like Minecraft through improved knowledge retrieval.

Ax Sayan Nag, K J Joseph, Koustava Goswami, Vlad I Morariu, Balaji Vasan Srinivasan 3/13/2026

Agentic Design Review System

Multi-agent system orchestrating collaborative design review where agents analyze graphics holistically with novel exemplar selection approach.

Ax Mingyang Li, Viktor Schlegel, Tingting Mu, Wuraola Oyewusi, Kai Kang, Goran Nenadic 3/13/2026

Evaluation and LLM-Guided Learning of ICD Coding Rationales

Evaluation framework for ICD medical coding using LLM-guided learning and systematic assessment of model rationales in healthcare.

Ax Carlos N\'u\~nez-Molina, Vicen\c{c} G\'omez, Hector Geffner 3/13/2026

From Next Token Prediction to (STRIPS) World Models

Study on whether next-token prediction yields usable world models, introducing STRIPS Transformer for symbolic planning from action traces.

Ax Henrique Assump\c{c}\~ao, Diego Ferreira, Leandro Campos, Fabricio Murai 3/13/2026

CodeEvolve: an open source evolutionary coding agent for algorithmic discovery and optimization

Open-source CodeEvolve framework combining LLMs with evolutionary algorithms for algorithmic solution synthesis and optimization.

Ax Atsuyuki Miyai, Mashiro Toyooka, Takashi Otonari, Zaiying Zhao, Kiyoharu Aizawa 3/13/2026

Jr. AI Scientist and Its Risk Report: Autonomous Scientific Exploration from a Baseline Paper

Jr. AI Scientist autonomous system that mimics novice researcher workflow for AI-driven scientific discovery with risk assessment capabilities.

Ax Yuxiang Zhou, Jichang Li, Yanhao Zhang, Haonan Lu, Guanbin Li 3/13/2026

Mobile-Agent-RAG: Driving Smart Multi-Agent Coordination with Contextual Knowledge Empowerment for Long-Horizon Mobile Automation

Mobile-Agent-RAG system combining multi-agent coordination with retrieval-augmented generation for long-horizon mobile automation tasks on UI.

Ax Tomoaki Yamaguchi, Yutong Zhou, Masahiro Ryo, Keisuke Katsura 3/13/2026

Agentic Explainable Artificial Intelligence (Agentic XAI) Approach To Explore Better Explanation

Agentic XAI approach using LLM agents to translate technical explanations into accessible narratives for improving trust in AI predictions.

Ax Weixun Wang, XiaoXiao Xu, Wanhe An, Fangwen Dai, Wei Gao, Yancheng He, Ju Huang, Qiang Ji, Hanqi Jin, Xiaoyang Li, Yang Li, Zhongwen Li, Shirong Lin, Jiashun Liu, Zenan Liu, Tao Luo, Dilxat Muhtar, Yuanbin Qu, Jiaqiang Shi, Qinghui Sun, Yingshui Tan, Hao Tang, Runze Wang, Yi Wang, Zhaoguo Wang, Yanan Wu, Shaopan Xiong, Binchen Xu, Xander Xu, Yuchi Xu, Qipeng Zhang, Xixia Zhang, Haizhou Zhao, Jie Zhao, Shuaibing Zhao, Baihui Zheng, Jianhui Zheng, Suhang Zheng, Yanni Zhu, Mengze Cai, Kerui Cao, Xitong Chen, Yue Dai, Lifan Du, Tao Feng, Tao He, Jin Hu, Yijie Hu, Ziyu Jiang, Cheng Li, Xiang Li, Jing Liang, Xin Lin, Chonghuan Liu, ZhenDong Liu, Zhiqiang Lv, Haodong Mi, Yanhu Mo, Junjia Ni, Shixin Pei, Jingyu Shen, XiaoShuai Song, Cecilia Wang, Chaofan Wang, Kangyu Wang, Pei Wang, Tao Wang, Wei Wang, Ke Xiao, Mingyu Xu, Tiange Xu, Nan Ya, Siran Yang, Jianan Ye, Yaxing Zang, Duo Zhang, Junbo Zhang, Boren Zheng, Wanxi Deng, Ling Pan, Lin Qu, Wenbo Su, Jiamang Wang, Wei Wang, Hu Wei, Minggang Wu, Cheng Yu, Bing Zhao, Zhicheng Zheng, Bo Zheng 3/13/2026

Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem

Agentic Learning Ecosystem (ALE) infrastructure for end-to-end agent development, enabling LLMs to operate in real-world environments with iterative refinement.

Ax Zelai Xu, Zhexuan Xu, Ruize Zhang, Chunyang Zhu, Shi Yu, Weilin Liu, Quanlu Zhang, Wenbo Ding, Chao Yu, Yu Wang 3/13/2026

WideSeek-R1: Exploring Width Scaling for Broad Information Seeking via Multi-Agent Reinforcement Learning

Multi-agent reinforcement learning system exploring width scaling for broad information seeking tasks, addressing organizational capability bottlenecks.

Ax Aniketh Garikaparthi, Manasi Patwardhan, Arman Cohan 3/13/2026

ResearchGym: Evaluating Language Model Agents on Real-World AI Research

Benchmark and execution environment evaluating AI agents on end-to-end research tasks using containerized ICML/ICLR/ACL paper repositories with 39 sub-tasks.

Ax Zhenyu Li, Guanlin Wu, Cheems Wang, Yongqiang Zhao 3/13/2026

Limited Reasoning Space: The cage of long-horizon reasoning in LLMs

Research on chain-of-thought reasoning failures in LLMs when scaling compute budgets, proposing limited reasoning space as explanation for performance collapse.

Ax Xiaoying Zhang, Zichen Liu, Yipeng Zhang, Xia Hu, Wenqi Shao 3/13/2026

RetroAgent: From Solving to Evolving via Retrospective Dual Intrinsic Feedback

Reinforcement learning method for LLM-based agents using retrospective feedback to enable continual adaptation and experiential learning.

Ax Rui Liu, Tao Zhe, Dongjie Wang, Zijun Yao, Kunpeng Liu, Yanjie Fu, Huan Liu, Jian Pei 3/13/2026

AgentOS: From Application Silos to a Natural Language-Driven Data Ecosystem

Open-source framework for locally-hosted LLM-based agents that autonomously operate computing environments and orchestrate workflows.

Ax Junnan Dong, Chuang Zhou, Zheng Yuan, Yifei Yu, Qiufeng Wang, Yinghui Li, Siyu An, Di Yin, Xing Sun, Feiyue Huang 3/13/2026

Deep Tabular Research via Continual Experience-Driven Execution

Agentic framework for multi-step reasoning over complex tabular data with hierarchical headers using closed-loop decision-making.

Ax Jiangming Shu, Yuxiang Zhang, Ye Ma, Xueyuan Lin, Jitao Sang 3/13/2026

Evaluate-as-Action: Self-Evaluated Process Rewards for Retrieval-Augmented Agents

EvalAct: Method for retrieval-augmented agents using self-evaluated process rewards to optimize multi-step reasoning via explicit quality assessment actions.

Ax Xin An, Jingyi Cai, Xiangyang Chen, Huayao Liu, Peiting Liu, Peng Wang, Bei Yang, Xiuwen Zhu, Yongfan Chen, Yan Gao, Yuan Gao, Baoyu Hou, Guangzheng Hu, Shuzhao Li, Weixu Qiao, Weidong Ren, Yanan Wang, Boyu Yang, Fan Yang, Jiangtao Zhang, Lixin Zhang, Lin Qu, Hu Wei, Xiaoxiao Xu, Bing Zhao 3/13/2026

Logics-Parsing-Omni Technical Report

Omni Parsing: Framework for multimodal parsing across documents, images, audio-visual with unified taxonomy and hierarchical levels.

Ax Marta Sumyk, Oleksandr Kosovan 3/13/2026

CUAAudit: Meta-Evaluation of Vision-Language Models as Auditors of Autonomous Computer-Use Agents

CUAAudit: Meta-evaluation framework for vision-language models as auditors of autonomous desktop computer-use agents.

Ax Valentyn Melnychuk, Dennis Frauen, Stefan Feuerriegel 3/13/2026

Bounds on Representation-Induced Confounding Bias for Treatment Effect Estimation

Theoretical bounds on bias from representation learning in conditional average treatment effect estimation.

Ax Jahir Sadik Monon, Deeparghya Dutta Barua, Md. Mosaddek Khan 3/13/2026

Enhancing Heterogeneous Multi-Agent Cooperation in Decentralized MARL via GNN-driven Intrinsic Rewards

GNN-driven intrinsic reward method for heterogeneous multi-agent cooperation in decentralized reinforcement learning.

Ax Yiming Huang, Tolga Birdal 3/13/2026

HOG-Diff: Higher-Order Guided Diffusion for Graph Generation

HOG-Diff: Diffusion model for graph generation incorporating higher-order topology guidance. Improves on image-based approaches.

Ax Ziqiao Weng, Weidong Cai, Bo Zhou 3/13/2026

FedSKD: Aggregation-free Model-heterogeneous Federated Learning via Multi-dimensional Similarity Knowledge Distillation for Medical Image Classification

FedSKD: Federated learning method for model-heterogeneous training via knowledge distillation without centralized aggregation. Medical imaging focus.

Ax Yijie Zheng, Bangjun Xiao, Lei Shi, Xiaoyang Li, Faming Wu, Tianyu Li, Xuefeng Xiao, Yang Zhang, Yuxuan Wang, Shouda Liu 3/13/2026

OrchMLLM: Orchestrate Multimodal Data with Batch Post-Balancing to Accelerate Multimodal Large Language Model Training

OrchMLLM optimizes multimodal LLM training via batch post-balancing. Addresses modality composition incoherence and GPU utilization issues.

Ax Wenqing Zheng, Noah Fatsi, Daniel Barcklow, Dmitri Kalaev, Steven Yao, Owen Reinert, C. Bayan Bruss, Daniele Rosa 3/13/2026

Tuning-Free LLM Can Build A Strong Recommender Under Sparse Connectivity And Knowledge Gap Via Extracting Intent

IKGR framework uses intent-centric knowledge graphs for LLM-based recommendations without fine-tuning. Handles sparsity and cold-start scenarios.