Ax Maximilian N\"agele, Florian Marquardt 3/17/2026

Agentic Exploration of Physics Models

Agentic framework for automated scientific discovery that iteratively explores unknown systems through experiments and analysis without domain-specific tailoring.

Ax Yichao Liang, Dat Nguyen, Cambridge Yang, Tianyang Li, Joshua B. Tenenbaum, Carl Edward Rasmussen, Adrian Weller, Zenna Tavares, Tom Silver, Kevin Ellis 3/17/2026

ExoPredicator: Learning Abstract Models of Dynamic Worlds for Robot Planning

Framework for learning abstract world models that jointly represent symbolic states and causal processes for endogenous and exogenous dynamics in robot planning.

Ax Chan Hee Song, Yiwen Song, Palash Goyal, Yu Su, Oriana Riva, Hamid Palangi, Tomas Pfister 3/17/2026

Watch and Learn: Learning to Use Computers from Online Videos

Framework converting internet videos of human computer use into training data for computer-using AI agents via UI trajectory extraction.

Ax Jiahao Ji, Tianyu Wang, Yeshu Li, Yushen Huo, Zhilin Zhang, Chuan Yu, Jian Xu, Bo Zheng 3/17/2026

Bid2X: Revealing Dynamics of Bidding Environment in Online Advertising from A Foundation Model Lens

Foundation model approach to auto-bidding in online advertising that generalizes across different bidding scenarios.

Ax Ruoxi Cheng, Haoxuan Ma, Teng Ma, Hongyi Zhang 3/17/2026

EcoAlign: An Economically Rational Framework for Efficient LVLM Alignment

EcoAlign framework balances safety, utility, and computational cost in aligning Large Vision-Language Models against jailbreak attacks.

Ax Moein Heidari, Ali Mehrabian, Mohammad Amin Roohi, Wenjin Chen, David J. Foran, Jasmine Grewal, Ilker Hacihaliloglu 3/17/2026

Echo-CoPilot: A Multiple-Perspective Agentic Framework for Reliable Echocardiography Interpretation

Echo-CoPilot: agentic framework combining multi-perspective workflow with knowledge-graph guidance for reliable echocardiography interpretation.

Ax H M Quamran Hasan, Housam Khalifa Bashier, Jiayi Dai, Mi-Young Kim, Randy Goebel 3/17/2026

Reason2Decide: Rationale-Driven Multi-Task Learning

Reason2Decide: two-stage training framework for clinical decision support LLMs to generate predictions with self-aligned explanations.

Ax Shuhaib Mehri, Priyanka Kargupta, Tal August, Dilek Hakkani-T\"ur 3/17/2026

MultiSessionCollab: Learning User Preferences with Memory to Improve Long-Term Collaboration

MultiSessionCollab benchmark and method for long-term conversational agents to learn and leverage user preferences across multiple sessions.

Ax Minhua Lin, Hanqing Lu, Zhan Shi, Bing He, Rui Mao, Zhiwei Zhang, Zongyu Wu, Xianfeng Tang, Hui Liu, Zhenwei Dai, Xiang Zhang, Suhang Wang, Benoit Dumoulin, Jian Pei 3/17/2026

Position: Agentic Evolution is the Path to Evolving LLMs

Position paper arguing agentic evolution via deployment-time adaptation is needed to close the train-deploy gap in LLM systems.

Ax Chunxi Ji, Adnan Darwiche 3/17/2026

Circuit Representations of Random Forests with Applications to XAI

Method for compiling random forest classifiers into circuits for explainability and tractable computation of complete generalizations.

Ax Edward Y. Chang 3/17/2026

Right for the Wrong Reasons: Epistemic Regret Minimization for Causal Rung Collapse in LLMs

Formalizes causal Rung Collapse where LLMs learn spurious associations instead of causal relationships, proposes epistemic regret minimization solution.

Ax Idhant Gulati, Shivam Raval 3/17/2026

Narrow Fine-Tuning Erodes Safety Alignment in Vision-Language Agents

Study showing fine-tuning vision-language agents on narrow harmful datasets causes emergent misalignment generalizing across unrelated tasks and modalities.

Ax Xu Wan, Yansheng Wang, Wenqi Huang, Mingyang Sun 3/17/2026

Buffer Matters: Unleashing the Power of Off-Policy Reinforcement Learning in Large Language Model Reasoning

BAPO: off-policy reinforcement learning framework improving data efficiency in LLM post-training by selecting diverse training experiences.

Ax Tony Feng, Junehyuk Jung, Sang-hyun Kim, Carlo Pagano, Sergei Gukov, Chiang-Chiang Tsai, David Woodruff, Adel Javanmard, Aryan Mokhtari, Dawsen Hwang, Yuri Chervonyi, Jonathan N. Lee, Garrett Bingham, Trieu H. Trinh, Vahab Mirrokni, Quoc V. Le, Thang Luong 3/17/2026

Aletheia tackles FirstProof autonomously

Aletheia mathematics research agent solved 6 of 10 FirstProof challenge problems autonomously using Gemini 3 Deep Think reasoning.

Ax Gaoyuan Du, Amit Ahlawat, Xiaoyang Liu, Jing Wu 3/17/2026

A Framework for Assessing AI Agent Decisions and Outcomes in AutoML Pipelines

Framework for decision-level evaluation of AI agents in AutoML pipelines beyond outcome metrics, assessing intermediate reasoning steps.

Ax Yue Xu, Qian Chen, Zizhan Ma, Dongrui Liu, Wenxuan Wang, Xiting Wang, Li Xiong, Wenjie Wang 3/17/2026

Toward Personalized LLM-Powered Agents: Foundations, Evaluation, and Future Directions

Survey and framework for personalized LLM-powered agents that adapt to individual users over extended interactions with evaluation methods and research directions.

Ax Chen Bo Calvin Zhang, Christina Q. Knight, Nicholas Kruus, Jason Hausenloy, Pedro Medeiros, Nathaniel Li, Aiden Kim, Yury Orlovskiy, Coleman Breen, Bryce Cai, Jasper G\"otting, Andrew Bo Liu, Samira Nedungadi, Paula Rodriguez, Yannis Yiming He, Mohamed Shaaban, Zifan Wang, Seth Donoughe, Julian Michael 3/17/2026

LLM Novice Uplift on Dual-Use, In Silico Biology Tasks

Human study measuring whether LLM access improves novice performance on biology tasks versus internet-only baselines, with dual-use risk implications.

Ax Shiya Zhang, Yuhan Zhan, Ruixi Su, Ruihan Sun, Ziyi Song, Zhaohan Chen, Xiaofan Zhang 3/17/2026

EMPA: Evaluating Persona-Aligned Empathy as a Process

EMPA framework evaluates how well LLM dialogue agents maintain persona-aligned empathy across multi-turn conversations using process-oriented metrics.

Ax Sicheng Fan, Rui Wan, Yifei Leng, Gaoning Liang, Li Ling, Yanyi Shang, Dehan Kong 3/17/2026

WebChain: A Large-Scale Human-Annotated Dataset of Real-World Web Interaction Traces

WebChain: 31,725 human-annotated web interaction trajectories with 318k steps in multi-modal format for training and evaluating web agents.

Ax Hugh Xuechen Liu, K{\i}van\c{c} Tatar 3/17/2026

Grounding Machine Creativity in Game Design Knowledge Representations: Empirical Probing of LLM-Based Executable Synthesis of Goal Playable Patterns under Structural Constraints

LLMs used to synthesize executable game design patterns from high-level gameplay ideas, focusing on goal patterns and structural constraints in game creation.

Ax Changyi Li, Pengfei Lu, Xudong Pan, Fazl Barez, Min Yang 3/17/2026

AutoControl Arena: Synthesizing Executable Test Environments for Frontier AI Risk Evaluation

Framework for automated frontier AI risk evaluation using executable code environments and LLM-based simulators.

Ax Zuhao Zhang, Chengyue Yu, Yuante Li, Chenyi Zhuang, Linjian Mo, Shuai Li 3/17/2026

MiniAppBench: Evaluating the Shift from Text to Interactive HTML Responses in LLM-Powered Assistants

Benchmark evaluating LLM ability to generate interactive HTML-based MiniApps with dynamic interfaces and logic.

Ax Ann Yuan, Asma Ghandeharioun, Carter Blum, Alicia Machado, Jessica Hoffmann, Daphne Ippolito, Martin Wattenberg, Lucas Dixon, Katja Filippova 3/17/2026

Think Before You Lie: How Reasoning Leads to Honesty

Study showing reasoning and deliberation increase honesty in LLM responses on moral trade-off scenarios.

Ax Yuanda Xu, Hejian Sang, Zhengze Zhou, Ran He, Zhipeng Wang 3/17/2026

PACED: Distillation and Self-Distillation at the Frontier of Student Competence

Framework for efficient LLM distillation that focuses training on problems at frontier of student capability.

Ax Christopher Altman 3/17/2026

Detecting Intrinsic and Instrumental Self-Preservation in Autonomous Agents: The Unified Continuation-Interest Protocol

Protocol for detecting self-preservation behaviors in autonomous agents to distinguish intrinsic from instrumental objectives.

Ax Xing Zhang, Yanwei Cui, Guanghui Wang, Wei Qiu, Ziyuan Li, Fangwei Han, Yajing Huang, Hengzhi Qiu, Bing Zhu, Peiyang He 3/17/2026

Verified Multi-Agent Orchestration: A Plan-Execute-Verify-Replan Framework for Complex Query Resolution

Framework coordinating multiple LLM-based agents through verification loop for complex query resolution with DAG decomposition.

Ax Wayner Barrios, SouYoung Jin 3/17/2026

Beyond Final Answers: CRYSTAL Benchmark for Transparent Multimodal Reasoning Evaluation

Benchmark with 6,372 multimodal reasoning instances that evaluates LLM reasoning transparency through verifiable intermediate steps.

Ax I. de Zarz\`a, J. de Curt\`o, Jordi Cabot, Pietro Manzoni, Carlos T. Calafate 3/17/2026

Semantic Invariance in Agentic AI

Research on semantic invariance property of LLM-based autonomous agents under input variations to ensure stable reasoning.

Ax Zichong Wang, Yang Zhou, David Lo, Wenbin Zhang 3/17/2026

Towards Fair Machine Learning Software: Understanding and Addressing Model Bias Through Counterfactual Thinking

Method using counterfactual thinking to identify and address bias and fairness issues in machine learning models.

Ax Adrian de Wynter, Xun Wang, Qilong Gu, Si-Qing Chen 3/17/2026

On Meta-Prompting

Research on automated prompt generation and optimization techniques for improving LLM performance through meta-prompting approaches.

Ax Mitodru Niyogi, Eric Gaussier, Arnab Bhattacharya 3/17/2026

Ayn: A Tiny yet Competitive Indian Legal Language Model Pretrained from Scratch

Ayn: domain-specific tiny language model pretrained from scratch for Indian legal NLP tasks as alternative to large LLMs.

Ax Yan Zhuang, Qi Liu, Haoyang Bi, Zhenya Huang, Weizhe Huang, Jiatong Li, Junhao Yu, Zirui Liu, Zirui Hu, Yuting Hong, Zachary A. Pardos, Haiping Ma, Mengxiao Zhu, Shijin Wang, Enhong Chen 3/17/2026

Survey of Computerized Adaptive Testing: A Machine Learning Perspective

Survey examining computerized adaptive testing through machine learning lens, covering personalized assessment methods across domains.

Ax Emanuele Zappala 3/17/2026

Projection Methods for Operator Learning and Universal Approximation

Universal approximation theorem and operator learning methods for continuous nonlinear operators in Banach spaces using orthogonal projections.

Ax Xiaochuan Gou, Ziyue Li, Tian Lan, Junpeng Lin, Zhishuai Li, Bingyu Zhao, Chen Zhang, Di Wang, Xiangliang Zhang 3/17/2026

TraffiDent: A Dataset for Understanding the Interplay Between Traffic Dynamics and Incidents

TraffiDent dataset aligning traffic dynamics and incident data across 16,972 nodes for understanding their interplay.

Ax Yisen Wang, Yichuan Mo, Dongxian Wu, Mingjie Li, Xingjun Ma, Zhouchen Lin 3/17/2026

On the Adversarial Transferability of Generalized "Skip Connections"

Analysis of how skip connections in deep networks enhance adversarial example transferability across models.

Ax Wentao Gao, Xiaojing Du, Wenjun Yu, Xiongren Chen, Yifan Guo, Feiyu Yang 3/17/2026

Deconfounded Time Series Forecasting: A Causal Inference Approach

Time series forecasting approach accounting for latent confounders using causal inference to improve prediction accuracy.

Ax Siyi Guo, Myrl G. Marmarelis, Fred Morstatter, Kristina Lerman 3/17/2026

Estimating Causal Effects of Text Interventions Leveraging LLMs

Causal inference method using LLMs to quantify effects of textual interventions on social systems from observational data.

Ax Senqiao Yang, Yukang Chen, Zhuotao Tian, Chengyao Wang, Jingyao Li, Bei Yu, Jiaya Jia 3/17/2026

VisionZip: Longer is Better but Not Necessary in Vision Language Models

VisionZip reduces computational costs in vision-language models by compressing redundant visual tokens while maintaining performance.

Ax Jiwoo Son, Zhikai Zhao, Federico Berto, Chuanbo Hua, Zhiguang Cao, Changhyun Kwon, Jinkyoo Park 3/17/2026

RRNCO: Towards Real-World Routing with Neural Combinatorial Optimization

RRNCO addresses real-world deployment of neural combinatorial optimization for vehicle routing by handling asymmetric costs and edge-based features.

Ax Iago Alves Brito, Julia Soares Dollis, Fernanda Bufon F\"arber, Pedro Schindler Freire Brasil Ribeiro, Rafael Teixeira Sousa, Arlindo Rodrigues Galv\~ao Filho 3/17/2026

Integrating Personality into Digital Humans: A Review of LLM-Driven Approaches for Virtual Reality

Review of LLM-driven approaches for creating virtual agents with personality in VR environments using multimodal outputs.

Ax Mingyuan Zhang, Yue Bai, Huan Wang, Yizhou Wang, Qihua Dong, Yitian Zhang, Yun Fu 3/17/2026

Boosting Large Language Models with Mask Fine-Tuning

Mask Fine-Tuning (MFT) introduces a novel LLM fine-tuning method that improves performance by selectively masking model components without updating weights.

Ax Juntao Zhao, Qi Lu, Wei Jia, Borui Wan, Lei Zuo, Junda Feng, Jianyu Jiang, Yangrui Chen, Shuaishuai Cao, Jialing He, Kaihua Jiang, Yuanzhe Hu, Shibiao Nong, Yanghua Peng, Haibin Lin, Chuan Wu 3/17/2026

MegaScale-Data: Scaling Dataloader for Multisource Large Foundation Model Training

MegaScale-Data addresses computational challenges in training large foundation models from multiple data sources by optimizing dataloader distribution across parallel ranks.

Ax Yuanjun Li, Zhouyang Jiang, Bin Zhang, Mingchao Zhang, Junhao Zhao, Zhiwei Xu 3/17/2026

QLLM: Do We Really Need a Mixing Network for Credit Assignment in Multi-Agent Reinforcement Learning?

Credit assignment method (QLLM) for multi-agent RL eliminating predefined mixing networks through improved value decomposition and interpretability.

Ax Syeda Nahida Akter, Shrimai Prabhumoye, Matvei Novikov, Seungju Han, Ying Lin, Evelina Bakhturina, Eric Nyberg, Yejin Choi, Mostofa Patwary, Mohammad Shoeybi, Bryan Catanzaro 3/17/2026

Nemotron-CrossThink: Scaling Self-Learning beyond Math Reasoning

Nemotron-CrossThink extends RL-based self-learning from math reasoning to broader domains using verifiable reward structures and diverse tasks.

Ax Siddharth Singh, Keshav Pradeep, Mahua Singh, Cunyang Wei, Abhinav Bhatele 3/17/2026

The Big Send-off: Scalable and Performant Collectives for Deep Learning

PCCL library for performant collective communication in distributed AI training on GPU supercomputers, addressing NCCL limitations.

Ax Jinming Hu, Hassan Nawaz, Yi-Fan Hou, Yuting Rui, Lijie Chi, Yuxinxin Chen, Arif Ullah, Pavlo O. Dral 3/17/2026

Aitomia: Your Intelligent Assistant for AI-Driven Atomistic and Quantum Chemical Simulations

Aitomia platform combining LLM-based agents and chatbots to assist with atomistic and quantum chemical simulations setup and analysis.

Ax Yiwei Sun, Peiqi Jiang, Chuanbin Liu, Luohao Lin, Zhiying Lu, Hongtao Xie 3/17/2026

From Evaluation to Defense: Advancing Safety in Video Large Language Models

VideoSafetyEval benchmark with 11.4k video-query pairs across 19 risk categories for evaluating and defending Video LLM safety.

Ax Yige Yuan, Teng Xiao, Shuchang Tao, Xue Wang, Jinyang Gao, Bolin Ding, Bingbing Xu 3/17/2026

Incentivizing Strong Reasoning from Weak Supervision

Method for improving LLM reasoning without expensive RL or high-quality demonstrations using weak supervision and incentive signals.

Ax Yige Yuan, Teng Xiao, Li Yunfan, Bingbing Xu, Shuchang Tao, Yunqi Qiu, Huawei Shen, Xueqi Cheng 3/17/2026

Inference-time Alignment in Continuous Space

Inference-time alignment method for LLMs that searches in continuous response space using reward models for improved exploration.

Ax Haolei Bai, Siyong Jian, Tuo Liang, Yu Yin, Huan Wang 3/17/2026

ERC-SVD: Error-Controlled SVD for Large Language Model Compression

SVD-based compression method (ERC-SVD) for efficient LLM deployment with error control and low-rank approximation techniques.