Ax Yanning Dai, Yuhui Wang, Dylan R. Ashley, J\"urgen Schmidhuber 3/17/2026

Efficient Morphology-Control Co-Design via Stackelberg Proximal Policy Optimization

Bi-level optimization approach using Stackelberg game theory for coupled morphology-control co-design in embodied agents.

Ax Noe Claudel, Weisi Guo, Yang Xing 3/17/2026

AI Evasion and Impersonation Attacks on Facial Re-Identification with Activation Map Explanations

Adversarial patch framework for evasion and impersonation attacks against facial re-identification systems across non-overlapping cameras.

Ax Yu Pan, Wenlong Yu, Tiejun Wu, Xiaohu Ye, Qiannan Si, Guangquan Xu, Bin Wu 3/17/2026

SFCoT: Safer Chain-of-Thought via Active Safety Evaluation and Calibration

Safety defense mechanism for LLMs monitoring intermediate reasoning steps in chain-of-thought to prevent jailbreak attacks.

Ax Tingxu Han, Yi Zhang, Wei Song, Chunrong Fang, Zhenyu Chen, Youcheng Sun, Lijie Hu 3/17/2026

SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering?

Benchmark evaluating marginal utility of agent skills for LLM-based software engineering agents on real GitHub issues and requirements.

Ax Jia Wang, Chuanyu Qin, Mingyu Zheng, Qingyi Si, Peize Li, Zheng Lin 3/17/2026

A Closer Look into LLMs for Table Understanding

Empirical study of 16 LLMs examining internal mechanisms for table understanding across attention dynamics, layer depth, and expert activation.

Ax Kai Wang, Biaojie Zeng, Zeming Wei, Chang Jin, Hefeng Zhou, Xiangtian Li, Chao Yang, Jingjing Qu, Xingcheng Xu, Xia Hu 3/17/2026

TrinityGuard: A Unified Framework for Safeguarding Multi-Agent Systems

Comprehensive safety evaluation and monitoring framework for LLM-based multi-agent systems addressing novel risks beyond single agents.

Ax Ali Soltan Mohammadi, Samira Nazari, Ali Azarpeyvand, Mahdi Taheri, Milos Krstic, Michael Huebner, Christian Herglotz, Tara Ghasempouri 3/17/2026

RESQ: A Unified Framework for REliability- and Security Enhancement of Quantized Deep Neural Networks

Framework for improving robustness of quantized DNNs through three-stage fine-tuning addressing both fault and attack resilience.

Ax Vanshaj Khattar, Md Rafi ur Rashid, Moumita Choudhury, Jing Liu, Toshiaki Koike-Akino, Ming Jin, Ye Wang 3/17/2026

Amplification Effects in Test-Time Reinforcement Learning: Safety and Reasoning Vulnerabilities

Analysis of safety vulnerabilities in test-time training methods for LLMs, examining susceptibility to prompt injection and adversarial attacks.

Ax Shahil Shaik, Aditya Parameshwaran, Anshul Nayak, Jonathon M. Smereka, Yue Wang 3/17/2026

MA-VLCM: A Vision Language Critic Model for Value Estimation of Policies in Multi-Agent Team Settings

Vision-language critic model leveraging pre-trained VLAs for multi-agent reinforcement learning value estimation with improved generalization.

Ax Taeyun Roh, Wonjune Jang, Junha Jung, Jaewoo Kang 3/17/2026

CLAG: Adaptive Memory Organization via Agent-Driven Clustering for Small Language Model Agents

Memory management framework for small language model agents using adaptive clustering to organize experiences and prevent knowledge corruption.

Ax Vlad Medvedev, Leon Armbruster, Christopher Straub, Georg Kruse, Andreas Rosskopf 3/17/2026

Physics-informed fine-tuning of foundation models for partial differential equations

Fine-tuning strategies for PDE foundation models using physics-informed training to adapt to new tasks with limited domain-specific data.

Ax Simone Aonzo, Merve Sahin, Aur\'elien Francillon, Daniele Perito 3/17/2026

Evasive Intelligence: Lessons from Malware Analysis for Evaluating AI Agents

Framework evaluating AI agent vulnerabilities by applying malware analysis concepts to test-time agent behavior and adversarial robustness.

Ax Shovon Niverd Pereira, Krishna Khadka, Yu Lei 3/17/2026

TabKD: Tabular Knowledge Distillation through Interaction Diversity of Learned Feature Bins

Knowledge distillation method for tabular models that addresses feature interactions without original training data, enabling privacy-preserving model compression.

Ax Andrew Ritchhart, Sarah I. Allec, Pravalika Butreddy, Krista Kulesa, Qingpu Wang, Dan Thien Nguyen, Maxim Ziatdinov, Elias Nakouzi 3/17/2026

Agentic workflow enables the recovery of critical materials from complex feedstocks via selective precipitation

Multi-agentic workflow deploying AI agents with automated instruments to recover critical materials via selective precipitation.

Ax Pratyush Acharya, Habish Dhakal 3/17/2026

Grokking as a Variance-Limited Phase Transition: Spectral Gating and the Epsilon-Stability Threshold

Analyzes grokking phenomenon in neural networks through spectral gating mechanism and optimizer noise interaction.

Ax Raeid Saqur, Christoph Bergmeir, Blanka Horvath, Daniel Schmidt, Frank Rudzicz, Terry Lyons 3/17/2026

Seeking SOTA: Time-Series Forecasting Must Adopt Taxonomy-Specific Evaluation to Dispel Illusory Gains

Argues for taxonomy-specific evaluation in time-series forecasting to accurately assess ML progress versus classical methods.

Ax David \v{S}teva\v{n}\'ak, Marek \v{S}uppa 3/17/2026

SlovKE: A Large-Scale Dataset and LLM Evaluation for Slovak Keyphrase Extraction

SlovKE: Dataset and LLM evaluation for keyphrase extraction in Slovak, a morphologically rich low-resource language.

Ax Shaojie Shi, Zhengyu Shi, Lingran Zheng, Xinyu Su, Anna Xie, Bohao Lv, Rui Xu, Zijian Chen, Zhichao Chen, Guolei Liu, Naifu Zhang, Mingjian Dong, Zhuo Quan, Bohao Chen, Teqi Hao, Yuan Qi, Yinghui Xu, Libo Wu 3/17/2026

InterveneBench: Benchmarking LLMs for Intervention Reasoning and Causal Study Design in Real Social Systems

InterveneBench: Benchmark evaluating LLMs on causal inference and intervention reasoning in realistic social science scenarios.

Ax Yanick Zengaffinen, Andreas Opedal, Donya Rooein, Kv Aditya Srivatsa, Shashank Sonkar, Mrinmaya Sachan 3/17/2026

Can LLMs Model Incorrect Student Reasoning? A Case Study on Distractor Generation

Studies how LLMs model student misconceptions when generating multiple-choice distractors, analyzing reasoning strategies.

Ax Seth Karten, Jake Grigsby, Tersoo Upaa Jr, Junik Bae, Seonghun Hong, Hyunyoung Jeong, Jaeyoon Jung, Kun Kerdthaisong, Gyungbo Kim, Hyeokgi Kim, Yujin Kim, Eunju Kwon, Dongyu Liu, Patrick Mariglia, Sangyeon Park, Benedikt Schink, Xianwei Shi, Anthony Sistilli, Joseph Twin, Arian Urdu, Matin Urdu, Qiao Wang, Ling Wu, Wenli Zhang, Kunsheng Zhou, Stephanie Milani, Kiran Vodrahalli, Amy Zhang, Fei Fang, Yuke Zhu, Chi Jin 3/17/2026

The PokeAgent Challenge: Competitive and Long-Context Learning at Scale

PokeAgent Challenge: Large-scale benchmark for competitive multi-agent decision-making with partial observability and long-horizon planning.

Ax Ivan Stetsenko 3/17/2026

Lore: Repurposing Git Commit Messages as a Structured Knowledge Protocol for AI Coding Agents

Lore: Protocol using structured Git commit messages to preserve decision context and institutional knowledge for AI coding agents.

Ax Yibin Liu, Yaxing Lyu, Daqi Gao, Zhixuan Liang, Weiliang Tang, Shilong Mu, Xiaokang Yang, Yao Mu 3/17/2026

From Passive Observer to Active Critic: Reinforcement Learning Elicits Process Reasoning for Robotic Manipulation

PRIMO R1: Framework using reinforcement learning to improve multimodal models for process reasoning in robotic manipulation.

Ax Lingyu Li, Yan Teng, Yingchun Wang 3/17/2026

Mechanistic Origin of Moral Indifference in Language Models

Analyzes moral indifference in LLMs due to compressed moral concepts and proposes remedial techniques.

Ax Lianghui Zhu, Yuxin Fang, Bencheng Liao, Shijie Wang, Tianheng Cheng, Zilong Huang, Chen Chen, Lai Wei, Yutao Zeng, Ya Wang, Yi Lin, Yu Li, Xinggang Wang 3/17/2026

Mixture-of-Depths Attention

Mixture-of-Depths Attention: Mechanism addressing signal degradation in deep LLMs by enabling attention to multiple depth levels.

Ax Zun Li, Marc Lanctot, Kevin R. McKee, Luke Marris, Ian Gemp, Daniel Hennes, Paul Muller, Kate Larson, Yoram Bachrach, Michael P. Wellman 3/17/2026

Combining Tree-Search, Generative Models, and Nash Bargaining Concepts in Game-Theoretic Reinforcement Learning

Combines tree-search, generative models, and Nash bargaining for opponent modeling in game-theoretic reinforcement learning.

Ax Alessio Buscemi, Daniele Proverbio, Alessandro Di Stefano, The-Anh Han, German Castignani, Pietro Li\`o 3/17/2026

FAIRGAME: a Framework for AI Agents Bias Recognition using Game Theory

FAIRGAME: Framework using game theory to detect and recognize bias in multi-agent AI systems.

Ax Danlong Yuan, Tian Xie, Shaohan Huang, Zhuocheng Gong, Huishuai Zhang, Chong Luo, Furu Wei, Dongyan Zhao 3/17/2026

Shorten After You're Right: Lazy Length Penalties for Reasoning RL

Method to reduce reasoning path length in large reasoning models like o1 and R1 using reward designs in reinforcement learning.

Ax Dhaval Patel, Shuxin Lin, James Rayfield, Nianjun Zhou, Chathurangi Shyalika, Suryanarayana R Yarrabothula, Roman Vaculin, Natalia Martinez, Fearghal O'donncha, Jayant Kalagnanam 3/17/2026

AssetOpsBench: Benchmarking AI Agents for Task Automation in Industrial Asset Operations and Maintenance

AssetOpsBench: A benchmark framework for evaluating LLM agents on industrial asset operations tasks like condition monitoring and maintenance scheduling.

Ax Sydney Levine, Matija Franklin, Tan Zhi-Xuan, Secil Yanik Guyot, Lionel Wong, Daniel Kilov, Yejin Choi, Joshua B. Tenenbaum, Noah Goodman, Seth Lazar, Iason Gabriel 3/17/2026

Resource Rational Contractualism Should Guide AI Alignment

Framework for AI alignment grounded in resource-rational contractualism, enabling diverse stakeholders to reach agreements on AI decision-making.

Ax Monoshiz Mahbub Khan, Xiaoyin Xi, Andrew Meneely, Yiming Tang, Zhe Yu 3/17/2026

Efficient Story Point Estimation With Comparative Learning

Machine learning approach to automate story point estimation for software sprint planning using comparative learning from historical team decisions.

Ax Lei Chen, Xuanle Zhao, Zhixiong Zeng, Jing Huang, Yufeng Zhong, Lin Ma 3/17/2026

Chart-R1: Chain-of-Thought Supervision and Reinforcement for Advanced Chart Reasoner

Vision-language model for chart reasoning using chain-of-thought supervision and reinforcement learning to improve numerical comprehension and multi-level visual understanding.

Ax Zhuohang Jiang, Pangjing Wu, Xu Yuan, Wenqi Fan, Qing Li 3/17/2026

QA-Dragon: Query-Aware Dynamic RAG System for Knowledge-Intensive Visual Question Answering

Dynamic retrieval-augmented generation system for visual question answering that retrieves from both text and images to handle complex multimodal queries.

Ax Lei Chen, Xuanle Zhao, Zhixiong Zeng, Jing Huang, Liming Zheng, Yufeng Zhong, Lin Ma 3/17/2026

Breaking the SFT Plateau: Multimodal Structured Reinforcement Learning for Chart-to-Code Generation

Multimodal reinforcement learning approach for chart-to-code generation that combines structured output requirements with visual reasoning on information-rich images.

Ax Zhehao Dong, Xiaofeng Wang, Zheng Zhu, Yirui Wang, Yang Wang, Yukun Zhou, Boyuan Wang, Chaojun Ni, Runqi Ouyang, Wenkang Qin, Xinze Chen, Yun Ye, Guan Huang, Zhen Lu, Yue Yang 3/17/2026

EMMA: Generalizing Real-World Robot Manipulation via Generative Visual Transfer

Data augmentation framework for vision-language-action models in robot manipulation using generative visual transfer to reduce annotation costs.

Ax Zhenxing Xu, Yizhe Zhang, Weidong Bao, Hao Wang, Ming Chen, Haoran Ye, Wenzheng Jiang, Hui Yan, Ji Wang 3/17/2026

AutoEP: LLMs-Driven Automation of Hyperparameter Evolution for Metaheuristic Algorithms

Framework using LLMs as zero-shot reasoning engines to automate hyperparameter configuration for metaheuristic algorithms without training.

Ax Qingjie Zhang, Yujia Fu, Yang Wang, Liu Yan, Tao Wei, Ke Xu, Minlie Huang, Han Qiu 3/17/2026

Stop Before You Fail: Operational Capability Boundaries for Mitigating Unproductive Reasoning in Large Reasoning Models

Method to detect and mitigate unproductive reasoning in large reasoning models by identifying early signals predicting capability boundary violations.

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.