Ax Qiang He, Yucheng Yang, Tianyi Zhou, Meng Fang, Mykola Pechenizkiy, Setareh Maghsudi 4/7/2026

One Model for All: Multi-Objective Controllable Language Models

Research paper on controllable LLMs with multi-objective alignment to varying human preferences, extending beyond fixed reward RLHF approaches.

Ax Hengshuai Yao, Xing Chen, Ahmed Murtadha, Guan Wang 4/7/2026

GAIN: Multiplicative Modulation for Domain Adaptation

GAIN method uses multiplicative modulation for domain adaptation in LLMs, re-emphasizing existing features instead of injecting new directions.

Ax Ole Delzer, Sidney Bender 4/7/2026

Reproducibility study on how to find Spurious Correlations, Shortcut Learning, Clever Hans or Group-Distributional non-robustness and how to fix them

Reproducibility study on detecting and fixing spurious correlations, shortcut learning, and group-distributional non-robustness in DNNs.

Ax Hohyun Sim, Hyeonjoong Cho, Ali Shokri, Zhoulai Fu, Binoy Ravindran 4/7/2026

ENCRUST: Encapsulated Substitution and Agentic Refinement on a Live Scaffold for Safe C-to-Rust Translation

ENCRUST pipeline for safe C-to-Rust translation using agentic LLM refinement with whole-program reasoning on live scaffolds.

Ax Alhasan Mahmood, Samir Abdaljalil, Hasan Kurban 4/7/2026

Multilingual Prompt Localization for Agent-as-a-Judge: Language and Backbone Sensitivity in Requirement-Level Evaluation

Study showing evaluation language choice inverts agent-as-judge rankings across five languages on 55 development tasks, revealing backbone sensitivity.

Ax Zheng Li, Jerry Cheng, Huanying Helen Gu 4/7/2026

StableTTA: Training-Free Test-Time Adaptation that Improves Model Accuracy on ImageNet1K to 96%

StableTTA training-free test-time adaptation method improving ensemble prediction stability and computational efficiency on ImageNet.

Ax Charafeddine Mouzouni 4/7/2026

Mapping the Exploitation Surface: A 10,000-Trial Taxonomy of What Makes LLM Agents Exploit Vulnerabilities

Systematic taxonomy from 10,000 trials identifying which system prompt features trigger LLM agents to exploit security vulnerabilities across models.

Ax Mingzhe Du, Luu Anh Tuan, Dong Huang, See-kiong Ng 4/7/2026

Paper Espresso: From Paper Overload to Research Insight

Paper Espresso open-source platform automatically discovers, summarizes and analyzes trending arXiv papers using LLMs with structured labeling.

Ax Madhav S Baidya 4/7/2026

PassiveQA: A Three-Action Framework for Epistemically Calibrated Question Answering via Supervised Finetuning

PassiveQA framework for calibrated question answering that handles incomplete or ambiguous queries through three-action decision awareness.

Ax Byeolhee Kim, Min-Kyung Kim, Young-Hak Kim, Tae-Joon Jeon 4/7/2026

Ruling Out to Rule In: Contrastive Hypothesis Retrieval for Medical Question Answering

Contrastive hypothesis retrieval method for medical RAG systems that suppresses clinically distinct but semantically similar negatives.

Ax Luca Nannini, Adam Leon Smith, Michele Joshua Maggini, Enrico Panai, Sandra Feliciano, Aleksandr Tiulkanov, Elena Maran, James Gealy, Piercosma Bisconti 4/7/2026

AI Agents Under EU Law

Legal analysis of how EU AI Act regulates autonomous AI agents across enterprise functions including customer service and clinical decision support.

Ax Rongfeng Zhao, Xuanhao Zhang, Zhaochen Guo, Xiang Shao, Zhongpan Zhu, Bin He, Jie Chen 4/7/2026

ROSClaw: A Hierarchical Semantic-Physical Framework for Heterogeneous Multi-Agent Collaboration

ROSClaw framework integrates LLMs with embodied agents to bridge semantic understanding and physical execution for multi-agent robot collaboration tasks.

Ax Deirdre O'Regan, Anil C. Kokaram 4/7/2026

An AI Teaching Assistant for Motion Picture Engineering

Implementation of LLM-based AI teaching assistant using RAG for a Master's program in motion picture engineering.

Ax Jaeyoon Jung, Yejun Yoon, Kunwoo Park 4/7/2026

Is a Picture Worth a Thousand Words? Adaptive Multimodal Fact-Checking with Visual Evidence Necessity

Research on multimodal fact-checking showing visual evidence doesn't universally improve performance in automated fact-checking systems.

Ax Seoungsub Lee, In Seo Kim, Seon Wook Kim 4/7/2026

MUXQ: Mixed-to-Uniform Precision MatriX Quantization via Low-Rank Outlier Decomposition

Quantization method for LLMs using mixed-to-uniform precision and low-rank decomposition for efficient on-device deployment.

Ax Abdullah Al Shafi, Swapnil Kundu Argha, M. A. Moyeen, Abdul Muntakim, Shoumik Barman Polok 4/7/2026

BiST: A Gold Standard Bangla-English Bilingual Corpus for Sentence Structure and Tense Classification with Inter-Annotator Agreement

Bilingual corpus of Bangla-English sentences annotated for syntactic structure and tense for low-resource multilingual NLP.

Ax Dayeon Ki, Kevin Duh, Marine Carpuat 4/7/2026

What Makes Good Multilingual Reasoning? Disentangling Reasoning Traces with Measurable Features

Analysis of what characterizes effective reasoning in multilingual large reasoning models, challenging assumptions that English reasoning patterns transfer.

Ax Serena Liu, Yutong Yang, Prisha Sheth, Weixuan Dong, Mingjiao Diao, Xinru Zhu, Nikhil Banga, Oscar Melendez, Arnav Sharma, Minda Zhao, Marina Lin, Mengyu Wang 4/7/2026

Individual and Combined Effects of English as a Second Language and Typos on LLM Performance

Study analyzing combined effects of English as second language and typographical errors on LLM performance in multilingual contexts.

Ax Yuan Chang, Jiaming Qu, Zhu Li 4/7/2026

Metaphors We Compute By: A Computational Audit of Cultural Translation vs. Thinking in LLMs

Computational audit examining whether LLMs conduct culture-aware reasoning or merely translate between cultures in creative writing tasks.

Ax Kanishk Jain, Qian Yang, Shravan Nayak, Parisa Kordjamshidi, Nishanth Anand, Aishwarya Agrawal 4/7/2026

Discovering Failure Modes in Vision-Language Models using RL

Reinforcement learning approach for automatically discovering failure modes in vision-language models beyond manual evaluation.

Ax Asena Karolin \"Ozdemir, Lars H. Heyen, Arvid Weyrauch, Achim Streit, Markus G\"otz, Charlotte Debus 4/7/2026

Sampling Parallelism for Fast and Efficient Bayesian Learning

Sampling parallelism method for efficient Bayesian neural networks and uncertainty quantification in risk-sensitive domains.

Ax Kalyan Cherukuri, Lav R. Varshney 4/7/2026

Hallucination Basins: A Dynamic Framework for Understanding and Controlling LLM Hallucinations

Geometric dynamical systems framework explaining LLM hallucinations as arising from basin structure in latent space with task-dependent separability.

Ax Vinod Vaikuntanathan, Or Zamir 4/7/2026

Undetectable Conversations Between AI Agents via Pseudorandom Noise-Resilient Key Exchange

Protocol enabling two AI agents to carry out secret conversations while producing transcripts indistinguishable from honest interactions to passive auditors.

Ax Zijun Wang, Haoqin Tu, Letian Zhang, Hardy Chen, Juncheng Wu, Xiangyan Liu, Zhenlong Yuan, Tianyu Pang, Michael Qizhe Shieh, Fengze Liu, Zeyu Zheng, Huaxiu Yao, Yuyin Zhou, Cihang Xie 4/7/2026

Your Agent, Their Asset: A Real-World Safety Analysis of OpenClaw

Real-world safety evaluation of OpenClaw personal AI agent analyzing attack surface and vulnerabilities in local system access and service integrations.

Ax Justin Chih-Yao Chen, Archiki Prasad, Zaid Khan, Joykirat Singh, Runchu Tian, Elias Stengel-Eskin, Mohit Bansal 4/7/2026

Cog-DRIFT: Exploration on Adaptively Reformulated Instances Enables Learning from Hard Reasoning Problems

Method enabling LLMs to learn from hard reasoning problems through adaptive task reformulation with reinforcement learning from verifiable rewards.

Ax Chenxi Wang, Zhuoyun Yu, Xin Xie, Wuguannan Yao, Runnan Fang, Shuofei Qiao, Kexin Cao, Guozhou Zheng, Xiang Qi, Peng Zhang, Shumin Deng 4/7/2026

SkillX: Automatically Constructing Skill Knowledge Bases for Agents

Framework for automatically constructing plug-and-play skill knowledge bases for LLM agents to improve learning efficiency and generalization.

Ax Naveen Raman, Stephanie Milani, Fei Fang 4/7/2026

Selecting Decision-Relevant Concepts in Reinforcement Learning

Algorithms for automatic selection of interpretable concepts for reinforcement learning agents without manual domain expertise.

Ax Cheng Xu, Changhong Jin, Yingjie Niu, Nan Yan, Yuke Mei, Shuhao Guan, Liming Chen, M-Tahar Kechadi 4/7/2026

LiveFact: A Dynamic, Time-Aware Benchmark for LLM-Driven Fake News Detection

Dynamic benchmark for evaluating LLM-based fake news detection and fact-checking with time-aware evaluation to address benchmark contamination issues.

Ax Sercan Karaka\c{s} 4/7/2026

Plausibility as Commonsense Reasoning: Humans Succeed, Large Language Models Do not

Study examining whether LLMs integrate world knowledge with syntactic structure in human-like ways using Turkish relative-clause attachment ambiguities as test cases.

Ax Yude Zou, Junji Gong, Xing Gao, Zixuan Li, Tianxing Chen, Guanjie Zheng 4/7/2026

InfBaGel: Human-Object-Scene Interaction Generation with Dynamic Perception and Iterative Refinement

Framework for generating human-object-scene interactions using instruction-conditioned generation with iterative refinement for embodied AI and simulation applications.

Ax Jiling Zhou, Aisvarya Adeseye, Seppo Virtanen, Antti Hakkala, Jouni Isoaho 4/7/2026

Strengthening Human-Centric Chain-of-Thought Reasoning Integrity in LLMs via a Structured Prompt Framework

Structured prompt framework for improving chain-of-thought reasoning integrity in LLMs for analytical tasks. Addresses reliability issues.

Ax James Hu, Mahdi Ghelichi 4/7/2026

Noise Immunity in In-Context Tabular Learning: An Empirical Robustness Analysis of TabPFN's Attention Mechanisms

Robustness analysis of TabPFN attention mechanisms under noisy tabular data in few-shot learning. Tabular model evaluation.

Ax Ke Li, Maoliang Li, Jialiang Chen, Jiayu Chen, Zihao Zheng, Shaoqi Wang, Xiang Chen 4/7/2026

DIRECT: Video Mashup Creation via Hierarchical Multi-Agent Planning and Intent-Guided Editing

Multi-agent planning system for automated video mashup creation with hierarchical orchestration. Cross-modal video editing application.

Ax Hengrui Gu, Xiaotian Han, Yujing Bian, Kaixiong Zhou 4/7/2026

Rethinking Exploration in RLVR: From Entropy Regularization to Refinement via Bidirectional Entropy Modulation

Entropy modulation approach for exploration in LLM reasoning with verifiable rewards. Addresses restricted exploration problem.

Ax Rafael O. Jarczewski, Gabriel U. Talasso, Leandro Villas, Allan M. de Souza 4/7/2026

Agentic Federated Learning: The Future of Distributed Training Orchestration

Framework using LLM agents to adapt federated learning orchestration to client heterogeneity and system dynamics. Improves distributed training.

Ax Shuai Liu, Shulin Tian, Kairui Hu, Yuhao Dong, Zhe Yang, Bo Li, Jingkang Yang, Chen Change Loy, Ziwei Liu 4/7/2026

FileGram: Grounding Agent Personalization in File-System Behavioral Traces

Framework for personalizing file-system agents using behavioral traces from local systems. Addresses privacy constraints in coworking AI.

Ax Mohammad Zangooei, Jannis Weil, Amr Rizk, Mina Tahmasbi Arashloo, Raouf Boutaba 4/7/2026

Analyzing Symbolic Properties for DRL Agents in Systems and Networking

Verification methods for deep RL agents in systems/networking to analyze behavior across system states. Addresses safe deployment.

Ax Gabriel Sarch, Linrong Cai, Qunzhong Wang, Haoyang Wu, Danqi Chen, Zhuang Liu 4/7/2026

Vero: An Open RL Recipe for General Visual Reasoning

Open-source visual reasoning VLM family matching proprietary models on charts, science, and spatial tasks. Includes training recipes and open weights.

Ax Parsa Hosseini, Sumit Nawathe, Mahdi Salmani, Meisam Razaviyayn, Soheil Feizi 4/7/2026

Early Stopping for Large Reasoning Models via Confidence Dynamics

Method to optimize inference cost in reasoning LLMs by detecting when to stop generation via confidence dynamics. Improves computational efficiency.

Ax Zun Li, Marc Lanctot, Kevin R. McKee, Luke Marris, Ian Gemp, Daniel Hennes, Paul Muller, Kate Larson, Yoram Bachrach, Michael P. Wellman 4/7/2026

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

Scalable opponent modeling combining tree search, generative models, and Nash bargaining for game-theoretic RL. Addresses imperfect information games.

Ax Dinesh Sharma, Ankit Shah, Chaitra Gopalappa 4/7/2026

A Multi-Agent Reinforcement Learning Framework for Public Health Decision Analysis

Multi-agent RL framework for HIV epidemic control optimization. Public health policy application.

Ax Xiaojie Xu, Zongyuan Li, Chang Lu, Runnan Qi, Yanan Ni, Lumin Jiang, Xiangbei Liu, Xuebo Zhang, Yongchun Fang, Kuihua Huang, Xian Guo, Zhanghua Wu, Zhenya Li 4/7/2026

Reflection of Episodes: Learning to Play Game from Expert and Self Experiences

Framework combining LLM self-reflection with expert and self-experience for StarCraft II gameplay. Addresses complex environment learning.

Ax Yukun Huang, Sanxing Chen, Jian Pei, Manzil Zaheer, Bhuwan Dhingra 4/7/2026

Cite Pretrain: Retrieval-Free Knowledge Attribution for Large Language Models

Method for LLMs to generate reliable citations without external retrievers by leveraging pretraining knowledge. Improves inference efficiency.

Ax Michael Katz, Harsha Kokel, Sarath Sreedharan 4/7/2026

Seemingly Simple Planning Problems are Computationally Challenging: The Countdown Game

Benchmark for evaluating long-term planning capabilities of LLMs and AI agents. Addresses gap in existing planning benchmarks.

Ax Kei-Sing Ng 4/7/2026

Similarity Field Theory: A Mathematical Framework for Intelligence

Mathematical framework formalizing similarity relations as structural basis for dynamic systems. Theoretical foundational work.

Ax Lianhao Zhou, Hongyi Ling, Cong Fu, Yepeng Huang, Michael Sun, Wendi Yu, Xiaoxuan Wang, Xiner Li, Xingyu Su, Junkai Zhang, Xiusi Chen, Chenxing Liang, Xiaofeng Qian, Heng Ji, Wei Wang, Marinka Zitnik, Shuiwang Ji 4/7/2026

Autonomous Agents for Scientific Discovery: Orchestrating Scientists, Language, Code, and Physics

Survey of autonomous LLM agents for scientific discovery, orchestrating human scientists, code, and physics simulations.

Ax Anshuman Chhabra, Shrestha Datta, Shahriar Kabir Nahin, Prasant Mohapatra 4/7/2026

Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges

Survey of security threats, defenses, and evaluation methods for agentic AI systems with tool use, planning, and autonomous execution.

Ax Chun Chet Ng, Jia Yu Lim, Wei Zeng Low 4/7/2026

PRISM: Prompt-Refined In-Context System Modelling for Financial Retrieval

PRISM: Training-free framework combining prompt engineering and multi-agent coordination for financial document retrieval with LLMs.

Ax Alexander Zadorojniy, Segev Wasserkrug, Eitan Farchi 4/7/2026

An Agent-Based Framework for the Automatic Validation of Mathematical Optimization Models

Agent-based framework for automatic validation of mathematical optimization models generated by LLMs from natural language descriptions.

Ax Leijie Wang, Otilia Stretcu, Wei Qiao, Thomas Denby, Krishnamurthy Viswanathan, Enming Luo, Chun-Ta Lu, Tushar Dogra, Ranjay Krishna, Ariel Fuxman 4/7/2026

Agile Deliberation: Concept Deliberation for Subjective Visual Classification

Research on iterative concept refinement for vision classifiers through human-in-the-loop deliberation for subjective visual tasks.