Ax Anuradha Chandrasekaran, Dimitrios Zikos, Mutlu Mete, Alan Pang, Brady D. Lund, Kewei Sha 5/6/2026

NEURON: A Neuro-symbolic System for Grounded Clinical Explainability

Neuro-symbolic system combining SNOMED CT ontology with machine learning for interpretable clinical AI predictions.

Ax Zhouhao Sun, Xuan Zhang, Xiao Ding, Bibo Cai, Li Du, Kai Xiong, Xinran Dai, Fei Zhang, weidi tang, Zhiyuan Kan, Yang Zhao, Bing Qin, Ting Liu 5/6/2026

GR-Ben: A General Reasoning Benchmark for Evaluating Process Reward Models

Benchmark for evaluating process reward models across diverse reasoning tasks beyond mathematics, enabling detection of intermediate reasoning errors.

Ax Haowen Hu, Pengzhou Cheng, Zheng Wu, Lingzhong Dong, Gongshen Liu, Zhuosheng Zhang 5/6/2026

Faithful Mobile GUI Agents with Guided Advantage Estimator

Framework improving faithfulness in vision-language GUI agents by grounding actions in screen evidence and user instructions via guided advantage estimation.

Ax Siqi Zhu 5/6/2026

Agentic AI Systems Should Be Designed as Marginal Token Allocators

Position paper proposing agentic systems be designed as token allocation economies with specialized layers for routing, planning, and action selection.

Ax Sai Ma, Zhuang Li, Sichao Li, Xinyue Xu, Ruibiao Zhu, Tony Boston, John A. Taylor 5/6/2026

EO-Gym: A Multimodal, Interactive Environment for Earth Observation Agents

Interactive simulation environment for training multimodal agents to perform Earth observation analysis with tool use and uncertainty resolution.

Ax Jie-Jing Shao, Haiyan Yin, Yueming Lyu, Xingrui Yu, Lan-Zhe Guo, Ivor Tsang, James Kwok, Yu-Feng Li 5/6/2026

Lifting Traces to Logic: Programmatic Skill Induction with Neuro-Symbolic Learning for Long-Horizon Agentic Tasks

Neuro-symbolic framework for inducing executable skills from agent interactions, combining LLM reasoning with programmatic logic for long-horizon planning in dynamic environments.

Ax Lei Gao, Zhuoming Li, Mengxi Jia, Jiakang Yuan, Hongbo Sun, Hao Sun, Xuelong Li 5/6/2026

Segment-Aligned Policy Optimization for Multi-Modal Reasoning

Policy optimization method aligning RL credit assignment with natural reasoning steps in multi-modal tasks at segment granularity rather than token or sequence level.

Ax Shijun Lei, Hongyu Wang, Yunji Liang, Haowen Zheng, Bin Guo, Zhiwen Yu 5/6/2026

Truth or Tribe: How In-group Favoritism Prioritize Facts in Persona Agents

Study of in-group favoritism biases in persona agents facing contradicting information and methods to mitigate adverse effects on factual accuracy.

Ax Jincheng Lou, Ruohan Xu, Jiapeng Li, Junyin Pi, Runzhe Tao, Weijian Fan, Xiao Tan, Guojie Luo, Yibo Lin 5/6/2026

DiagramNet: An End-to-End Recognition Framework and Dataset for Non-Standard System-Level Diagrams

Multimodal dataset and recognition framework for non-standard system-level chip design diagrams to improve MLLM understanding of architectural specifications.

Ax Alessio Donvito, Antonio Lieto 5/6/2026

Structural Ranking of the Cognitive Plausibility of Computational Models of Analogy and Metaphors with the Minimal Cognitive Grid

Evaluation of cognitive plausibility for computational models of analogy and metaphor including SME, CogSketch, and LLMs using the Minimal Cognitive Grid framework.

Ax Wesley Shu, Peng Wei 5/6/2026

AI Safety as Control of Irreversibility: A Systems Framework for Decision-Energy and Sovereignty Boundaries

Systems framework analyzing AI safety through irreversibility control and deployment friction reduction in autonomous decision-making systems.

Ax Seokhyun Lee, Jaeho Kim, Changjun Oh, Mihaela van der Schaar, Changhee Lee 5/6/2026

TimeTok: Granularity-Controllable Time-Series Generation via Hierarchical Tokenization

Hierarchical tokenization framework for time-series generation enabling user control over temporal granularity from sketches or scratch.

Ax Wesley Shu, Peng Wei 5/6/2026

Artificial Jagged Intelligence as Uneven Optimization Energy Allocation Capability Concentration, Redistribution, and Optimization Governance

Formal theory of Artificial Jagged Intelligence modeling uneven optimization pressure across capability domains during training as finite-budget gradient allocation.

Ax Shuaipeng Zhou, Yu Zhang 5/6/2026

SCALE-LoRA: Auditing Post-Retrieval LoRA Composition with Residual Merging and View Reliability

Method for auditing and composing LoRA adapter libraries with residual merging and reliability assessment for task-level reuse and instance-level selection.

Ax Yasir Mahmood, Arnab Sharma, Axel-Cyrille Ngonga Ngomo, Balram Tiwari 5/6/2026

Rethinking Explanations: Formalizing Contrast in Description Logics

Formal framework for explaining entailments in description logic knowledge bases with user-centered contrast-based approach beyond traditional justifications.

Ax Guowei Zou, Haitao Wang, Beiwen Zhang, Boning Zhang, Hejun Wu 5/6/2026

CoFlow: Coordinated Few-Step Flow for Offline Multi-Agent Decision Making

Few-step generative model for offline multi-agent reinforcement learning enabling coordinated inference without sacrificing inter-agent coordination.

Ax Yunhan Bu, Quan Zhang, Huaping Zhang, Guotong Geng, Chunxiao Gao, Askar Hamdulla, Juan Wang, Qiuchi Li, Baohua Zhang, Shuai Lei, Yunbo Cao, Zhunchen Luo 5/6/2026

Grounding Multi-Hop Reasoning in Structural Causal Models via Group Relative Policy Optimization

Framework grounding multi-hop fact verification in structural causal models using group relative policy optimization to improve LLM reasoning and reduce hallucinations.

Ax Qinchuan Cheng, Ruixuan Xie, Jiaqi Liu, Xiaoya Yuan, Yuxin Liu 5/6/2026

MAP-Law: Coverage-Driven Retrieval Control for Multi-Turn Legal Consultation

Multi-turn legal consultation agent using coverage-driven retrieval control to determine sufficient evidence and relevant legal issues.

Ax Tianshi Zheng, Rui Wang, Xiyun Li, Yangqiu Song, Tianqing Fang 5/6/2026

SciResearcher: Scaling Deep Research Agents for Frontier Scientific Reasoning

Deep research agents for automated scientific discovery using post-training on information-seeking tasks and iterative problem-solving capabilities.

Ax Jiyao Wang, Yunbiao Wang, Yubo Jiao, Xiao Yang, Dengbo He, Sasan Jafarnejad, Luis Miranda-Moreno, Raphael Frank, Jiangbo Yu 5/6/2026

MILD: Mediator Agent System with Bidirectional Perception and Multi-Layered Alignment for Human-Vehicle Collaboration

Agent system for human-vehicle collaboration using bidirectional perception and alignment to improve driver-automation coordination and situational awareness.

Ax Florian Valentin Wunderlich, Lars Benedikt Kaesberg, Jan Philip Wahle, Terry Ruas, Bela Gipp 5/6/2026

Multi-Agent Reasoning Improves Compute Efficiency: Pareto-Optimal Test-Time Scaling

Analysis of inference scaling strategies including self-consistency, self-refinement, and multi-agent debate for compute-efficient LLM performance improvement.

Ax Mukund Pandey 5/6/2026

Evaluating Agentic AI in the Wild: Failure Modes, Drift Patterns, and a Production Evaluation Framework

Evaluation framework for production agentic AI systems addressing compounding errors, tool failures, output drift, and long-horizon task evaluation beyond lab-scale benchmarks.

Ax Yuliang Song, Eldan Cohen 5/6/2026

CP-SynC: Multi-Agent Zero-Shot Constraint Modeling in MiniZinc with Synthesized Checkers

Multi-agent system using LLMs to translate natural language into constraint programming models with synthesized validation checkers to reduce semantic errors.

Ax Keon Woo Kim 5/6/2026

Latent State Design for World Models under Sufficiency Constraints

Framework for designing latent state representations in world models for agents, categorizing methods by functional purpose rather than implementation approach.

Ax Vincent Schmalbach 5/6/2026

Model Routing as a Trust Problem: Route Receipts for Adaptive AI Systems

Research on routing mechanisms in AI systems and their impact on trust, cost, quality, and accountability of responses across different service tiers and endpoints.

Ax Huiqian Lai 5/6/2026

Are LLMs More Skeptical of Entertainment News?

Study of genre bias in LLM credibility assessment, showing models misclassify entertainment news more than hard news.

Ax Yue Ma, Ziyuan Yang, Yi Zhang 5/6/2026

Catching the Infection Before It Spreads: Foresight-Guided Defense in Multi-Agent Systems

Defense mechanism against infectious jailbreak attacks in multi-agent systems through foresight-guided strategies.

Ax Rishabh Kar 5/6/2026

Runtime Evaluation of Procedural Content Generation in an Endless Runner Game Using Autonomous Agents

Momentum: game with runtime procedural content generation evaluated by autonomous agents for balance and playability.

Ax Qisong Zhang (School of Artificial Intelligence, Beijing University of Posts and Telecommunications), Wenzhuo Wu (School of Artificial Intelligence, Beijing University of Posts and Telecommunications), Zhuangzhuang Jia (School of Artificial Intelligence, Beijing University of Posts and Telecommunications), Yunhao Yang (School of Artificial Intelligence, Beijing University of Posts and Telecommunications), Huayu Zhang (Institute of Artificial Intelligence), Xianghao Zang (Institute of Artificial Intelligence), Zhixiang He (Institute of Artificial Intelligence), Zhongjiang He (Institute of Artificial Intelligence), Kongming Liang (School of Artificial Intelligence, Beijing University of Posts and Telecommunications), Zhanyu Ma (School of Artificial Intelligence, Beijing University of Posts and Telecommunications) 5/6/2026

DataEvolver: Let Your Data Build and Improve Itself via Goal-Driven Loop Agents

DataEvolver: closed-loop visual data generation system using goal-driven agents for iterative dataset creation and improvement.

Ax Thomas Eiter, Katsumi Inoue, Sota Moriyama 5/6/2026

Neural Decision-Propagation for Answer Set Programming

Decision-propagation method integrating Answer Set Programming with neural networks for scalable neuro-symbolic reasoning.

Ax Jia Xiao 5/6/2026

NeuroState-Bench: A Human-Calibrated Benchmark for Commitment Integrity in LLM Agent Profiles

NeuroState-Bench: human-calibrated benchmark evaluating commitment integrity in multi-turn LLM agent tasks via side-query probes.

Ax Manuel Hern\'andez, Eduardo S\'anchez-Soto 5/6/2026

Sheaf-Theoretic Planning: A Categorical Foundation for Resilient Multi-Agent Autonomous Systems

Categorical sheaf-theoretic framework for resilient multi-agent autonomous systems planning in stochastic environments.

Ax George Fatouros, Georgios Makridis, John Soldatos, Dimosthenis Kyriazis, Pedro Malo, George Kousiouris, Giannis Ledakis, Louiza Kachrimani, Panagiotis Rizomiliotis, Bruno Almeida, Despina Tomkou, Kostas Metaxas, Konstantinos Ilias, Christos Gkizelis, Ernstjan de Gooyert, Amin Babazadeh, Kostis Mavrogiorgos, Pepi Paraskevoulakou, Christos Xenakis, Giannis Chouchoulis, Konstantina Tripodi 5/6/2026

CyberAId: AI-Driven Cybersecurity for Financial Service Providers

AI-driven cybersecurity system for financial institutions using LLMs to enhance SOC reasoning capacity and alert investigation.

Ax Jiajia Li, Xiaoyu Wen, Zhongtian Ma, Shuyue Hu, Qiaosheng Zhang, Zhen Wang 5/6/2026

Disentangling Intent from Role: Adversarial Self-Play for Persona-Invariant Safety Alignment

Adversarial self-play defense against persona-based jailbreak attacks in LLMs through intent-role disentanglement.

Ax Noga Peleg Pelc, Gal A. Kaminka, Yoav Goldberg 5/6/2026

A Language for Describing Agentic LLM Contexts

Formal language specification for encoding LLM agent context composition, standardizing context engineering practices.

Ax Polydoros Giannouris, Yuechen Jiang, Lingfei Qian, Yuyan Wang, Xueqing Peng, Jimin Huang, Guojun Xiong, Sophia Ananiadou 5/6/2026

Moira: Language-driven Hierarchical Reinforcement Learning for Pair Trading

Hierarchical reinforcement learning with language for pair trading, addressing credit assignment in long-horizon semantic tasks.

Ax Ahmet Bahaddin Ersoz 5/6/2026

12 Angry AI Agents: Evaluating Multi-Agent LLM Decision-Making Through Cinematic Jury Deliberation

Multi-agent LLM benchmark using 12 AI agents with film personas to evaluate deliberation and reasoning capabilities.

Ax Abrar Hossain Zahin, Amit Kumar Saha, Tanvir Mridha, Saifur Rahman, Jannatul Ferdous Prome, Raima Husna, Israt Jahan, Ahmed Wasif Reza 5/6/2026

TumorXAI: Self-Supervised Deep Learning Framework for Explainable Brain MRI Tumor Classification

Self-supervised learning framework for brain tumor classification using SSL methods (SimCLR, BYOL, DINO, Moco v3) on MRI data.

Ax Zhongqi Yang, Mahkameh Rasouli, Neda Mohseni, Yong Huang, Iman Azimi, Amir M. Rahmani 5/6/2026

Personalized Digital Health Modeling with Adaptive Support Users

Personalized digital health modeling framework using adaptive weighting for heterogeneous user data with limited annotations.

Ax Hengyu Liu, Tianyi Li, Zhihong Cui, Yushuai Li, Zhangkai Wu, Torben Bach Pedersen, Kristian Torp, Christian S. Jensen 5/6/2026

Reliable AI Needs to Externalize Implicit Knowledge: A Human-AI Collaboration Perspective

Position paper on externalizing implicit knowledge in AI systems for reliability through human-AI collaboration infrastructure.

Ax Chloe Li, Sara Price, Samuel Marks, Jon Kutasov 5/6/2026

Model Spec Midtraining: Improving How Alignment Training Generalizes

Model Spec Midtraining improves LLM alignment generalization by training on specification-aligned behavior before final fine-tuning.

Ax Bing Zhou, Xiao Huang, Huan Ning, Qiusheng Wu, Diya Li, Ziyi Zhang 5/6/2026

NORA: A Harness-Engineered Autonomous Research Agent for End-to-End Spatial Data Science

NORA: multi-agent autonomous research system specialized for spatial data science workflows, automating scientific research end-to-end.

Ax Terry Dorsey, Kevin Huggins 5/6/2026

The Dynamic Gist-Based Memory Model (DGMM): A Memory-Centric Architecture for Artificial Intelligence

Proposes DGMM architecture addressing memory, temporal grounding, and interpretability limitations in LLMs through gist-based memory mechanisms.

Ax Wenyi Wu, Sibo Zhu, Kun Zhou, Biwei Huang 5/6/2026

Planner Matters! An Efficient and Unbalanced Multi-agent Collaboration Framework for Long-horizon Planning

arXiv paper proposing multi-agent framework with planner, actor, and memory manager roles for long-horizon LM-based task automation.

Ax Eric H. C. Chow 5/6/2026

Retrieval and Multi-Hop Reasoning in 1M-Token Context Windows: Evaluating LLMs on Classical Chinese Text

arXiv paper evaluating 1M-token context window retrieval and multi-hop reasoning in frontier LLMs on classical Chinese texts.

Ax Brendan McCane 5/6/2026

Intervention Complexity as a Canonical Reward and a Measure of Intelligence

arXiv paper proposing intervention complexity as canonical reward measure for general intelligence in computable environments.

Ax Haixin Wang, Hejie Cui, Chenwei Zhang, Xin Liu, Shuowei Jin, Shijie Geng, Xinyang Zhang, Nasser Zalmout, Zhenyu Shi, Yizhou Sun 5/6/2026

T$^2$PO: Uncertainty-Guided Exploration Control for Stable Multi-Turn Agentic Reinforcement Learning

arXiv paper on uncertainty-guided exploration for stabilizing multi-turn reinforcement learning in agentic LLMs.

Ax Nishant Bhargava, Rodrigo Sobral Barrento 5/6/2026

MEMAUDIT: An Exact Package-Oracle Evaluation Protocol for Budgeted Long-Term LLM Memory Writing

arXiv paper introducing MEMAUDIT protocol for evaluating long-term memory writing in budgeted LLM agents independent of retrieval and reasoning.

Ax Ji Guo, Xiaolong Qin, Cencen Liu, Jielei Wang, Jierun Chen, Wenbo Jiang 5/6/2026

CBV: Clean-label Backdoor Attacks on Vision Language Models via Diffusion Models

arXiv paper on clean-label backdoor attacks against vision-language models using diffusion model-generated triggers.

Ax Alexander Smola 5/6/2026

Submodular Benchmark Selection

arXiv paper formalizing efficient benchmark selection for LLM evaluation as submodular maximization problem.