Ax Soham Wasmatkar, Subinay Adhikary, Rakshit Rohan, Shouvik Kumar Guha, Saptarshi Pyne, Kripabandhu Ghosh 5/6/2026

Can Causal Discovery Algorithms Help in Generating Legal Arguments?

Explores whether causal discovery algorithms can improve legal argument generation using Pearl's framework for probabilistic reasoning.

Ax Yiheng Zhang, Yiming Wang, Kaiyan Zhao, Zhenglin Wan, Jiayu Chen, Leong Hou U 5/6/2026

ANO: A Principled Approach to Robust Policy Optimization

ANO optimizer unifies trust region frameworks to address PPO's hard clipping trade-off between sample efficiency and optimization stability.

Ax Zhisheng Tang, Mayank Kejriwal 5/6/2026

A Compound AI Agent for Conversational Grant Discovery

Compound AI system aggregating 12,000 federal grants across fragmented US agency portals (NSF, NIH, DARPA) for unified grant discovery.

Ax Yinghui Chi, Lucien Wang 5/6/2026

Controllable and Verifiable Process Data Synthesis for Process Reward Models

Controllable framework for synthesizing process supervision data with template-aware error injection and trajectory consistency for training process reward models.

Ax Jianing Wang, Linsen Guo, Zhengyu Chen, Qi Guo, Hongyu Zang, Wenjie Shi, Haoxiang Ma, Xiangyu Xi, Xiaoyu Li, Wei Wang, Xunliang Cai 5/6/2026

HeavySkill: Heavy Thinking as the Inner Skill in Agentic Harness

HeavySkill framework analyzes heavy thinking as the core execution unit in agentic systems with orchestration, memory, skills, and tool use.

Ax Rahul Kumar 5/6/2026

The Compliance Trap: How Structural Constraints Degrade Frontier AI Metacognition Under Adversarial Pressure

SCHEMA evaluation reveals cognitive collapse in frontier AI models under adversarial pressure, a safety failure mode beyond deception detection.

Ax Kyle Zheng, Han Zhang, Renliang Sun, Chenchen Ye, Wei Wang 5/6/2026

FitText: Evolving Agent Tool Ecologies via Memetic Retrieval

FitText framework makes tool retrieval dynamic in agent reasoning loops, bridging semantic gaps between task descriptions and API documentation across thousands of endpoints.

Ax Tu Nguyen, Rasul Tutunov, Xiaotong Ji, Matthieu Zimmer 5/6/2026

The Model Knows, the Decoder Finds: Future Value Guided Particle Power Sampling

Power sampling method for efficient LLM decoding that locates high-probability solution modes by targeting p_theta(x)^alpha with future-dependent corrections.

Ax Munachiso Samuel Nwadike, Zangir Iklassov, Kareem Ali, Rifo Genadi, Kentaro Inui 5/6/2026

Measuring AI Reasoning: A Guide for Researchers

Guide for evaluating LLM reasoning through adaptive multi-step search rather than final-answer accuracy, formalizing reasoning as search procedures.

Ax Xiyuan Wang, Yi Hu, Yanbo Wang, Chuan Shi, Muhan Zhang 5/6/2026

Position: How can Graphs Help Large Language Models?

Position paper exploring how graph structures can enhance LLM capabilities through knowledge representation, up-to-date information, and improved reasoning.

Ax David Wilmot 5/6/2026

Shadow-Loom: Causal Reasoning over Graphical World Model of Narratives

Open-source Shadow-Loom framework converts narratives into versioned graphical world models with causal physics and counterfactual reasoning engines.

Ax Jinliang Xu 5/6/2026

GRAIL: A Deep-Granularity Hybrid Resonance Framework for Real-Time Agent Discovery via SLM-Enhanced Indexing

GRAIL framework for efficient LLM-based agent discovery using SLM-enhanced indexing, achieving real-time semantic precision without 30+ second latencies.

Ax Qiaohong Zhang, Weihao Ye, Jialong Chen, Yi Luo, BoYuan Li, Bowen Deng, Zibin Zheng, Jianhao Lin, Wei-Shi Zheng, Chuan Chen 5/6/2026

DataClaw: A Process-Oriented Agent Benchmark for Exploratory Real-World Data Analysis

DataClaw benchmark with 2.06M real-world datasets for evaluating autonomous data analysis agents on exploratory tasks and reasoning processes.

Ax Abolfazl Mohammadi-Seif, Ricardo Baeza-Yates 5/6/2026

Improving Model Safety by Targeted Error Correction

Dual-classifier GBDT pipeline distinguishes routine errors from high-risk misclassifications in critical ML applications across medical and classification domains.

Ax Ruiqing Zhao, Fengzhi Li, Yuan Zuo, Rui Liu, Yansong Liu, Yunfei Ma, Fanyu Meng, Junlan Feng 5/6/2026

Strategy-Aware Optimization Modeling with Reasoning LLMs

SAGE framework teaches LLMs to choose effective modeling strategies for optimization problems through multi-strategy datasets and supervised fine-tuning.

Ax Sunghwan Kim, Junhee Cho, Beong-woo Kwak, Taeyoon Kwon, Liang Wang, Nan Yang, Xingxing Zhang, Furu Wei, Jinyoung Yeo 5/6/2026

On Training Large Language Models for Long-Horizon Tasks: An Empirical Study of Horizon Length

Empirical study examining how task horizon length affects training dynamics and capabilities of LLMs as interactive agents.

Ax Vincent Henkel, Felix Gehlhoff, David Kube, Asaad Almutareb, Luis Cruz, Bernd Hellingrath, Philip Koch, Christoph Legat, Florian Mohr, Michael Oberle, Felix Ocker, Thorsten Schoeler, Mario Thron, Nico Andre T\"opfer, Lucas Vogt, Yuchen Xia 5/6/2026

Foundation-Model-Based Agents in Industrial Automation: Purposes, Capabilities, and Open Challenges

Examination of foundation-model-based agent systems in industrial automation contexts, purposes, capabilities, and limitations.

Ax Alberto Pozanco, Daniel Borrajo, Manuela Veloso 5/6/2026

Counterfactual Reasoning in Automated Planning

Survey of counterfactual reasoning techniques in automated planning for handling deviations from fixed task specifications.

Ax Ruta Binkyte, Ivaxi Sheth, Zhijing Jin, Mohammad Havaei, Bernhard Sch\"olkopf, Mario Fritz 5/6/2026

Trustworthy AI Suffers from Invariance Conflicts and Causality is The Solution

Position paper arguing causality is necessary to resolve conflicts between trustworthy AI objectives like fairness and robustness.

Ax Xiayang Li, Kuo Gai, Shihua Zhang 5/6/2026

Deciphering Shortcut Learning from an Evolutionary Game Theory Perspective

Theoretical analysis of shortcut learning in deep neural networks using evolutionary game theory framework.

Ax Junjie Yu, Pengrui Lu, Weiye Si, Hongliang Lu, Jiabao Wu, Kaiwen Tao, Kun Wang, Lingyu Yang, Qiran Zhang, Xiuting Guo, Xuanyu Wang, Yang Wang, Yanjie Wang, Yi Yang, Zijian Hu, Ziyi Yang, Zonghan Zhou, Binghao Qiang, Borui Zhang, Chenning Li, Enchang Zhang, Feifan Chen, Feng Jian, Fengyin Sun, Hao Qiu, Hao Zheng, Haoran Zhu, Hongyu Liu, Jianbin Deng, Jiaxin Song, Jiaying Chi, Jiayou Shi, Jie Fang, Jinghui Zhong, Jingyu Zhou, Jinze Li, Junfeng Yi, Junyan Yu, Junzhi Xue, Ni Song, Pengyi Chen, Qi Chen, Quansheng Li, Rui Tao, Shenghai Gong, Shenhang Lu, Tianqi Shen, Tianxiang Zhu, Tiehan Kang, Tingyu Li, Wendi Wu, Xiao Shen, Xiao Zhou, Xiaotao Zhang, Xinrong Li, Xuankun Yang, Xun Zhang, Yan Li, Ye Lu, Yi Wang, Yibo Zhou, Yichi Zhang, Yihao Sun, Yijun Huang, Yixin Zhu, Yixuan Wu, Yuchen Sun, Yue Wu, Yuheng Sun, Yukun Li, Yutian Tu, Yuxuan Qin, Yuzhuo Wu, Zeyu Li, Zhengyu Lou, Zhenning Ran, Zizhu He, Pengfei Liu 5/6/2026

AcademiClaw: When Students Set Challenges for AI Agents

AcademiClaw: bilingual benchmark of 80 complex long-horizon academic tasks from real student workflows for evaluating AI agents.

Ax Majed El Helou, Benjamin Ryder, Chiara Troiani, Jean Diaconu, Herv\'e Muyal, Marcelo Yannuzzi 5/6/2026

Hybrid Inspection and Task-Based Access Control in Zero-Trust Agentic AI

Zero-trust security framework for LLM-driven agents using hybrid inspection and task-based access control for tool invocation.

Ax Gelei Xu, Ningzhi Tang, Xueyang Li, Toby Jia-Jun Li, Zhi Zheng, Wei Jin, Yiyu Shi 5/6/2026

An Empirical Study of Agent Skills for Healthcare: Practice, Gaps, and Governance

Empirical study of 557 healthcare agent skills, analyzing procedural adaptations and governance for healthcare AI agents.

Ax Guangrui Xie 5/6/2026

ORPilot: A Production-Oriented Agentic LLM-for-OR Tool for Optimization Modeling

ORPilot: open-source agentic LLM system that translates business problems into optimization models for production use.

Ax Joshua Strong, Pramit Saha, Emma Sun, Helen Higham, Alison Noble 5/6/2026

Coherent Hierarchical Multi-Label Learning to Defer for Medical Imaging

Learning to defer approach for hierarchical multi-label medical imaging decisions where models can defer to experts.

Ax Fan Ma, Yuntian Liu, Xiang Lan, Weipeng Zhou, Jun Ni, Mauro Giuffr\`e, Lingfei Qian, Xueqing Peng, Yujia Zhou, Ruey-Ling Weng, Huan He, Lu Li, Qingyu Chen, Andrew Loza, Laila Rasmy, Degui Zhi, Yuan Lu, Chenjie Zeng, Joshua C Denny, Lee Schwamm, Daniella Meeker, Lucila Ohno-Machado, Yong Chen, Hua Xu 5/6/2026

Foundation Models to Unlock Real-World Evidence from Nationwide Medical Claims

ReClaim: generative transformer foundation model for extracting insights from large-scale medical claims data.

Ax Maria Chang, Ronny Luss, Miao Lui, Keerthiram Murugesan, Karthikeyan Ramamurthy, Djallel Bouneffouf 5/6/2026

Mitigating Misalignment Contagion by Steering with Implicit Traits

Research on misalignment contagion between multiple LMs in multi-turn interactions and steering techniques using implicit traits.

Ax Christine P Lee, Xinyu Jessica Wang, Aws Albarghouthi, David Porfirio, Bilge Mutlu 5/6/2026

U-Define: Designing User Workflows for Hard and Soft Constraints in LLM-Based Planning

System for designing user workflows with hard and soft constraints in LLM-based planning, addressing reliability and control challenges.

Ax David Mumford 5/6/2026

AIs and Humans with Agency

Philosophical comparison of human agency development with potential LLM agency. Argues for joint action/planning architecture with humans.

Ax Jiujiu Chen, Yazheng Liu, Sihong Xie, Hui Xiong 5/6/2026

SCPRM: A Schema-aware Cumulative Process Reward Model for Knowledge Graph Question Answering

SCPRM: Schema-aware reward model for knowledge graph question answering. Addresses risk compensation in process rewards for LLM reasoning paths.

Ax Ziqi Liu, Kiljae Lee, Yuan Zhang, Weijing Tang 5/6/2026

First-Order Efficiency for Probabilistic Value Estimation via A Statistical Viewpoint

First-order efficiency methods for Shapley/Semivalues computation via statistical viewpoint. Model-agnostic feature attribution for explainability.

Ax Jingze Ge, Yun Liu, Xue Geng, Wanqi Dong, Wang Zhe Mark, Min Wu, Xulei Yang 5/6/2026

Compress Then Adapt? No, Do It Together via Task-aware Union of Subspaces

JACTUS: Joint adaptation and compression for large models across diverse tasks. Simultaneous parameter-efficient fine-tuning and low-rank compression.

Ax Vicente Pelechanoa, Antoni Mestre, Manoli Albert, Miriam Gil 5/6/2026

HAAS: A Policy-Aware Framework for Adaptive Task Allocation Between Humans and Artificial Intelligence Systems

HAAS framework for policy-aware adaptive task allocation between humans and AI. Addresses complementary roles and contextual task distribution.

Ax Mohamad Khajezade, Fatemeh H. Fard, Mohamed Sami Shehata 5/6/2026

Standing on the Shoulders of Giants: Stabilized Knowledge Distillation for Cross--Language Code Clone Detection

Knowledge distillation approach for cross-language code clone detection using compact open-source models. Improves semantic detection reliability.

Ax Abhinav Singh Parmar 5/6/2026

Separating Intelligence from Execution: A Workflow Engine for the Model Context Protocol

MCP Workflow Engine: Orchestration layer decoupling LLM reasoning from execution via Model Context Protocol. Reduces token consumption for repeated tasks.

Ax Shakya Jayakody, Youpeng Zhao, Chinmay Dhanraj Nehate, Jun Wang 5/6/2026

GhostServe: A Lightweight Checkpointing System in the Shadow for Fault-Tolerant LLM Serving

GhostServe: Fault-tolerant checkpointing system for million-token LLM agent serving. Addresses KV cache challenges in long-running inference tasks.

Ax Brice Valentin Kok-Shun, Johnny Chan, Gabrielle Peko, David Sundaram 5/6/2026

Agentopic: A Generative AI Agent Workflow for Explainable Topic Modeling

Agentopic: Multi-agent workflow for explainable topic modeling using LLMs. Collaborative agents handle identification, validation, and hierarchical grouping.

Ax Diana Maria Popa, Simona-Vasilica Oprea, Adela B\^ara 5/6/2026

Generative-AI and the transformation of workforce. A job postings-driven analysis

Analysis of 150,000+ job postings examining generative AI's impact on workforce skill requirements. Tests augmentation vs. substitution across sectors.

Ax Theodor Spiro 5/6/2026

The Oracle's Fingerprint: Correlated AI Forecasting Errors and the Limits of Bias Transmission

Study of correlated forecasting errors across GPT-4o, Claude, and Gemini on 568 binary predictions. Shows epistemic monoculture with mean error correlation r=0.77.

Ax Mengying Wang, Nicolaas Jedema, Rahul Pandey, RaviKiran Krishnan, Jens Lehmann, Yinghui Wu 5/6/2026

Graph Query Generation with Constraint-guided Large Language Agents

UniQGen: LLM agent framework for knowledge graph question answering across RDF/SPARQL and Cypher. Constraint-guided query generation for property graphs.

Ax Cutter Dawes, Aryan Sharma, Angelos Ioannis Lagos, Shivam Raval 5/6/2026

H-Probes: Extracting Hierarchical Structures From Latent Representations of Language Models

H-probes method to extract hierarchical structures from LLM latent representations. Analyzes geometric representations enabling hierarchical reasoning.

Ax Firat Ozdemir, Yun Cheng, Salman Mohebi, Fanny Lehmann, Simon Adamov, Zhenyi Zhang, Leonardo Trentini, Dana Grund, Oliver Fuhrer, Torsten Hoefler, Siddhartha Mishra, Sebastian Schemm, Benedikt Soja, Mathieu Salzmann 5/6/2026

Earth System Foundation Model (ESFM): A unified framework for heterogeneous data integration and forecasting

Open Earth System Foundation Model extending Aurora for weather/climate forecasting. Unified framework for heterogeneous geophysical data integration.

Ax Huanchen Cai, Sten Ternstr\"om 5/6/2026

Voice Mapping of Text-to-Speech Systems: A Metric-Based Approach for Voice Quality Assessment

Evaluation framework for text-to-speech synthesis quality using crest factor, spectrum balance, and cepstral metrics across six TTS models.

Ax Advait Tilak, Jiwon Choi, Nazifa Mouli, Wei Le 5/6/2026

BRITE: A Benchmark for Reliable and Interpretable T2V Evaluation on Implausible Scenarios

BRITE: benchmark for text-to-video evaluation on implausible scenarios including audio-visual alignment and QA-based interpretable assessment.

Ax Alizishaan Khatri, Chiquita Prabhu 5/6/2026

Latent Space Probing for Adult Content Detection in Video Generative Models

Latent space probing framework for detecting adult content in video generative models by analyzing internal representations during generation.

Ax Yida Xue, Ningyu Zhang, Tingwei Wu, Zhe Ma, Daxiong Ji, Zhao Wang, Guozhou Zheng, Huajun Chen 5/6/2026

OceanPile: A Large-Scale Multimodal Ocean Corpus for Foundation Models

OceanPile: multimodal ocean corpus addressing fragmented ocean data for training foundation models on climate and marine biodiversity tasks.

Ax Hao Wang, Limeng Qiao, Chi Zhang, Lin Ma, Guanglu Wan, Xiangyuan Lan, Xiaodan Liang 5/6/2026

X2SAM: Any Segmentation in Images and Videos

X2SAM integrates MLLMs with foundation segmentation models enabling pixel-level perception from conversational instructions across images and videos.

Ax Md. Enamul Hoq, Wataru Uegami, Saghir Alfasly, Ghazal Alabtah, Sahar Rahimi Malakshan, Armita Kazemi, Alex T. Schmitgen, Fred Prior, H. R. Tizhoosh 5/6/2026

Retrieval-Guided Generation for Safer Histopathology Image Captioning

Retrieval-guided generation approach for medical image captioning reducing hallucinations and factual inconsistency in histopathology image descriptions.

Ax Anirudh Iyengar Kaniyar Narayana Iyengar, Tampu Ravi Kumar, Manan Suri, Raviteja Bommireddy, Dinesh Manocha, Puneet Mathur, Vivek Gupta 5/6/2026

DIAGRAMS: A Review Framework for Reasoning-Level Attribution in Diagram QA

DIAGRAMS: review framework for creating reasoning-level attribution in diagram QA, providing structured evidence annotation across visual diagrams and infographics.

Ax Han Gong, Zhen Zhou, Yunyang Shi, Yan Tan, Jinbiao Huo, Qi Hong, Zhiyuan Liu 5/6/2026

TRIP-Evaluate: An Open Multimodal Benchmark for Evaluating Large Models in Transportation

TRIP-Evaluate: open multimodal benchmark for assessing LLMs and MLLMs on transportation tasks including regulation QA, traffic management, and autonomous driving reasoning.