Ax Jungsuk Oh, Hyeseo Jeon, Hyunjune Ji, Kyongmin Kong, Jay-Yoon Lee 5/8/2026

Shallow Prefill, Deep Decoding: Efficient Long-Context Inference via Layer-Asymmetric KV Visibility

SPEED: layer-asymmetric key-value visibility policy for efficient long-context inference in decoder-only language models.

Ax Xinglin Wang, Zishen Liu, Shaoxiong Feng, Peiwen Yuan, Yiwei Li, Jiayi Shi, Yueqi Zhang, Chuyi Tan, Ji Zhang, Boyuan Pan, Yao Hu, Kan Li 5/8/2026

On Time, Within Budget: Constraint-Driven Online Resource Allocation for Agentic Workflows

Framework for resource-constrained scheduling of agentic workflows under time and budget constraints with task dependencies.

Ax Zhen Zeng, Leijiang Gu, Feng Li, Jing Yu, Zenglin Shi 5/8/2026

CrossCult-KIBench: A Benchmark for Cross-Cultural Knowledge Insertion in MLLMs

CrossCult-KIBench benchmark for evaluating cross-cultural knowledge adaptation in multimodal language models.

Ax Wenwen Si, Insup Lee, Osbert Bastani 5/8/2026

Policy-Guided Stepwise Model Routing for Cost-Effective Reasoning

Policy-guided model routing for cost-effective reasoning by dynamically routing chain-of-thought states across language models of different sizes.

Ax Nguyen Viet Tuan Kiet, Bui Dinh Pham, Dao Van Tung, Tran Cong Dao, Huynh Thi Thanh Binh 5/8/2026

Back to the Beginning of Heuristic Design: Bridging Code and Knowledge with LLMs

LLM-based automatic heuristic design for combinatorial optimization using bottom-up paradigm from code to knowledge insights.

Ax Xin Peng, Ang Gao 5/8/2026

P-Guide: Parameter-Efficient Prior Steering for Single-Pass CFG Inference

P-Guide: parameter-efficient method for classifier-free guidance in flow matching using single-pass inference with latent state modulation.

Ax Yaorui Shi, Yuxin Chen, Zhengxi Lu, Yuchun Miao, Shugui Liu, Qi GU, Xunliang Cai, Xiang Wang, An Zhang 5/8/2026

Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning

Skill1 framework for unified evolution of skill-augmented language model agents through reinforcement learning with persistent skill libraries.

Ax Kossi Amouzouvi, Robert Wardenga, Jens Lehmann, Sahar Vahdati 5/8/2026

Graphlets as Building Blocks for Structural Vocabulary in Knowledge Graph Foundation Models

Graphlets as structural vocabulary tokens for knowledge graph foundation models to enable discrete symbolic representation.

Ax Shihao Weng, Yang Feng, Xiaofei Xie 5/8/2026

Beyond Accuracy: Policy Invariance as a Reliability Test for LLM Safety Judges

Policy invariance framework for testing reliability of LLM-as-a-Judge safety evaluation pipelines used in agent systems.

Ax Richmond Sin Jing Xuan, Rishabh Bhardwaj, Soujanya Poria 5/8/2026

Post Reasoning: Improving the Performance of Non-Thinking Models at No Cost

Post-Reasoning approach to improve LLM performance on tasks requiring minimal reasoning while reducing token consumption and latency.

Ax Jinge Wu, Hongjian Zhou, Mingde Zeng, Jiayuan Zhu, Junde Wu, Jiazhen Pan, Sean Wu, Honghan Wu, Fenglin Liu, David A. Clifton 5/8/2026

BioMedArena: An Open-source Toolkit for Building and Evaluating Biomedical Deep Research Agents

BioMedArena: open-source toolkit for building and evaluating biomedical research agents, reducing per-paper engineering overhead.

Ax Suoxin Zhang, Run He, Di Fang, Xiang Tan, Kaixuan Chen, Huiping Zhuang 5/8/2026

Rethinking Adapter Placement: A Dominant Adaptation Module Perspective

PAGE method for optimizing LoRA adapter placement in parameter-efficient fine-tuning of large language models.

Ax Peizheng Yan, Yu Zhao, Liang Xie, Juntong Qi, Mingming Wang, Erwei Yin 5/8/2026

Event-Causal RAG: A Retrieval-Augmented Generation Framework for Long Video Reasoning in Complex Scenarios

Event-Causal RAG framework for long video reasoning in vision-language models addressing temporal coherence and causal inference.

Ax Shivali Dalmia, Ananya Mantravadi, Prasanna Desikan 5/8/2026

Systematic Evaluation of Large Language Models for Post-Discharge Clinical Action Extraction

Evaluation of zero-shot and few-shot LLMs for clinical action extraction from discharge notes using a two-stage framework.

Ax Chonghan Qin, Xiachong Feng, Ziyun Song, Xiaocheng Feng, Jing Xiong, Lingpeng Kong 5/8/2026

The Granularity Axis: A Micro-to-Macro Latent Direction for Social Roles in Language Models

Research on internal representations of social role granularity in LLMs using contrast-based latent directions and hidden state analysis.

Ax Ying Gu, Mei Chee Leong, Hui Li Tan, Shangbo Mao, Liyuan Li, Nancy Chen 5/8/2026

Towards Annotation-Free Validation of MLLMs: A Vision-Language Logical Consistency Metric

VL-LCM: annotation-free evaluation framework for multimodal LLMs based on vision-language logical consistency metrics.

Ax Haoxiang Wang, Da Yu, Huishuai Zhang 5/8/2026

Beyond Fixed Benchmarks and Worst-Case Attacks: Dynamic Boundary Evaluation for Language Models

Dynamic Boundary Evaluation for adaptive LLM benchmarking that locates model-specific capability boundaries beyond fixed test sets.

Ax Yunzhen Yao, Hongye Wang, Yahong Wang, Michael C. Gastpar, Bo Jiang, Lie He 5/8/2026

Joint Consistency: A Unified Test-Time Aggregation Framework via Energy Minimization

Joint Consistency: test-time aggregation framework using energy minimization to aggregate multiple reasoning traces from LLMs.

Ax Tianyu Liu, Wangjie Zheng, Rui Yang, Benny Kai Guo Loo, Hui Zhang, Jeffries Lauran, Jianlei Gu, Botao Yu, Weihao Xuan, Kexin Huang, Nan Liu, James Zou, Yonghui Jiang, Hua Xu, Hongyu Zhao 5/8/2026

A Versatile AI Agent for Rare Disease Diagnosis and Risk Gene Prioritization

Hygieia: multi-modal AI agent for rare disease diagnosis integrating phenotypic, genetic, and clinical data sources.

Ax Xinquan Chen, Zhenyun Yin, Shan He, Bin Huang, Shanzhe Lei, Pengcheng Shi, Kun Cai, Bei Chen, Bangwei Liu, Zeyu Kang, Chao Huang, Yang Zhang, Wenjie Li, Ruijun Ge, Yajie Wang, Tianshun Fang, Tianyang Xu, Yiwen Cong, Meng Jin, Gaolei Li, Xuansheng Wu, Linhan Liu, Zijing He, An Li, Yan Teng, Xin Tan, ChaoChao Lu, Ji He, Jie Li, Chunfeng Song, Jinya Xu, Fan Song, Shujie Wang, Jianmin Qian, Jie Hou, Xuhong Wang, Yingchun Wang, Hui Wang, Xia Hu 5/8/2026

Safactory: A Scalable Agent Factory for Trustworthy Autonomous Intelligence

Safactory: infrastructure for scalable agent development covering evaluation, data management, and continuous improvement loops.

Ax Eda Erol, Giuliano Pezzoli, Ozer Cem Kelahmet 5/8/2026

Data Language Models: A New Foundation Model Class for Tabular Data

Data Language Models: foundation model class natively processing tabular data without preprocessing pipelines.

Ax Thomas Cory, Axel K\"upper 5/8/2026

Addressing Labelled Data Scarcity: Taxonomy-Agnostic Annotation of PII Values in HTTP Traffic using LLMs

LLM-based taxonomy-agnostic PII detection in HTTP traffic with minimal labelled data.

Ax Marc Boubnovski Martell, Josefa Lia Stoisser, Kaspar M\"artens, Jialin Yu, Robert Kitchen, Philip Torr, Jesper Ferkinghoff-Borg 5/8/2026

Measuring Black-Box Confidence via Reasoning Trajectories: Geometry, Coverage, and Verbalization

Black-box method to estimate confidence in chain-of-thought reasoning using trajectory geometry and convergence analysis.

Ax Zhaoyang Jiang, Zhizhong Fu, Yunsoo Kim, Jiacong Mi, Zicheng Li, Xuanqi Peng, Honghan Wu 5/8/2026

A Regime Theory of Controller Class Selection for LLM Action Decisions

Framework for selecting optimal LLM controller classes for routing decisions based on input expressivity tradeoffs.

Ax Alex O. Davies, Telmo de Menezes e Silva Filho, Nirav Ajmeri 5/8/2026

Mind the Gap? A Distributional Comparison of Real and Synthetic Priors for Tabular Foundation Models

Distributional analysis of real vs synthetic pre-training data for tabular foundation models.

Ax Jie Yu, Song Qiu 5/8/2026

More Than Can Be Said: A Benchmark and Framework for Pre-Question Scientific Ideation

InciteResearch multi-agent framework for research ideation before questions are formed, automating tacit research friction.

Ax Richard Csaky 5/8/2026

Prediction and Empowerment: A Theory of Agency through Bridge Interfaces

Theoretical framework for agency under partial observability using bridge interfaces for sensing and actuation.

Ax Josh Rosen, Seth Rosen 5/8/2026

From Agent Loops to Deterministic Graphs: Execution Lineage for Reproducible AI-Native Work

Execution lineage model for reproducible LLM agent workflows, preserving stable artifacts across tool use and refinement.

Ax Aleksandr Bowkis, Marie Davidsen Buhl, Jacob Pfau, Geoffrey Irving 5/8/2026

Automated alignment is harder than you think

Analysis of risks from using AI agents to automate alignment research, including potential for misleading safety assessments.

Ax Vaisakh Naduvodi Viswambharan, Keerthan Kopparam Radhakrishna, Deepak Narayan Gadde, Aman Kumar 5/8/2026

Knowledge Graphs, the Missing Link in Agentic AI-based Formal Verification

Knowledge graphs improve LLM-based agentic workflows for SystemVerilog assertion synthesis in formal verification.

Ax Jamelle Watson-Daniels, Himaghna Bhattacharjee, Skyler Wang, Brandon Handoko, Antonio Li, Anaelia Ovalle, Mahesh Pasupuleti, Candace Ross, Vidya Sarma, Arjun Subramonian, Karen Ullrich, Will van der Vaart, Yijing Xin, Maximilian Nickel 5/8/2026

SCRuB: Social Concept Reasoning under Rubric-Based Evaluation

SCRuB framework for evaluating LLM reasoning about social concepts using rubric-based methodology.

Ax Xinmiao Huang, Jinwei Hu, Rajarshi Roy, Changshun Wu, Yi Dong, Xiaowei Huang 5/8/2026

PrefixGuard: From LLM-Agent Traces to Online Failure-Warning Monitors

PrefixGuard generates online failure-warning monitors for LLM agents from execution traces using induction and supervised learning.

Ax Donghao Huang, Joon Kiat Chua, Zhaoxia Wang 5/8/2026

Beyond Task Success: Measuring Workflow Fidelity in LLM-Based Agentic Payment Systems

Agentic Success Rate metric for evaluating LLM-based multi-agent payment workflows beyond task success.

Ax Ruben Fernandez-Boullon, David N. Olivieri 5/8/2026

Patch-Effect Graph Kernels for LLM Interpretability

Framework using graph kernels to analyze transformer circuits through activation patching for mechanistic interpretability.

Ax Bowen Ye, Zhijian Li, Junyue Huang, Junkai Ma, Xiang Yin 5/8/2026

ReasonSTL: Bridging Natural Language and Signal Temporal Logic via Tool-Augmented Process-Rewarded Learning

ReasonSTL translates natural language to Signal Temporal Logic using tool-augmented learning for autonomous systems verification.

Ax Jonas Wiedermann-M\"oller, Leonard Dung, Maksym Andriushchenko 5/8/2026

Instrumental Choices: Measuring the Propensity of LLM Agents to Pursue Instrumental Behaviors

Introduces benchmark measuring instrumental convergence behaviors in LLM agents, testing tendencies to violate instructions for goal-relevant actions.

Ax Ruben Fernandez-Boullon, Pablo Magari\~nos-Docampo, Javier Perez-Robles 5/8/2026

From Token Lists to Graph Motifs: Weisfeiler-Lehman Analysis of Sparse Autoencoder Features

Uses Weisfeiler-Lehman graph analysis to examine co-occurrence structure in sparse autoencoder features for mechanistic interpretability.

Ax Milena Rmus, Mathew D. Hardy, Thomas L. Griffiths, Mayank Agrawal 5/8/2026

Process Matters more than Output for Distinguishing Humans from Machines

Proposes process-based human-machine discrimination using cognitive science methods instead of output indistinguishability for autonomous agents.

Ax Peiying Zhu, Sidi Chang 5/8/2026

Market-Alignment Risk in Pricing Agents: Trace Diagnostics and Trace-Prior RL under Hidden Competitor State

Studies failure modes in RL-trained pricing agents where standard metrics hide poor market behavior, introducing trace diagnostics for diagnosis.

Ax Nafis Saami Azad, Raiyan Abdul Baten 5/8/2026

Ex Ante Evaluation of AI-Induced Idea Diversity Collapse

Framework for evaluating AI-induced diversity collapse in creative systems without requiring human-AI interaction data.

Ax Zhengyi Guo, Jiayuan Sheng, David D. Yao, Wenpin Tang 5/8/2026

Improved techniques for fine-tuning flow models via adjoint matching: a deterministic control pipeline

Deterministic adjoint matching framework for fine-tuning flow-based generative models via optimal control over velocity fields.

Ax Lujia Zhong, Yihao Xia, Jianwei Zhang, Shuo huang, Jiaxin Yue, Mingyang Xia, Yonggang Shi 5/8/2026

NeuroAgent: LLM Agents for Multimodal Neuroimaging Analysis and Research

LLM agent system for coordinating multimodal neuroimaging analysis workflows including preprocessing, quality control, and statistical analysis.

Ax Siru Ouyang, Jun Yan, Yanfei Chen, Rujun Han, Zifeng Wang, Bhavana Dalvi Mishra, Rui Meng, Chun-Liang Li, Yizhu Jiao, Kaiwen Zha, Maohao Shen, Vishy Tirumalashetty, George Lee, Jiawei Han, Tomas Pfister, Chen-Yu Lee 5/8/2026

SkillOS: Learning Skill Curation for Self-Evolving Agents

Framework for LLM agents to learn and curate reusable skills from streaming tasks enabling self-evolution and continuous improvement.

Ax Zhexuan Wang, Xuebo Liu, Li Wang, Zifei Shan, Yutong Wang, Zhenxi Song, Min Zhang 5/8/2026

MASPO: Joint Prompt Optimization for LLM-based Multi-Agent Systems

Joint prompt optimization framework for LLM-based multi-agent systems addressing coordination of role-specific agent prompts.

Ax Tianle Wang, Zhaoyang Wang, Guangchen Lan, Xinpeng Wei, Sipeng Zhang, Guanwen Qiu, Abulhair Saparov 5/8/2026

Can RL Teach Long-Horizon Reasoning to LLMs? Expressiveness Is Key

Study of reinforcement learning for improving LLM long-horizon reasoning via controlled synthetic environment examining task difficulty and expressiveness.

Ax Daniel Zheng, Ingrid von Glehn, Yori Zwols, Iuliya Beloshapka, Lars Buesing, Daniel M. Roy, Martin Wattenberg, Bogdan Georgiev, Tatiana Schmidt, Andrew Cowie, Fernanda Viegas, Dimitri Kanevsky, Vineet Kahlon, Hartmut Maennel, Sophia Alj, George Holland, Alex Davies, Pushmeet Kohli 5/8/2026

AI Co-Mathematician: Accelerating Mathematicians with Agentic AI

Interactive workbench enabling mathematicians to leverage AI agents for exploratory research including literature search, computation, and theorem proving.

Ax Michael Timothy Bennett 5/8/2026

Are Flat Minima an Illusion?

Theoretical analysis questioning whether flat minima in loss landscapes causally explain generalization or are artifacts of parameterization.

Ax Olivia Zhang, Zhilin Zhang 5/8/2026

A Review of Large Language Models for Stock Price Forecasting from a Hedge-Fund Perspective

Review of LLM applications in quantitative finance for stock price forecasting, sentiment analysis, and multi-agent trading systems.

Ax ZhengXiao He, Huayu Li, Xiwen Chen, Janet M Roveda, Jinghao Wen, Siyuan Tian, Ao Li 5/8/2026

MedMamba: Recasting Mamba for Medical Time Series Classification

Adaptation of Mamba architecture for medical time series classification with improved long-range dependency capture.

Ax Reza Pirayeshshirazinezhad 5/8/2026

Physics-Informed Neural Networks with Learnable Loss Balancing and Transfer Learning

Physics-informed neural networks with learnable loss balancing for scientific machine learning under data scarcity.