Ax Md. Nazmul Islam Ananto, Shamit Fatin, Mohammed Eunus Ali, Md Rizwan Parvez 5/8/2026

CompassLLM: A Multi-Agent Approach toward Geo-Spatial Reasoning for Popular Path Query

CompassLLM multi-agent approach using LLMs for geo-spatial reasoning on popular path queries from trajectory data without requiring model retraining.

Ax Yuxiang Zhang, Jiangming Shu, Ye Ma, Xueyuan Lin, Shangxi Wu, Jitao Sang 5/8/2026

Memory as Action: Autonomous Context Curation for Long-Horizon Agentic Tasks

Memory-as-Action (MemAct) framework treating working memory management as learnable policy actions for long-horizon AI agent tasks to mitigate attention dilution.

Ax Chiyan Loo 5/8/2026

Self-Consistency Is Losing Its Edge: Diminishing Returns and Rising Costs in Modern LLMs

Analysis showing self-consistency decoding technique yields diminishing returns on modern LLMs like Gemini 2.5, often degrading performance on already-solved problems.

Ax Peiran Xu, Sudong Wang, Yao Zhu, Jianing Li, Gege Qi, Yunjian Zhang 5/8/2026

SpatialBench: Benchmarking Multimodal Large Language Models for Spatial Cognition

SpatialBench benchmark for evaluating multimodal LLMs on spatial cognition tasks, capturing hierarchical structure of spatial abilities.

Ax Bufang Yang, Lilin Xu, Liekang Zeng, Yunqi Guo, Siyang Jiang, Wenrui Lu, Kaiwei Liu, Yixuan Li, Xiaofan Jiang, Guoliang Xing, Zhenyu Yan 5/8/2026

ProAgent: Harnessing On-Demand Sensory Contexts for Proactive LLM Agent Systems in the Wild

ProAgent framework for proactive LLM agents that continuously perceive and assist users in real-world settings using sensory contexts and contextual awareness.

Ax Zijun Gao, Zhikun Xu, Xiao Ye, Ben Zhou 5/8/2026

CORE: Concept-Oriented Reinforcement for Bridging the Definition-Application Gap in Mathematical Reasoning

CORE reinforcement learning framework providing fine-grained conceptual signals to teach LLMs genuine mathematical concept application rather than pattern reuse.

Ax Yong Xiao, Xubo Li, Haoran Zhou, Yingyu Li, Yayu Gao, Guangming Shi, Ping Zhang, Marwan Krunz 5/8/2026

SANet: A Semantic-aware Agentic AI Networking Framework for Cross-layer Optimization in 6G

SANet framework using specialized AI agents for autonomous decision-making, dynamic adaptation, and cross-layer optimization in 6G networks.

Ax Abhijnan Nath, Alireza Bagheri Garakani, Tianchen Zhou, Fan Yang, Yan Gao, Nikhil Krishnaswamy 5/8/2026

Owen-Shapley Policy Optimization: A Principled RL Algorithm for Generative Search LLMs

Owen-Shapley policy optimization algorithm for RL-trained LLMs with token-level credit assignment, addressing reward sparsity in recommendation tasks.

Ax Kaixiang Wang, Yidan Lin, Jiong Lou, Zhaojiacheng Zhou, Bunyod Suvonov, Jie Li 5/8/2026

E-mem: Multi-agent based Episodic Context Reconstruction for LLM Agent Memory

E-mem multi-agent episodic context reconstruction framework preserving logical integrity and sequential dependencies for LLM agent memory systems.

Ax Dionizije Fa, Marko Culjak, Bruno Pandza, Mateo Cupic 5/8/2026

BioAgent Bench: An AI Agent Evaluation Suite for Bioinformatics

BioAgent Bench evaluation suite with curated end-to-end bioinformatics tasks for measuring AI agent performance and robustness with automated assessment.

Ax Jiahui Zhou, Dan Li, Boxin Li, Xiao Zhang, Erli Meng, Lin Li, Zhuomin Chen, Jian Lou, See-Kiong Ng 5/8/2026

Time Series Reasoning via Process-Verifiable Thinking Data Synthesis and Scheduling for Tailored LLM Reasoning

Process-verifiable thinking data synthesis framework enabling LLMs to perform long Chain-of-Thought reasoning for diverse time series tasks.

Ax Martin Odersky, Yaoyu Zhao, Yichen Xu, Oliver Bra\v{c}evac, Cao Nguyen Pham 5/8/2026

Tracking Capabilities for Safer Agents

Safety harness using capability-safe Scala 3 language to restrict agent tool calls and prevent information leakage, unintended side effects, and prompt injection attacks.

Ax Chengkai Wang, Baisong Liu 5/8/2026

Beyond Factual Correctness: Mitigating Preference-Inconsistent Explanations in Explainable Recommendation

PURE framework addressing preference-inconsistent explanations in LLM-based recommenders through preference-aware reasoning.

Ax Matthew Holmes, Thiago Lacerda, Reva Schwartz 5/8/2026

Making AI Evaluation Deployment Relevant Through Context Specification

Context specification methodology for making AI evaluations operational and relevant to organizational deployment success and decision-making.

Ax Zhengwei Xie, Zhisheng Chen, Ziyan Weng, Jinhan Li, Chenglong Li, Zikai Xiao, Jingwei Song, Jinhao Jing, Vireo Zhang, Kun Wang 5/8/2026

MineEvolve: Self-Evolution with Accumulated Knowledge for Long-Horizon Embodied Minecraft Agents

MineEvolve framework enabling embodied Minecraft agents to accumulate knowledge through interaction and self-evolution for long-horizon task completion.

Ax Baoding He, Zenan Li, Wei Sun, Yuan Yao, Taolue Chen, Xiaoxing Ma, Zhendong Su 5/8/2026

Neuro-Symbolic Proof Generation for Scaling Systems Software Verification

Neuro-symbolic framework integrating LLMs into interactive theorem proving to automate proof script generation for systems software verification.

Ax Zeda Xu, Nikolas Martelaro, Christopher McComb 5/8/2026

Supervising Ralph Wiggum: Exploring a Metacognitive Co-Regulation Agentic AI Loop for Engineering Design

Metacognitive co-regulation framework for LLM design agents to overcome fixation bias and explore alternative solutions in engineering design tasks.

Ax Bowen Ye, Rang Li, Qibin Yang, Yuanxin Liu, Linli Yao, Hanglong Lv, Zhihui Xie, Chenxin An, Lei Li, Lingpeng Kong, Qi Liu, Zhifang Sui, Tong Yang 5/8/2026

Claw-Eval: Towards Trustworthy Evaluation of Autonomous Agents

Claw-Eval benchmark suite with 300 human-verified tasks across 9 categories for trustworthy evaluation of autonomous LLM agents in real-world software environments.

Ax Xi-Wei Pan, Shi-Wen An, Jin-Guo Liu 5/8/2026

Problem Reductions at Scale: Agentic Integration of Computationally Hard Problems

Framework for routing NP-hard optimization problems to diverse solvers via polynomial-time reductions, integrated with agentic orchestration.

Ax Wentao Zhang, Zhe Zhao, Haibin Wen, Yingcheng Wu, Cankun Guo, Ming Yin, Bo An, Mengdi Wang 5/8/2026

Autogenesis: A Self-Evolving Agent Protocol

Autogenesis Protocol for self-evolving LLM-based agent systems, addressing lifecycle management, version tracking, and safe updates to enable modular agent composition.

Ax Jazmia Henry 5/8/2026

Beyond Static Snapshots: A Grounded Evaluation Framework for Language Models at the Agentic Frontier

Critique of current LLM evaluation frameworks identifying systematic failures (distributional, temporal, scope, process) inadequate for deployed agentic systems and RLHF reward hacking.

Ax Kai Xi, Stephen Gould, Sylvie Thi\'ebaux 5/8/2026

Learning Lifted Action Models from Unsupervised Visual Traces

Deep learning framework for learning lifted action models from visual state sequences without action observation, applicable to AI planning in real-world domains.

Ax Zhixin Han, Yanzhi Zhang, Chuyang Wei, Maohang Gao, Xiawei Yue, Kefei Chen, Yu Zhuang, Haoxiang Guan, Jiyan He, Jian Li, Yitong Duan, Yu Shi, Mengting Hu, Shuxin Zheng 5/8/2026

FutureWorld: A Live Reinforcement Learning Environment for Predictive Agents with Real-World Outcome Rewards

FutureWorld live RL environment for training predictive agents on real-world event forecasting with actual outcome rewards.

Ax Ke Xu 5/8/2026

WaferSAGE: Large Language Model-Powered Wafer Defect Analysis via Synthetic Data Generation and Rubric-Guided Reinforcement Learning

WaferSAGE uses vision-language models with synthetic data generation for semiconductor wafer defect analysis.

Ax Haotian Zhao, Songlin Zhou, Yuxin Zhang, Stephen S. -T. Yau, Wenyu Zhang, Lun Tian, Tianshu Zhu, Yifeng Huang, Yucheng Zeng, Jingnan Gu, Daxiang Dong, Jianmin Wu 5/8/2026

AEM: Adaptive Entropy Modulation for Multi-Turn Agentic Reinforcement Learning

Adaptive Entropy Modulation improves credit assignment in multi-turn LLM agent reinforcement learning tasks.

Ax Theodore Papamarkou, Pierre Alquier, Matthias Bauer, Wray Buntine, Andrew Davison, Gintare Karolina Dziugaite, Maurizio Filippone, Andrew Y. K. Foong, Vincent Fortuin, Dimitris Fouskakis, Jes Frellsen, Eyke H\"ullermeier, Theofanis Karaletsos, Mohammad Emtiyaz Khan, Nikita Kotelevskii, Salem Lahlou, Yingzhen Li, Fang Liu, Clare Lyle, Thomas M\"ollenhoff, Konstantina Palla, Maxim Panov, Yusuf Sale, Kajetan Schweighofer, Artem Shelmanov, Siddharth Swaroop, Martin Trapp, Willem Waegeman, Andrew Gordon Wilson, Alexey Zaytsev 5/8/2026

Position: agentic AI orchestration should be Bayes-consistent

Position paper arguing agentic AI control layers should be Bayes-consistent for tool/expert selection under uncertainty.

Ax Jay Bhan, Nicole Nobili, Patrick Langer 5/8/2026

New Bounds for Zarankiewicz Numbers via Reinforced LLM Evolutionary Search

LLM evolutionary search determines Zarankiewicz numbers in discrete mathematics using reinforced optimization.

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 5/8/2026

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

GR-Ben benchmark evaluates process reward models across diverse reasoning tasks beyond mathematics.

Ax Lei Gao, Zhuoming Li, Mengxi Jia, Jiakang Yuan, Hongbo Sun, Hao Sun, Xuelong Li 5/8/2026

Segment-Aligned Policy Optimization for Multi-Modal Reasoning

Segment-Aligned Policy Optimization improves credit assignment in multi-modal reasoning RL for language models.

Ax Luong N. Nguyen 5/8/2026

Zero-Shot Confidence Estimation for Small LLMs: When Supervised Baselines Aren't Worth Training

Zero-shot confidence estimation for small LLMs enabling cost-effective local-to-cloud routing without supervised training.

Ax Hongkun Yu 5/8/2026

Evaluating Prompting and Execution-Based Methods for Deterministic Computation in LLMs

Systematic evaluation of prompting and execution methods for deterministic computation in large language models.

Ax Xutao Mao, Jinman Zhao, Gerald Penn, Cong Wang 5/8/2026

What Happens Inside Agent Memory? Circuit Analysis from Emergence to Diagnosis

Circuit analysis of LLM agent memory systems revealing internal mechanisms of information management across sessions.

Ax Tianyang Han, Hengyu Shi, Junjie Hu, Xu Yang, Zhiling Wang, Junhao Su 5/8/2026

Correct Is Not Enough: Training Reasoning Planners with Executor-Grounded Rewards

Executor-grounded reward training improves faithful reasoning in LLMs beyond final-answer correctness.

Ax Dutao Zhang, Tian Liao 5/8/2026

An Agent-Oriented Pluggable Experience-RAG Skill for Experience-Driven Retrieval Strategy Orchestration

Experience-RAG Skill enables AI agents to orchestrate different retrieval strategies based on task context.

Ax Osvaldo Luamba Quinjica, David Ifeoluwa Adelani 5/8/2026

ANGOFA: Leveraging OFA Embedding Initialization and Synthetic Data for Angolan Language Model

Four pre-trained language models for low-resource Angolan languages using transfer learning and synthetic data.

Ax Kichang Lee, Yujin Shin, Jonghyuk Yun, Songkuk Kim, Jun Han, JeongGil Ko 5/8/2026

DeTrigger: A Gradient-Centric Approach to Backdoor Attack Mitigation in Federated Learning

DeTrigger proposes gradient-centric method to mitigate backdoor attacks in federated learning systems.

Ax Jiaan Han, Junxiao Chen, Yanzhe Fu 5/8/2026

CatNet: Controlling the False Discovery Rate in LSTM with SHAP Feature Importance and Gaussian Mirrors

CatNet algorithm controls false discovery rate in LSTM feature selection using SHAP importance and Gaussian mirrors with kernel-based independence measures.

Ax Jingwen Tan, Gopi Krishnan Rajbahadur, Zi Li, Xiangfu Song, Jianshan Lin, Dan Li, Zibin Zheng, Ahmed E. Hassan 5/8/2026

LicenseGPT: A Fine-tuned Foundation Model for Publicly Available Dataset License Compliance

LicenseGPT fine-tuned foundation model for dataset license compliance interpretation, addressing legal risks in commercial AI product development.

Ax Pedro Orvalho, Marta Kwiatkowska 5/8/2026

Are Large Language Models Robust in Understanding Code Against Semantics-Preserving Mutations?

Evaluates LLM robustness on code understanding against semantics-preserving mutations, assessing reasoning quality beyond accuracy on programming tasks.

Ax Majid Mohammadi, Siu Lun Chau, Krikamol Muandet 5/8/2026

Amortized Linear-time Exact Shapley Value for Product-Kernel Methods

Amortized linear-time exact Shapley value computation for product-kernel methods, enabling scalable explainability in kernel-based models.

Ax Qirun Zeng, Eric He, Richard Hoffmann, Xuchuang Wang, Jinhang Zuo 5/8/2026

Practical Adversarial Attacks on Stochastic Bandits via Fake Data Injection

Practical adversarial attacks on stochastic bandits via fake data injection with bounded perturbations, more realistic than prior per-round manipulation assumptions.

Ax Tim Walter, Hannah Markgraf, Jonathan K\"ulz, Matthias Althoff 5/8/2026

Leveraging Analytic Gradients in Provably Safe Reinforcement Learning

Provably safe RL using analytic gradients for autonomous robots, integrating safety safeguards during training to reduce sim-to-real deployment gaps.

Ax Huiyao Chen, Yi Yang, Yinghui Li, Meishan Zhang, Baotian Hu, Min Zhang 5/8/2026

Beyond Chunking: Discourse-Aware Hierarchical Retrieval for Long Document Question Answering

Discourse-aware hierarchical retrieval for long document QA using rhetorical structure theory, improving over flat chunking approaches for LLM comprehension.

Ax Zhiwei Li, Guodong Long, Chunxu Zhang, Honglei Zhang, Jing Jiang, Chengqi Zhang 5/8/2026

A Survey of Personalized Federated Foundation Models for Privacy-Preserving Recommendation

Survey of federated foundation models for privacy-preserving recommendation systems, addressing integration of FMs in decentralized collaborative settings.

Ax Sayed Mohammad Vakilzadeh Hatefi, Maximilian Dreyer, Reduan Achtibat, Patrick Kahardipraja, Thomas Wiegand, Wojciech Samek, Alexander Binder, Sebastian Lapuschkin 5/8/2026

Attribution-Guided Pruning for Insight and Control: Circuit Discovery and Targeted Correction in Small-scale LLMs

Attribution-guided pruning discovers circuits in small LLMs for mechanistic interpretability, enabling diagnosis and targeted correction of undesirable behaviors.

Ax Sung-Hyun Kim, Geum-Hwan Hwang, In-Chang Baek, Seo-Young Lee, Kyung-Joong Kim 5/8/2026

Multi-Objective Instruction-Aware Representation Learning in Procedural Content Generation RL

Multi-objective instruction-aware RL for procedural content generation leveraging natural language control, addressing limitations in handling complex textual instructions.

Ax Zhuo Liu, Tao Chen 5/8/2026

Toward Practical Equilibrium Propagation: Brain-inspired Recurrent Neural Network with Feedback Regulation and Residual Connections

Improves Equilibrium Propagation learning framework with feedback regulation and residual connections for brain-inspired computing, addressing instability and computational costs.

Ax Ivan Rodkin, Daniil Orel, Konstantin Smirnov, Arman Bolatov, Bilal Elbouardi, Besher Hassan, Yuri Kuratov, Aydar Bulatov, Preslav Nakov, Timothy Baldwin, Artem Shelmanov, Mikhail Burtsev 5/8/2026

Beyond Memorization: Extending Reasoning Depth with Recurrence, Memory and Test-Time Compute Scaling

Study of multi-step reasoning in LLMs using cellular automata framework, examining how recurrence, memory, and test-time compute scaling improve reasoning depth beyond memorization.

Ax Peter Racioppo 5/8/2026

Robust Filter Attention: Self-Attention as Precision-Weighted State Estimation

RFA reformulates self-attention as robust state estimation using linear SDEs, matching computational complexity of standard attention while improving theoretical foundations.

Ax Hyunwoo Kim, Hyo Kyung Lee 5/8/2026

Frictional Q-Learning

Frictional Q-Learning reduces extrapolation errors in off-policy RL by treating replay buffer as low-dimensional manifold, using friction analogy for action selection.