Isolater - Feed

Ax Yuxuan Xie, Ang Li 2/17/2026

Bounding Probabilities of Causation with Partial Causal Diagrams

Proposes methods to bound probabilities of causation with partial causal diagrams for individual-level explanation and decision-making.

Ax Dennis Gross 2/17/2026

Formally Verifying and Explaining Sepsis Treatment Policies with COOL-MC

COOL-MC framework formally verifies and explains sepsis treatment RL policies through model checking with explainability for healthcare decision-making.

Ax Jing Tang, Kun Wang, Haolang Lu, Hongjin Chen, KaiTao Chen, Zhongxiang Sun, Qiankun Li, Lingjuan Lyu, Guoshun Nan, Zhigang Zeng 2/17/2026

Diagnosing Knowledge Conflict in Multimodal Long-Chain Reasoning

Examines knowledge conflicts in multimodal LLMs during long chain-of-thought reasoning, using internal representation probing to identify linear separability of conflict types.

Ax Haolang Lu, Hongrui Peng, WeiYe Fu, Guoshun Nan, Xinye Cao, Xingrui Li, Hongcan Guo, Kun Wang 2/17/2026

Disentangling Deception and Hallucination Failures in LLMs

Mechanistic analysis of LLM failures distinguishing knowledge existence from behavior expression in entity-based factual queries.

Ax Gabriel Roccabruna, Olha Khomyn, Giuseppe Riccardi 2/17/2026

MATEO: A Multimodal Benchmark for Temporal Reasoning and Planning in LVLMs

MATEO benchmark evaluates multimodal LLMs on temporal reasoning and planning for complex goal achievement with ordered steps and precondition dependencies.

Ax Erkan Karabulut, Daniel Daza, Paul Groth, Martijn C. Schut, Victoria Degeler 2/17/2026

Tabular Foundation Models Can Learn Association Rules

Tabular foundation models applied to association rule mining for knowledge discovery in tabular data, addressing scalability and low-data regime performance limitations.

Ax Lu\'is Silva, Diogo Gon\c{c}alves, Catarina Farinha, Clara Matos, Lu\'is Ungaro 2/17/2026

Arbor: A Framework for Reliable Navigation of Critical Conversation Flows

Arbor framework decomposes decision tree navigation for LLMs to maintain structured workflows in high-stakes domains like healthcare, addressing instruction-following degradation in long prompts.

Ax Mustafa F. Abdelwahed, Felipe Meneguzzi Kin Max Piamolini Gusmao, Joan Espasa 2/17/2026

Removing Planner Bias in Goal Recognition Through Multi-Plan Dataset Generation

Multi-plan dataset generation approach to remove planner bias in goal recognition for autonomous agents.

Ax Lunjun Zhang, Ryan Chen, Bradly C. Stadie 2/17/2026

Evolutionary System Prompt Learning can Facilitate Reinforcement Learning for LLMs

Evolutionary system prompt learning method for joint improvement of LLM contexts and weights via reinforcement learning.

Ax Zikai Xiao, Jianhong Tu, Chuhang Zou, Yuxin Zuo, Zhi Li, Peng Wang, Bowen Yu, Fei Huang, Junyang Lin, Zuozhu Liu 2/17/2026

WebWorld: A Large-Scale World Model for Web Agent Training

Large-scale open-web simulator trained on 1M+ interactions for web agent training supporting reasoning and multi-format data.

Ax Kenneth Payne 2/17/2026

AI Arms and Influence: Frontier Models Exhibit Sophisticated Reasoning in Simulated Nuclear Crises

Evaluation of frontier models' strategic reasoning, theory of mind, and metacognitive abilities in simulated nuclear crises.

Ax Ivan Diliso, Roberto Barile, Claudia d'Amato, Nicola Fanizzi 2/17/2026

Return of the Schema: Building Complete Datasets for Machine Learning and Reasoning on Knowledge Graphs

Framework for building complete knowledge graph datasets with schema-level information for algorithm evaluation.

Ax Yixin Zhang, Ziyi Wang, Yiming Rong, Haoxi Wang, Jinling Jiang, Shuang Xu, Haoran Wu, Shiyu Zhou, Bo Xu 2/17/2026

World Models for Policy Refinement in StarCraft II

LLM-based StarCraft II agents enhanced with learnable action-conditioned world models for policy refinement.

Ax Chenyang Ma, Clyde Fare, Matthew Wilson, Dave Braines 2/17/2026

EmbeWebAgent: Embedding Web Agents into Any Customized UI

Framework embedding web agents into customized UIs with lightweight frontend hooks for improved robustness and action expressiveness.

Ax Matthew Kowal, Goncalo Paulo, Louis Jaburi, Tom Tseng, Lev E McKinney, Stefan Heimersheim, Aaron David Tucker, Adam Gleave, Kellin Pelrine 2/17/2026

Concept Influence: Leveraging Interpretability to Improve Performance and Efficiency in Training Data Attribution

Training data attribution method using concept-based interpretability to identify which training examples drive LLM behaviors.

Ax Luise Ge, Brendan Juba, Kris Nilsson, Alison Shao 2/17/2026

Lifted Relational Probabilistic Inference via Implicit Learning

Joint learning and reasoning approach for probabilistic inference in first-order relational domains without constructing explicit models.

Ax Gregor Bachmann, Yichen Jiang, Seyed Mohsen Moosavi Dezfooli, Moin Nabi 2/17/2026

The Potential of CoT for Reasoning: A Closer Look at Trace Dynamics

In-depth analysis of chain-of-thought prompting trace dynamics to understand driving forces behind LLM reasoning performance.

Ax Claudiu Cristian Musat, Jackson Tolins, Diego Antognini, Jingling Li, Martin Klissarov, Tom Duerig 2/17/2026

Position: Introspective Experience from Conversational Environments as a Path to Better Learning

Position paper on linguistic self-reflection and conversational environments as foundation for robust AI reasoning inspired by developmental psychology.

Ax Gaoyang Zhang, Shanghong Zou, Yafang Wang, He Zhang, Ruohua Xu, Feng Zhao 2/17/2026

ReusStdFlow: A Standardized Reusability Framework for Dynamic Workflow Construction in Agentic AI

Framework for dynamic workflow construction in agentic AI using standardized, modular workflow segments and dual knowledge architecture.

Ax Gen Zhou, Sugitha Janarthanan, Lianghong Chen, Pingzhao Hu 2/17/2026

MAC-AMP: A Closed-Loop Multi-Agent Collaboration System for Multi-Objective Antimicrobial Peptide Design

Multi-agent collaboration system for antimicrobial peptide design balancing activity, toxicity, and novelty objectives.

Ax Alisa Vinogradova, Vlad Vinogradov, Luba Greenwood, Ilya Yasny, Dmitry Kobyzev, Shoman Kasbekar, Kong Nguyen, Dmitrii Radkevich, Roman Doronin, Andrey Doronichev 2/17/2026

Hunt Globally: Deep Research AI Agents for Drug Asset Scouting in Investing, Business Development, and Search & Evaluation

AI agents for drug discovery that scout non-English biotech sources globally, addressing >85% of patents originating outside the U.S.

Ax William Xion, Wolfgang Nejdl 2/17/2026

Training-Induced Bias Toward LLM-Generated Content in Dense Retrieval

Study revealing dense retrievers exhibit bias toward LLM-generated content, investigating relationship between perplexity and source bias in retrieval systems.

Ax Andrii Grekhov, Volodymyr Kharchenko, Vasyl Kondratiuk 2/17/2026

Simulation-Based Study of AI-Assisted Channel Adaptation in UAV-Enabled Cellular Networks

Simulation study of AI-assisted channel adaptation in UAV cellular networks with ground base stations and aerial repeaters.

Ax Andrii Grekhov, Volodymyr Kharchenko, Vasyl Kondratiuk 2/17/2026

Traffic Simulation in Ad Hoc Network of Flying UAVs with Generative AI Adaptation

Traffic simulation model for UAV ad-hoc networks with generative AI-based channel adaptation across packet sizes and transmission parameters.

Ax Vignesh Sriram, Yuqiao Meng, Luoxi Tang, Zhaohan Xi 2/17/2026

Adversarial Network Imagination: Causal LLMs and Digital Twins for Proactive Telecom Mitigation

Closed-loop framework combining causal LLMs, knowledge graphs, and digital twins for proactive telecom failure mitigation and simulation.

Ax Abdikarim Mohamed Ibrahim, Rosdiadee Nordin 2/17/2026

A Safety-Constrained Reinforcement Learning Framework for Reliable Wireless Autonomy

Safety-constrained reinforcement learning framework preventing unsafe emergent behaviors in wireless systems, UAVs, and IoT applications.

Ax Jie Zheng, Ruichen Zhang, Dusit Niyato, Haijun Zhang, Jiacheng Wang, Hongyang Du, Jiawen Kang, Zehui Xiong 2/17/2026

Large Language Model (LLM)-enabled Reinforcement Learning for Wireless Network Optimization

Framework integrating LLMs with reinforcement learning for wireless network optimization, addressing high-dimensional state spaces and computational demands.

Ax Miao Ye, Yanye Chen, Yong Wang, Cheng Zhu, Qiuxiang Jiang, Gai Huang, Feng Ding 2/17/2026

An Overlay Multicast Routing Method Based on Network Situational Aware-ness and Hierarchical Multi-Agent Reinforcement Learning

Hierarchical multi-agent reinforcement learning for overlay multicast routing with network situational awareness decoupling multi-objective problems.

Ax Chatavut Viriyasuthee 2/17/2026

Computability of Agentic Systems

Quest Graph framework analyzing computational capabilities of agentic systems with finite context, establishing equivalence to Turing machines and pushdown automata.

Ax Eranga Bandara, Ross Gore, Sachin Shetty, Ravi Mukkamala, Tharaka Hewa, Abdul Rahman, Xueping Liang, Safdar H. Bouk, Amin Hass, Peter Foytik, Ng Wee Keong, Kasun De Zoysa 2/17/2026

An Agentic AI Control Plane for 6G Network Slice Orchestration, Monitoring, and Trading

Agentic AI control plane architecture for 6G network slice orchestration using intent-driven and economically programmable approaches.

Ax Zirong Chen, Meiyi Ma 2/17/2026

Real-World Design and Deployment of an Embedded GenAI-powered 9-1-1 Calltaking Training System: Experiences and Lessons Learned

Real-world deployment of generative AI-powered 9-1-1 training system addressing staffing crisis and reducing training time requirements.

Ax Peng He, Zhaohui Li, Zeyuan Wang, Jinjun Xiong, Tingting Li 2/17/2026