2/20/2026
Dynamic System Instructions and Tool Exposure for Efficient Agentic LLMs
Instruction-Tool Retrieval (ITR) RAG variant dynamically retrieves minimal system prompts and necessary tool subsets per step for efficient agentic LLMs.
2/20/2026
IntentCUA: Learning Intent-level Representations for Skill Abstraction and Multi-Agent Planning in Computer-Use Agents
Multi-agent computer-use framework with intent-aligned plan memory to stabilize long-horizon execution and reduce error accumulation.
2/20/2026
RFEval: Benchmarking Reasoning Faithfulness under Counterfactual Reasoning Intervention in Large Reasoning Models
Framework evaluating reasoning faithfulness in large reasoning models through counterfactual intervention on stance consistency and causal influence.
2/20/2026
Retaining Suboptimal Actions to Follow Shifting Optima in Multi-Agent Reinforcement Learning
Multi-agent RL method retaining multiple high-value actions via sub-value functions to adapt to shifting value functions.
2/20/2026
Predictive Batch Scheduling: Accelerating Language Model Training Through Loss-Aware Sample Prioritization
Predictive Batch Scheduling uses lightweight online predictor to prioritize high-loss samples, accelerating LLM training convergence.
2/20/2026
How AI Coding Agents Communicate: A Study of Pull Request Description Characteristics and Human Review Responses
Empirical study analyzing pull request characteristics from five AI coding agents and human reviewer responses using AIDev dataset.
2/20/2026
Agentic Wireless Communication for 6G: Intent-Aware and Continuously Evolving Physical-Layer Intelligence
6G wireless systems architecture using intent-driven autonomous agents for multi-dimensional objectives and evolving requirements.
2/20/2026
Toward Trustworthy Evaluation of Sustainability Rating Methodologies: A Human-AI Collaborative Framework for Benchmark Dataset Construction
Human-AI collaborative framework for constructing benchmark datasets to standardize ESG/sustainability rating methodologies.
2/20/2026
Owen-based Semantics and Hierarchy-Aware Explanation (O-Shap)
Owen-value based method extending SHAP for hierarchical feature attribution in vision tasks with spatial/semantic dependencies.
2/20/2026
Instructor-Aligned Knowledge Graphs for Personalized Learning
Knowledge graphs capturing educational concept dependencies and prerequisites for personalized learning at scale.
2/20/2026
Epistemology of Generative AI: The Geometry of Knowing
Philosophical examination of generative AI's epistemic character and implications for knowledge production in science, education, and institutions.
2/20/2026
Efficient Parallel Algorithm for Decomposing Hard CircuitSAT Instances
Parallel algorithm for decomposing hard CircuitSAT instances using specialized constraints and hardness estimations.
2/20/2026
JEPA-DNA: Grounding Genomic Foundation Models through Joint-Embedding Predictive Architectures
JEPA-DNA: pre-training framework for genomic foundation models using joint-embedding predictive architecture to capture functional genomic context.
2/20/2026
Texo: Formula Recognition within 20M Parameters
Texo: minimalist 20M parameter formula recognition model achieving state-of-the-art performance with 80% size reduction through distillation and transfer learning.
2/20/2026
Continual learning and refinement of causal models through dynamic predicate invention
Framework for constructing symbolic causal world models online by integrating continuous model learning with meta-interpretive learning in agent decision loops.
2/20/2026
From Labor to Collaboration: A Methodological Experiment Using AI Agents to Augment Research Perspectives in Taiwan's Humanities and Social Sciences
Methodological experiment using AI agents in collaborative research workflows for humanities and social sciences, analyzing Taiwan Claude.ai usage data.
2/20/2026
Decoding the Human Factor: High Fidelity Behavioral Prediction for Strategic Foresight
Framework for predicting consistent individual-specific human behavior in high-stakes environments by combining LLMs with psychological trait modeling.
2/20/2026
Mechanistic Interpretability of Cognitive Complexity in LLMs via Linear Probing using Bloom's Taxonomy
Mechanistic interpretability study using linear probing and Bloom's Taxonomy to analyze cognitive complexity in LLM internal neural representations.
2/20/2026
All Leaks Count, Some Count More: Interpretable Temporal Contamination Detection in LLM Backtesting
Framework for detecting and quantifying temporal data contamination in LLM backtesting to validate whether models leak post-cutoff training knowledge.
2/20/2026
Web Verbs: Typed Abstractions for Reliable Task Composition on the Agentic Web
Web Verbs framework providing typed abstractions for reliable task composition on agentic web, enabling LLM-based web agents beyond low-level primitives.
2/20/2026
ArXiv-to-Model: A Practical Study of Scientific LM Training
Case study training 1.36B-parameter scientific language model from raw arXiv LaTeX sources, documenting end-to-end process for domain-specialized LM development.
2/20/2026
MedClarify: An information-seeking AI agent for medical diagnosis with case-specific follow-up questions
MedClarify: LLM-based AI agent for medical diagnosis that iteratively asks follow-up questions to resolve diagnostic uncertainty through differential reasoning.
2/20/2026
Dataless Weight Disentanglement in Task Arithmetic via Kronecker-Factored Approximate Curvature
Method for disentangling task vectors in foundation models using Kronecker-factored approximate curvature without external task data.
2/20/2026
Visual Model Checking: Graph-Based Inference of Visual Routines for Image Retrieval
Graph-based visual inference approach for complex image retrieval queries involving relationships, compositions, and precise constraints.
2/20/2026
A Contrastive Variational AutoEncoder for NSCLC Survival Prediction with Missing Modalities
Contrastive Variational AutoEncoder for predicting NSCLC patient survival using multi-modal biomedical data with missing modalities.
2/20/2026
A Privacy by Design Framework for Large Language Model-Based Applications for Children
Privacy-by-Design framework for LLM-based applications targeting children, addressing implementation gaps in privacy regulation compliance.
2/20/2026
WarpRec: Unifying Academic Rigor and Industrial Scale for Responsible, Reproducible, and Efficient Recommendation
WarpRec framework bridging gap between research and production recommender systems with backend-agnostic architecture, 50+ algorithms, and 40 metrics.
2/20/2026
Pareto Optimal Benchmarking of AI Models on ARM Cortex Processors for Sustainable Embedded Systems
Benchmarking framework for optimizing AI models on ARM Cortex embedded processors, measuring energy efficiency, accuracy, and resource utilization.
2/20/2026
Enhancing Large Language Models (LLMs) for Telecom using Dynamic Knowledge Graphs and Explainable Retrieval-Augmented Generation
arXiv paper on applying LLMs to telecom domain using dynamic knowledge graphs and retrieval-augmented generation to reduce hallucinations and improve accuracy.
2/20/2026
Evaluating Chain-of-Thought Reasoning through Reusability and Verifiability
Evaluation framework for chain-of-thought reasoning quality using reusability and verifiability metrics in multi-agent IR pipelines.
2/20/2026
KLong: Training LLM Agent for Extremely Long-horizon Tasks
KLong open-source LLM agent framework for extremely long-horizon tasks using trajectory-splitting SFT and progressive RL training.
2/20/2026
ODESteer: A Unified ODE-Based Steering Framework for LLM Alignment
ODESteer unified ODE-based framework for LLM alignment via activation steering with multi-step guidance.
2/20/2026
A Hybrid Federated Learning Based Ensemble Approach for Lung Disease Diagnosis Leveraging Fusion of SWIN Transformer and CNN
Federated learning ensemble combining SWIN Transformer and CNN for lung disease diagnosis from medical imaging.
2/20/2026
AI Gamestore: Scalable, Open-Ended Evaluation of Machine General Intelligence with Human Games
AI Gamestore platform for evaluating machine general intelligence using open-ended human games and dynamic benchmarks.
2/20/2026
MolHIT: Advancing Molecular-Graph Generation with Hierarchical Discrete Diffusion Models
MolHIT hierarchical discrete diffusion model for molecular graph generation improving chemical validity for drug discovery.
2/20/2026
AutoNumerics: An Autonomous, PDE-Agnostic Multi-Agent Pipeline for Scientific Computing
AutoNumerics multi-agent framework autonomously designs, implements, and verifies numerical PDE solvers using AI.
2/20/2026
CLEF HIPE-2026: Evaluating Accurate and Efficient Person-Place Relation Extraction from Multilingual Historical Texts
CLEF HIPE-2026 evaluation lab for person-place relation extraction from historical multilingual texts.
2/20/2026
GPU-Accelerated Algorithms for Graph Vector Search: Taxonomy, Empirical Study, and Research Directions
Taxonomy and empirical study of GPU-accelerated graph-based approximate nearest neighbor search algorithms for large-scale applications.
2/20/2026
APEX-SQL: Talking to the data via Agentic Exploration for Text-to-SQL
APEX-SQL agentic framework for text-to-SQL that dynamically explores database schemas to resolve semantic ambiguity in complex enterprise environments.
2/20/2026
Is Mamba Reliable for Medical Imaging?
Robustness evaluation of Mamba state-space models on medical imaging benchmarks under adversarial perturbations and corruptions.
2/20/2026
Intent Laundering: AI Safety Datasets Are Not What They Seem
Systematic evaluation showing AI safety datasets overrely on triggering cues and fail to reflect real-world adversarial attacks.
2/20/2026
The Compute ICE-AGE: Invariant Compute Envelope under Addressable Graph Evolution
Production C++ implementation of deterministic semantic state substrate using graph engine architecture for inference systems.
2/20/2026
Quantifying LLM Attention-Head Stability: Implications for Circuit Universality
Study quantifying stability of transformer attention heads across model instances to assess whether mechanistic interpretability circuits are universal.
2/20/2026
Can Adversarial Code Comments Fool AI Security Reviewers -- Large-Scale Empirical Study of Comment-Based Attacks and Defenses Against LLM Code Analysis
Empirical study of comment-based adversarial attacks against LLM code vulnerability detection across Python, JavaScript, and Java.
2/20/2026
DeepVision-103K: A Visually Diverse, Broad-Coverage, and Verifiable Mathematical Dataset for Multimodal Reasoning
DeepVision-103K dataset with 103K diverse mathematical problems for training multimodal LLMs using reinforcement learning with verifiable rewards.
2/20/2026
PETS: A Principled Framework Towards Optimal Trajectory Allocation for Efficient Test-Time Self-Consistency
PETS framework for efficient test-time scaling via principled trajectory allocation to improve LLM self-consistency under budget constraints.
2/20/2026
Low-Dimensional and Transversely Curved Optimization Dynamics in Grokking
Geometric analysis of transformer optimization dynamics showing grokking emerges in low-dimensional subspaces during modular arithmetic training.
2/20/2026
LiveClin: A Live Clinical Benchmark without Leakage
LiveClin benchmark for evaluating medical LLMs using contemporary clinical case reports updated biannually to prevent data contamination.
2/20/2026
PREFER: An Ontology for the PREcision FERmentation Community
Ontology standard for precision fermentation data in biofoundries to improve interoperability across platforms.
2/20/2026
Attending to Routers Aids Indoor Wireless Localization
Attention mechanism for Wi-Fi indoor localization that weights router information appropriately during signal aggregation.