3/19/2026
Chain of Mindset: Reasoning with Adaptive Cognitive Modes
Chain of Mindset method enabling LLMs to adaptively switch between cognitive modes for improved reasoning across problem-solving stages.
3/19/2026
A Hierarchical Error-Corrective Graph Framework for Autonomous Agents with LLM-Based Action Generation
HECG framework for autonomous agents using LLM-based action generation with multi-dimensional strategy alignment and error correction mechanisms.
3/19/2026
JobMatchAI An Intelligent Job Matching Platform Using Knowledge Graphs, Semantic Search and Explainable AI
JobMatchAI production system for job candidate matching using Transformer embeddings, skill knowledge graphs, and explainable AI reranking.
3/19/2026
The Comprehension-Gated Agent Economy: A Robustness-First Architecture for AI Economic Agency
Comprehension-Gated Agent Economy architecture gates AI agent economic agency on verified comprehension functions rather than capability benchmarks.
3/19/2026
I Know What I Don't Know: Latent Posterior Factor Models for Multi-Evidence Probabilistic Reasoning
Latent Posterior Factors framework for aggregating noisy heterogeneous evidence in decision-making with explicit uncertainty quantification and interpretability.
3/19/2026
Theoretical Foundations of Latent Posterior Factors: Formal Guarantees for Multi-Evidence Reasoning
Theoretical characterization of Latent Posterior Factors framework for aggregating multiple evidence sources in probabilistic reasoning with formal guarantees.
3/19/2026
Interpretable Context Methodology: Folder Structure as Agentic Architecture
Model Workspace Protocol for sequential agentic workflows using folder structure as architecture, reducing engineering overhead versus multi-agent frameworks.
3/19/2026
TRUST-SQL: Tool-Integrated Multi-Turn Reinforcement Learning for Text-to-SQL over Unknown Schemas
TRUST-SQL uses multi-turn reinforcement learning and tool integration for text-to-SQL parsing on unknown database schemas in enterprise settings.
3/19/2026
Theoretical Foundations of {\delta}-margin Majority Voting
Theoretical analysis of delta-margin majority voting for consensus-based prediction quality control in high-stakes ML applications.
3/19/2026
Reinforcement learning with learned gadgets to tackle hard quantum problems on real hardware
Uses reinforcement learning with learned gadgets to design quantum circuits addressing noise and connectivity constraints in real quantum hardware.
3/19/2026
ACT-JEPA: Novel Joint-Embedding Predictive Architecture for Efficient Policy Representation Learning
ACT-JEPA combines joint-embedding predictive architecture with self-supervised learning for efficient policy representation in imitation learning.
3/19/2026
Physics-Informed Evolution: An Evolutionary Framework for Solving Quantum Control Problems Involving the Schr\"odinger Equation
Physics-Informed Evolution framework embeds physical laws into evolutionary algorithm fitness functions for quantum control problems.
3/19/2026
Oracular Programming: A Modular Foundation for Building LLM-Enabled Software
Oracular Programming framework for building modular, composable LLM-enabled software with enforceable contracts and reliable composition primitives.
3/19/2026
Integrating Arithmetic Learning Improves Mathematical Reasoning in Smaller Models
Method to improve mathematical reasoning in smaller LLMs by integrating arithmetic learning alongside knowledge distillation and data augmentation.
3/19/2026
Frequency Autoregressive Image Generation with Continuous Tokens
Proposes frequency progressive autoregressive approach for image generation using continuous tokens instead of raster-scan prediction.
3/19/2026
Learning Over Dirty Data with Minimal Repairs
Research on minimal data repair showing imputing all missing values unnecessary for accurate ML models; introduces minimal and almost-minimal repair concepts.
3/19/2026
SocialJax: An Evaluation Suite for Multi-agent Reinforcement Learning in Sequential Social Dilemmas
SocialJax is an evaluation suite for multi-agent reinforcement learning in sequential social dilemmas, measuring generalization across social scenarios.
3/19/2026
Impact of Data Duplication on Deep Neural Network-Based Image Classifiers: Robust vs. Standard Models
Study of data deduplication effects on deep neural network image classifiers. Examines impact on robustness against adversarial attacks.
3/19/2026
Comparing Uncertainty Measurement and Mitigation Methods for Large Language Models: A Systematic Review
Systematic review of uncertainty quantification and mitigation methods for LLMs to address hallucination and calibration challenges.
3/19/2026
Edge-Cloud Collaborative Computing on Distributed Intelligence and Model Optimization: A Survey
Survey of edge-cloud collaborative computing for AI and LLM deployment. Covers distributed intelligence and model optimization techniques.
3/19/2026
RAGXplain: From Explainable Evaluation to Actionable Guidance of RAG Pipelines
RAGXplain framework for evaluating and debugging RAG systems. Provides actionable insights into retrieval, context, and generation performance beyond aggregate metrics.
3/19/2026
Advancing Software Quality: A Standards-Focused Review of LLM-Based Assurance Techniques
Survey of LLM-based software quality assurance techniques covering requirement analysis, code review, test generation, and standards compliance.
3/19/2026
BiomedSQL: Text-to-SQL for Scientific Reasoning on Biomedical Knowledge Bases
Benchmark for text-to-SQL systems evaluating scientific reasoning over biomedical knowledge bases requiring implicit domain understanding.
3/19/2026
Probing Association Biases in LLM Moderation Over-Sensitivity
Analysis revealing association biases beyond token level cause LLM content moderation over-sensitivity on decontextualized statements.
3/19/2026
MOBODY: Model Based Off-Dynamics Offline Reinforcement Learning
Offline RL method handling dynamics mismatch between source and target datasets by leveraging high-shift regions for better exploration.
3/19/2026
SatSOM: Saturation Self-Organizing Maps for Continual Learning
Self-organizing maps extension addressing catastrophic forgetting in continual learning through saturation mechanisms.
3/19/2026
Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions
Benchmark evaluating memory capabilities in LLM agents including memorization, updating, and retrieval of long-term information across multi-turn interactions.
3/19/2026
ToolRegistry: A Protocol-Agnostic Tool Management Library for Function-Calling LLMs
Protocol-agnostic tool management library for function-calling LLMs that reduces fragmentation and development overhead in LLM applications.
3/19/2026
Learning from Oblivion: Predicting Knowledge Overflowed Weights via Retrodiction of Forgetting
Method for predicting better pre-trained weights via retrodiction of forgetting to encapsulate more knowledge beyond training datasets.
3/19/2026
Fast weight programming and linear transformers: from machine learning to neurobiology
Analysis of fast weight programmers and 2D-state RNNs as linear transformers with connections to neurobiology and language modeling advances.
3/19/2026
Role-Augmented Intent-Driven Generative Search Engine Optimization
Framework for optimizing content for generative search engines powered by LLMs and RAG by modeling user intent and role-based search patterns.
3/19/2026
Human Psychometric Questionnaires Mischaracterize LLM Psychology: Evidence from Generation Behavior
Study showing psychometric questionnaires designed for humans mischaracterize LLM psychology compared to behavior in real user interactions.
3/19/2026
EdiVal-Agent: An Object-Centric Framework for Automated, Fine-Grained Evaluation of Multi-Turn Editing
Object-centric evaluation framework for automated fine-grained assessment of multi-turn instruction-based image editing using VLMs.
3/19/2026
Tree Search for LLM Agent Reinforcement Learning
Tree-based group relative policy optimization for LLM agent reinforcement learning addressing sparse supervision in long-horizon multi-turn tasks.
3/19/2026
IA2: Alignment with ICL Activations Improves Supervised Fine-Tuning
Method aligning supervised fine-tuning with in-context learning activations to improve LLM generalization and calibration in data-scarce settings.
3/19/2026
In-Context Compositional Q-Learning for Offline Reinforcement Learning
Offline RL framework using linear Transformers for compositional Q-function estimation across diverse subtasks via in-context learning.
3/19/2026
Stable Forgetting: Bounded Parameter-Efficient Unlearning in Foundation Models
Parameter-efficient machine unlearning method for foundation models addressing weight unbounding in privacy removal.
3/19/2026
HarmMetric Eval: Benchmarking Metrics and Judges for LLM Harmfulness Assessment
Benchmark evaluating metrics and judges for assessing harmful content generation in LLMs.
3/19/2026
Slow-Fast Policy Optimization: Reposition-Before-Update for LLM Reasoning
Slow-Fast Policy Optimization framework improving LLM reasoning via RL with better gradient stability and exploration.
3/19/2026
Detecting Data Contamination from Reinforcement Learning Post-training for Large Language Models
Methods for detecting data contamination in LLM evaluation during reinforcement learning post-training phases.
3/19/2026
Scalable Energy-Based Models via Adversarial Training: Unifying Discrimination and Generation
Scalable energy-based models via adversarial training unifying classification and generative modeling using EBM framework.
3/19/2026
CBF-RL: Safety Filtering Reinforcement Learning in Training with Control Barrier Functions
CBF-RL integrates control barrier functions into reinforcement learning training for enforcing safety constraints during policy training.
3/19/2026
Frame Semantic Patterns for Identifying Underreporting of Notifiable Events in Healthcare: The Case of Gender-Based Violence
Frame semantic patterns methodology for identifying underreported gender-based violence in e-medical records using NLP.
3/19/2026
Generative Hints
Generative hints training methodology enforcing functional invariances in vision models beyond empirical training data.
3/19/2026
Reduced Density Matrices Through Machine Learning
Neural network approach to accelerate computation of n-particle reduced density matrices for strongly-correlated quantum states.
3/19/2026
A robust methodology for long-term sustainability evaluation of Machine Learning models
Methodology for sustainable ML model evaluation addressing gaps in Green AI auditing practices and standardization.
3/19/2026
Genomic Next-Token Predictors are In-Context Learners
Research showing genomic sequence models exhibit in-context learning similar to LLMs, demonstrating ICL emerges across sequence domains.
3/19/2026
Uni-DAD: Unified Distillation and Adaptation of Diffusion Models for Few-step Few-shot Image Generation
Uni-DAD: Unified method for distilling and adapting diffusion models for few-step image generation in new domains.
3/19/2026
SO-Bench: A Structural Output Evaluation of Multimodal LLMs
Benchmark for evaluating multimodal LLMs on schema-grounded visual information extraction and reasoning tasks in agentic settings.
3/19/2026
Adaptive Accountability in Networked MAS: Tracing and Mitigating Emergent Norms at Scale
Framework for runtime monitoring of multi-agent systems using cryptographic provenance and drift detection to mitigate emergent norms at scale.