4/2/2026
A ROS 2 Wrapper for Florence-2: Multi-Mode Local Vision-Language Inference for Robotic Systems
ROS 2 middleware integration for Florence-2 vision-language model in robotics systems, enabling local inference for robotic perception.
4/2/2026
ORBIT: Scalable and Verifiable Data Generation for Search Agents on a Tight Budget
ORBIT dataset with 20K reasoning-intensive queries for training search agents combining LMs and web search, using verifiable generation methodology.
4/2/2026
CliffSearch: Structured Agentic Co-Evolution over Theory and Code for Scientific Algorithm Discovery
Agentic evolutionary framework for scientific algorithm discovery combining LLM-guided search with structured theory and code co-evolution.
4/2/2026
$\texttt{YC-Bench}$: Benchmarking AI Agents for Long-Term Planning and Consistent Execution
Benchmark for evaluating LLM agents on long-term planning over one-year startup simulation with hundreds of turns, testing strategic coherence under uncertainty.
4/2/2026
The Recipe Matters More Than the Kitchen:Mathematical Foundations of the AI Weather Prediction Pipeline
Mathematical framework analyzing AI weather prediction pipelines, emphasizing training methodology and data diversity over architecture choices.
4/2/2026
LAtent Phase Inference from Short time sequences using SHallow REcurrent Decoders (LAPIS-SHRED)
Spatio-temporal dynamics reconstruction from sparse observations using shallow recurrent decoders. Domain-specific to complex systems, not AI/ML focused.
4/2/2026
Code Comprehension then Auditing for Unsupervised LLM Evaluation
Method for unsupervised code correctness evaluation using LLMs through code comprehension before auditing, eliminating need for reference implementations.
4/2/2026
Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG
Survey of agentic RAG systems combining LLMs with real-time retrieval to address static training data limitations and improve contextual accuracy.
4/2/2026
Teaching AI to Handle Exceptions: Supervised Fine-Tuning with Human-Aligned Judgment
Research on fine-tuning LLMs as agentic systems to handle exceptions and improve decision-making in complex real-world contexts.
4/2/2026
Mitigating Content Effects on Reasoning in Language Models through Fine-Grained Activation Steering
Study on mitigating reasoning biases in LLMs through activation steering at inference time to improve logical validity discrimination.
4/2/2026
LocationReasoner: Evaluating LLMs on Real-World Site Selection Reasoning
Research evaluating LLM reasoning capabilities on real-world site selection tasks, testing if models like o1 and DeepSeek-R1 generalize beyond math/code domains.
4/2/2026
HiMA-Ecom: Enabling Joint Training of Hierarchical Multi-Agent E-commerce Assistants
Benchmark and framework for training hierarchical multi-agent LLM systems with master-coordinator and specialized sub-agents for e-commerce applications.
4/2/2026
Auto-Formulating Dynamic Programming Problems with Large Language Models
Approach using LLMs to automate formulation of dynamic programming models for operations research, addressing stochastic transitions and data scarcity.
4/2/2026
Retrieval-of-Thought: Efficient Reasoning via Reusing Thoughts
Retrieval-of-Thought method that reuses reasoning steps across problems via thought graphs to improve inference efficiency and reduce latency/cost.
4/2/2026
Dive into the Agent Matrix: A Realistic Evaluation of Self-Replication Risk in LLM Agents
Research on self-replication risks in LLM agents driven by objective misalignment, moving from theoretical concern to practical reality assessment.
4/2/2026
Genesis: Evolving Attack Strategies for LLM Web Agent Red-Teaming
Genesis: framework evolving attack strategies for red-teaming LLM web agents using behavioral pattern learning.
4/2/2026
EHRStruct: A Comprehensive Benchmark Framework for Evaluating Large Language Models on Structured Electronic Health Record Tasks
EHRStruct: benchmark framework evaluating LLM performance on structured electronic health record tasks with standardized metrics.
4/2/2026
Alphacast: An Interaction-Driven Agentic Reasoning Framework for Cognition-Inspired Time Series Forecasting
Alphacast: agentic reasoning framework for time series forecasting using iterative multi-step reasoning with domain knowledge integration.
4/2/2026
DR-LoRA: Dynamic Rank LoRA for Fine-Tuning Mixture-of-Experts Models
DR-LoRA: parameter-efficient fine-tuning method for MoE LLMs using dynamic rank allocation based on expert specialization.
4/2/2026
Distilling the Thought, Watermarking the Answer: A Principle Semantic Guided Watermark for Large Reasoning Models
ReasonMa: semantic-guided watermarking technique for reasoning LLMs that preserves logical coherence while protecting models.
4/2/2026
Finite-State Controllers for (Hidden-Model) POMDPs using Deep Reinforcement Learning
arXiv paper on Lexpop framework using deep RL to train finite-state controllers for solving POMDPs robustly.
4/2/2026
Meta-Learning and Meta-Reinforcement Learning -- Tracing the Path towards DeepMind's Adaptive Agent
Survey on meta-learning and meta-reinforcement learning enabling rapid adaptation to novel tasks with minimal data.
4/2/2026
Epistemic Filtering and Collective Hallucination: A Jury Theorem for Confidence-Calibrated Agents
arXiv paper on heterogeneous agent collective accuracy using calibration and selective abstention in voting systems.
4/2/2026
When Agents Persuade: Rhetoric Generation and Mitigation in LLMs
Analysis of LLM-based agents' capability to generate propaganda and rhetorical manipulation, with detection of techniques like loaded language and appeals to fear.
4/2/2026
Semi-Autonomous Formalization of the Vlasov-Maxwell-Landau Equilibrium
AI-assisted formalization of Vlasov-Maxwell-Landau system equilibrium in Lean 4 using DeepThink reasoning and Claude Code agent for automated theorem proving.
4/2/2026
When Only the Final Text Survives: Implicit Execution Tracing for Multi-Agent Attribution
Attribution method for multi-agent systems that identifies responsible agents without execution logs by analyzing final text only, addressing privacy-constrained scenarios.
4/2/2026
SCoOP: Semantic Consistent Opinion Pooling for Uncertainty Quantification in Multiple Vision-Language Model Systems
Training-free uncertainty quantification framework for combining multiple vision-language models through semantic-consistent opinion pooling to reduce hallucinations.
4/2/2026
PReD: An LLM-based Foundation Multimodal Model for Electromagnetic Perception, Recognition, and Decision
Foundation multimodal model for electromagnetic domain covering perception, recognition, and decision-making using LLM capabilities adapted for domain-specific applications.
4/2/2026
View-oriented Conversation Compiler for Agent Trace Analysis
Compiler for analyzing and visualizing structured agent traces including nested tool calls, reasoning blocks, and sub-agent invocations for better agentic system understanding.
4/2/2026
Cognitive Friction: A Decision-Theoretic Framework for Bounded Deliberation in Tool-Using Agents
Decision-theoretic framework (Triadic Cognitive Architecture) for tool-using agents that bounds information-acquisition costs and tool usage to prevent systematic failures.
4/2/2026
Ego-Foresight: Self-supervised Learning of Agent-Aware Representations for Improved RL
Self-supervised learning method for RL agents that models agent and environment separately to improve sample efficiency without requiring supervisory signals.
4/2/2026
A Divide-and-Conquer Strategy for Hard-Label Extraction of Deep Neural Networks via Side-Channel Attacks
Demonstrates hard-label extraction of deep neural networks via side-channel attacks using divide-and-conquer strategy for DNN intellectual property theft.
4/2/2026
Cross-Camera Distracted Driver Classification through Feature Disentanglement and Contrastive Learning
Addresses accuracy loss in distracted driver classification across camera conditions using feature disentanglement and contrastive learning for robustness.
4/2/2026
Enhancing Team Diversity with Generative AI: A Novel Project Management Framework
Project management framework using generative AI agents to address team composition gaps by matching sociologically identified personality patterns and roles.
4/2/2026
How Blind and Low-Vision Individuals Prefer Large Vision-Language Model-Generated Scene Descriptions
User study with blind and low-vision participants evaluating preferences for LVLM-generated scene descriptions, examining effectiveness and user preferences.
4/2/2026
Science-T2I: Addressing Scientific Illusions in Image Synthesis
ScienceT2I dataset and benchmark evaluating scientific correctness in image synthesis, addressing gap between visual fidelity and physical realism across 16 scientific domains.
4/2/2026
Neural Conditional Transport Maps
Neural framework for learning conditional optimal transport maps with hypernetworks that generate adaptive transport parameters for categorical and continuous variables.
4/2/2026
But what is your honest answer? Aiding LLM-judges with honest alternatives using steering vectors
JUSSA framework uses steering vectors to improve LLM-as-judge reliability by detecting and mitigating subtle dishonesty like sycophancy through contrastive alternatives.
4/2/2026
Situationally-Aware Dynamics Learning
Framework for online learning of hidden state representations in autonomous robots to handle unobserved factors in complex, unstructured environments.
4/2/2026
Graceful Forgetting in Generative Language Models
Proposes graceful forgetting methods to mitigate negative transfer by selectively forgetting detrimental pre-training knowledge during fine-tuning of language models.
4/2/2026
How Does Alignment Enhance LLMs' Multilingual Capabilities? A Language Neurons Perspective
Analyzes language-specific neurons to understand how multilingual alignment transfers capabilities from high-resource to low-resource languages in LLMs.
4/2/2026
Two-stage Vision Transformers and Hard Masking offer Robust Object Representations
Two-stage vision transformer with hard masking approach for robust object representations that balance context dependence with distribution shift robustness.
4/2/2026
"Is This Really a Human Peer Supporter?": Misalignments Between Peer Supporters and Experts in LLM-Supported Interactions
Investigates misalignments between LLM-supported peer supporters and mental health experts, examining quality and safety concerns in AI-driven psychosocial support.
4/2/2026
MemeMind: A Large-Scale Multimodal Dataset with Chain-of-Thought Reasoning for Harmful Meme Detection
MemeMind dataset with chain-of-thought reasoning for detecting harmful memes, addressing implicit harmful content in multimodal text-image combinations.
4/2/2026
Binned semiparametric Bayesian networks for efficient kernel density estimation
Introduces binned semiparametric Bayesian networks to reduce computational cost of kernel density estimation using data binning strategies.
4/2/2026
Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization
Klear-Reasoner model demonstrates long reasoning capabilities with gradient-preserving clipping for policy optimization, achieving strong benchmark performance with reproducible training details.
4/2/2026
FedKLPR: KL-Guided Pruning-Aware Federated Learning for Person Re-Identification
Federated learning approach for person re-identification that addresses statistical heterogeneity and communication efficiency in privacy-preserving surveillance systems.
4/2/2026
Polychromic Objectives for Reinforcement Learning
Addresses mode collapse in reinforcement learning fine-tuning by introducing polychromic objectives that preserve policy diversity and enable better exploration.
4/2/2026
Adaptive Data-Knowledge Alignment in Genetic Perturbation Prediction
Proposes end-to-end integration of data-driven learning and existing knowledge for predicting transcriptional responses to genetic perturbations in biological systems.
4/2/2026
Are Large Vision-Language Models Ready to Guide Blind and Low-Vision Individuals?
Evaluates whether large vision-language models can effectively guide blind and low-vision individuals, addressing how to measure real-world utility beyond standard metrics.