WeSearch
Hub / Ai Research
ai-research · WeSearch

Ai Research news.

Page 17 of Ai Research headlines on WeSearch — deduped and updated continuously from 10+ editorial sources.

ARXIV CS.AI

WebGameBench: Requirement-to-Application Evaluation for Coding Agents via Browser-Native Games

5/19/2026 · 11 views
ARXIV CS.AI

Causal Intervention-Based Memory Selection for Long-Horizon LLM Agents

5/19/2026 · 12 views
ARXIV CS.AI

SAPO: Step-Aligned Policy Optimization for Reasoning-Based Generative Recommendation

5/19/2026 · 13 views
ARXIV CS.AI

Multimodal Cultural Heritage Knowledge Graph Extension with Language and Vision Models

5/19/2026 · 18 views
ARXIV CS.AI

EGI: A Multimodal Emotional AI Framework for Enhancing Scrum Master Real-time Self-Awareness

5/19/2026 · 18 views
ARXIV CS.AI

EXG: Self-Evolving Agents with Experience Graphs

5/19/2026 · 14 views
ARXIV CS.AI

Divergence-Suppressing Couplings for Rectified Flow

5/19/2026 · 8 views
ARXIV CS.AI

Harnessing LLM Agents with Skill Programs

5/19/2026 · 16 views
ARXIV CS.AI

Agents for Experiments, Experiments for Agents: A Design Grammar for AI-Enabled Experimental Science

5/19/2026 · 12 views
ARXIV CS.AI

Surface-Form Neural Sparse Retrieval: Robust Fuzzy Matching for Industrial Music Search

5/19/2026 · 14 views
ARXIV CS.AI

Entropy-Gradient Inversion: Moving Toward Internal Mechanism of Large Reasoning Models

5/19/2026 · 13 views
ARXIV CS.AI

STRIDE: A Self-Reflective Agent Framework for Reliable Automatic Equation Discovery

5/19/2026 · 10 views
ARXIV CS.AI

Accelerating AI-Powered Research: The PuppyChatter Framework for Usable and Flexible Tooling

5/19/2026 · 10 views
ARXIV CS.AI

Going Headless? On the Boundaries of Vertical AI Firms

5/19/2026 · 8 views
ARXIV CS.AI

Interactive Evaluation Requires a Design Science

5/19/2026 · 9 views
ARXIV CS.AI

Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents

5/19/2026 · 8 views
ARXIV CS.AI

KISS - Knowledge Infrastructure for Scientific Simulation: A Scaffolding for Agentic Earth Science

5/19/2026 · 12 views
ARXIV CS.AI

PAIR: Prefix-Aware Internal Reward Model for Multi-Turn Agent Optimization

5/19/2026 · 9 views
ARXIV CS.AI

Evaluating Cognitive Age Alignment in Interactive AI Agents

5/19/2026 · 14 views
ARXIV CS.AI

DuIVRS-2: An LLM-based Interactive Voice Response System for Large-scale POI Attribute Acquisition

5/19/2026 · 15 views
ARXIV CS.AI

LAST-RAG: Literature-Anchored Stochastic Trajectory Retrieval-Augmented Generation for Knowledge-Conditioned Degradation Model Selection

5/19/2026 · 12 views
ARXIV CS.AI

Agentic Chunking and Bayesian De-chunking of AI Generated Fuzzy Cognitive Maps: A Model of the Thucydides Trap

5/19/2026 · 14 views
ARXIV CS.AI

Ethical Hyper-Velocity (EHV): A Provably Deterministic Governance-Aware JIT Compiler Architecture for Agentic Systems

5/19/2026 · 14 views
ARXIV CS.AI

SVFSearch: A Multimodal Knowledge-Intensive Benchmark for Short-Video Frame Search in the Gaming Vertical Domain

5/19/2026 · 16 views
ARXIV CS.AI

Reconciling Contradictory Views on the Effectiveness of SFT in LLMs: An Interaction Perspective

5/19/2026 · 9 views
ARXIV CS.AI

Unleashing LLMs in Bayesian Optimization: Preference-Guided Framework for Scientific Discovery

5/19/2026 · 12 views
ARXIV CS.AI

Shared Backbone PPO for Multi-UAV Communication Coverage with Connection Preservation

5/19/2026 · 14 views
ARXIV CS.AI

TeleCom-Bench: How Far Are Large Language Models from Industrial Telecommunication Applications?

5/19/2026 · 13 views
ARXIV CS.AI

New Insight of Variance reduce in Zero-Order Hard-Thresholding: Mitigating Gradient Error and Expansivity Contradictions

5/19/2026 · 14 views
ARXIV CS.AI

DocOS: Towards Proactive Document-Guided Actions in GUI Agents

5/19/2026 · 6 views
ARXIV CS.AI

LLM-Guided Communication for Cooperative Multi-Agent Reinforcement Learning

5/19/2026 · 18 views
ARXIV CS.AI

Learning to Solve Compositional Geometry Routing Problems

5/19/2026 · 14 views
ARXIV CS.AI

Safety Geometry Collapse in Multimodal LLMs and Adaptive Drift Correction

5/19/2026 · 12 views
ARXIV CS.AI

TaskGround: Structured Executable Task Inference for Full-Scene Household Reasoning

5/19/2026 · 14 views
ARXIV CS.AI

POST: Prior-Observation Adversarial Learning of Spatio-Temporal Associations for Multivariate Time Series Anomaly Detection

5/19/2026 · 12 views
ARXIV CS.AI

Generative AI and the Productivity Divide: Human-AI Complementarities in Education

5/19/2026 · 17 views
ARXIV CS.AI

Evidence-Grounded Frontier Mapping and Agentic Hypothesis Generation in Nanomedicine

5/19/2026 · 13 views
ARXIV CS.AI

Whispers in the Noise: Surrogate-Guided Concept Awakening via a Multi-Agent Framework

5/19/2026 · 12 views
ARXIV CS.AI

TRACE: Trajectory Correction from Cross-layer Evidence for Hallucination Reduction

5/19/2026 · 15 views
ARXIV CS.AI

Visualizing the Invisible: Generative Visual Grounding Empowers Universal EEG Understanding in MLLMs

5/19/2026 · 13 views
ARXIV CS.AI

Scalable Environments Drive Generalizable Agents

5/19/2026 · 7 views
ARXIV CS.AI

Pairwise Preference Reward and Group-Based Diversity Enhancement for Superior Open-Ended Generation

5/19/2026 · 15 views
ARXIV CS.AI

Beyond the Cartesian Illusion: Testing Two-Stage Multi-Modal Theory of Mind under Perceptual Bottlenecks

5/19/2026 · 14 views
ARXIV CS.AI

DARE-EEG: A Foundation Model for Mining Dual-Aligned Representation of EEG

5/19/2026 · 14 views
ARXIV CS.AI

SD-Search: On-Policy Hindsight Self-Distillation for Search-Augmented Reasoning

5/19/2026 · 13 views
ARXIV CS.AI

Causely: A Causal Intelligence Layer for Enterprise AI A Benchmark Study on SRE and Reliability Workflows

5/19/2026 · 15 views
ARXIV CS.AI

QSTRBench: a New Benchmark to Evaluate the Ability of Language Models to Reason with Qualitative Spatial and Temporal Calculi

5/19/2026 · 15 views
ARXIV CS.AI

When Fireflies Cluster; Enhancing Automatic Clustering via Centroid-Guided Firefly Optimization

5/19/2026 · 15 views
ARXIV CS.AI

OCCAM: Open-set Causal Concept explAnation and Ontology induction for black-box vision Models

5/19/2026 · 13 views
ARXIV CS.AI

A Practical Noise2Noise Denoising Pipeline for High-Throughput Raman Spectroscopy

5/19/2026 · 14 views

Sources in Ai Research

Other categories