AI News Archive: May 18, 2026 — Part 22
Sourced from 500+ daily AI sources, scored by relevance.
- Run Buddy AI
AI running coach in your headphones
- ResumeCoach AI
AI career coach that builds your resume through conversation
- AI Smart Daily Planner
Turn messy thoughts into organized tasks instantly
- Podcastify
Generate podcast with AI from any content
- Zephr
AI-native design system components, tokens, and MCP tools
- MindFlash: AI Flashcards
Your free and generous AI-powered Flashcard App
- PUSHIT
AI-powered instant replays for sports clubs. Press & share!
- NEXUS AIOS
Secure, local desktop workspace for multi-agent AI
- intabi AI Travel Planner
Travel Made Simple! One Trip at a Time!
- FoxSEO
AI SEO on autopilot
- Trexa
Cut your Shopify support tickets in half with AI
- Compass
Bring your Claude Code workforce to your Slack workspace
- ThunderBlue Abogacy Legal 2026
Interactive 3D legal simulator powered by GPU & AI voice
- Rankforge — SEO, AEO & GEO platform
Optimize content for search and AI
- prmptree — every inbox. on autopilot.
AI agent that manages your Gmail — no prompts needed
- BergAI Live Commentator
AI market commentator for learning crypto trading
- GroundScholar
AI ground school that cites the real FAR and AIM
- GridMenu
AI-powered menu maker for restaurants, cafés and bars
- EXPRNCES
AI-powered local experience discovery
- AlyXium
Turn ideas into AI-powered MVPs
- CV Matcher Pro
Stop losing jobs to robots get your CV score in seconds
- Future Coders
Fundamentals of coding, AI, typing & game dev for kids 5–14.
- Fix Style
Your Personal AI Style Architect
- Rental Safe
AI reviews your tenancy contract before you sign
- Multilingual NLP Analysis API
BUY/SELL signals from Hebrew and Arabic financial news
- BidBolt
Create, send, and track professional quotes powered by AI.
- ShivHit.ai — AI Consulting Platform
The world’s first AI‑powered consulting platform.
- SaathiMed
AI-powered health companion with longitudinal care tracking
- Mobile Vision Automation Framework
Zero-Root AI Android UI & Gaming Automation Pipeline
- linkedin photo AI
Turn any photo into a LinkedIn-ready headshot in seconds
- Spokio
Offline text-to-speech for Mac with local voice cloning
- The CEO guide to AI Transformation
Overcome the critical issues of AI business transformation
- Speak2Easy
Hear it. Say it. Perfect it. AI language pronunciation.
- Syndicate
Drop your idea. Let AI fight over it.
- Landing Doctor
Get an AI doctor's diagnosis for your landing page
- AIThesaurus.io
Multilingual AI thesaurus with integrated SEO search volume
- Cockpyt AI
Cockpyt AI est un outil de suivi de visibilité dans les IA
- Oylo
Live AI video transformation. No rendering. Just playing.
- Efficient Gradient Methods for Distributed Saddle Problems
The distributed setting for Saddle Problems (SPs) has recently emerged as a framework for various modern applications in machine learning and multiagent systems. Despite its relevance, the theoretical foundations of this setting have not yet been thoroughly established. In this paper, we advance thi...
- LLM-Guided Communication for Cooperative Multi-Agent Reinforcement Learning
Communication is a key component in multi-agent reinforcement learning (MARL) for mitigating partial observability, yet prior approaches often rely on inefficient information exchange or fail to transmit sufficient state information. To address this, we propose LLM-driven Multi-Agent Communication (...
- Interaction-Breaking Adversarial Learning Framework for Robust Multi-Agent Reinforcement Learning
Cooperation is central to multi-agent reinforcement learning (MARL), yet learned coordination can be fragile when external perturbations disrupt inter-agent interactions. Prior robust MARL methods have primarily considered value-oriented attacks, leaving a gap in robustness when interaction structur...
- Evaluating Multi-turn Human-AI Interaction
Large language models (LLMs) are increasingly used as collaborative assistants, yet dominant NLP evaluation practices remain centered on aggregate metrics such as accuracy and fluency. These approaches often overlook behaviors that are critical in human-facing settings (e.g., consistency across mult...
- The Hidden Cost of Contextual Sycophancy: an AI Literacy Intervention in Human-AI Collaboration
Large Language Models (LLMs) are increasingly used in educational settings as interactive tools for collaboration. However, their tendency toward sycophancy, aligning with user beliefs even when incorrect, raises concerns for learning and decision-making, especially for less knowledgeable users. Thi...
- Distorted Perspectives of LLM-Simulated Preferences: Can AI Mislead Design?
Designers of digital solutions increasingly consult Large Language Models (LLMs) for their work. However, it remains unclear how this may affect the user experiences they produce and there are no established practices. We investigate how design preferences expressed by LLM-driven simulation methods ...
- What Would GPT Click: Practical Effects of Human-AI Behavioral Misalignment and the Cost of Synthetic Participants in User Experience
Synthetic participants represent a methodologically concerning concept that threatens the integrity of UX research. Findings from previous experiments specify how AI outputs are misaligned with the behaviors and thoughts of real humans in various ways. However, industry voices keep underestimating t...
- DARE-EEG: A Foundation Model for Mining Dual-Aligned Representation of EEG
Foundation models pre-trained through masked reconstruction on large-scale EEG data have emerged as a promising paradigm for learning generalizable neural representations across diverse brain-computer interface applications. However, a critical yet overlooked challenge is that EEG encoders must lear...
- MEEDAV: A Synchronous Web Viewer for EEG, Eye-Tracking and Speech Data
MEEDAV is an open-source web-based application for the synchronised visualisation of electroencephalography (EEG), eye-tracking, and audio data collected in psycholinguistic research. While originally developed for the Eyetracked Multi-Modal Translation (EMMT) corpus, which uses four-channel EEG dat...
- A Brief Overview: On-Policy Self-Distillation In Large Language Models
On-Policy Self-Distillation (OPSD) introduces a unified learning framework in which a single large language model simultaneously serves as both teacher and student. Unlike conventional knowledge distillation that relies on a separate, often larger teacher model, OPSD operates under different context...
- An Empirical Study of Privacy Leakage Chains via Prompt Injection in Black-Box Chatbot Environments
LLM-based chatbot agents increasingly process user requests by combining natural-language reasoning with external tools such as web browsing. These capabilities improve usability, but they also create attack surfaces when untrusted external content is processed as part of a user' s task. This paper ...
- PROTEA: Offline Evaluation and Iterative Refinement for Multi-Agent LLM Workflows
Multi-agent LLM workflows -- systems composed of multiple role-specific LLM calls -- often outperform single-prompt baselines, but they remain difficult to debug and refine. Failures can originate from subtle errors in intermediate outputs that propagate to downstream nodes, requiring developers to ...