Deep Dives

Analysis

Deep-dive editorial on AI industry trends and original research

649 articles 55 pages

All Critical (9-10) Important (7-8) Notable (5-6) Logged (1-4) 649 articles

Editorial illustration for: PSPA-Bench: A Personalized Benchmark for Smartphone GUI Agent

PSPA-Bench: New Benchmark Exposes Personalization Gap in Smartphone GUI Agents

3/10 4 min read 6 months ago

Editorial illustration for: Beyond pass@1: A Reliability Science Framework for Long-Horizon LLM Agents

Frontier Models Hit 19% Meltdown Rate in Long-Horizon LLM Agent Study

4/10 4 min read 6 months ago

Editorial illustration for: Route-Induced Density and Stability (RIDE): Controlled Intervention and Mechanism Analysis of Rou

RIDE Study: Routing Meta Prompts Densify LLM Layers, Not Sparsify

3/10 4 min read 6 months ago

Editorial illustration for: AEC-Bench: A Multimodal Benchmark for Agentic Systems in Architecture, Engineering, and Construct

AEC-Bench: Multimodal Benchmark for AI Agents in Architecture

4/10 3 min read 6 months ago

Editorial illustration for: Webscraper: Leverage Multimodal Large Language Models for Index-Content Web Scraping

Webscraper Framework Uses MLLMs to Extract Data From Dynamic Sites

4/10 4 min read 6 months ago

Editorial illustration for: SimMOF: AI agent for Automated MOF Simulations

SimMOF Automates MOF Simulations via LLM Multi-Agent System

3/10 4 min read 6 months ago

Editorial illustration for: Knowledge database development by large language models for countermeasures against viruses and m

Los Alamos Researchers Use LLMs to Build Biodefense Countermeasure Databases

4/10 4 min read 6 months ago

Editorial illustration for: SciVisAgentBench: A Benchmark for Evaluating Scientific Data Analysis and Visualization Agents

SciVisAgentBench: 108 Cases for Testing Scientific Visualization Agents

3/10 4 min read 6 months ago

Editorial illustration for: GISTBench: Evaluating LLM User Understanding via Evidence-Based Interest Verification

GISTBench Tests LLM User Understanding in Recommendation Systems

3/10 4 min read 6 months ago

Editorial illustration for: PAR$^2$-RAG: Planned Active Retrieval and Reasoning for Multi-Hop Question Answering

PAR²-RAG Framework Beats IRCoT by 23.5% on Multi-Hop Question Answering

3/10 4 min read 6 months ago

Editorial illustration for: Drop the Hierarchy and Roles: How Self-Organizing LLM Agents Outperform Designed Structures

Self-Organizing LLM Agents Outperform Designed Structures by 14%, Study Finds

5/10 4 min read 6 months ago

Editorial illustration for: Mimosa Framework: Toward Evolving Multi-Agent Systems for Scientific Research

Mimosa Multi-Agent Framework Achieves 43.1% on ScienceAgentBench

4/10 4 min read 6 months ago

← Prev 1 … 40 41 42 43 44 … 55 Next → Page 42 of 55

📬 Get AI news daily → Subscribe Free