AI
StagedWorkspace: A Versioned Workspace for Knowledge-Work Agents
Researchers have proposed StagedWorkspace, a versioned workspace for knowledge-work agents. This system binds parsed records and review diffs to conte...
AI
AI
HLSR: Hybrid Live Forecast Selective Dynamic Vehicle Rerouting for Real-Time Congestion Avoidance
Researchers propose a new framework called HLSR to reduce urban traffic congestion. It combines real-time data with short-term forecasts to reroute ve...
AI
Delegation Asymmetry in Agentic Recommender Systems: Measuring Two-Sided Receptivity in Online Dating
Researchers investigated the effectiveness of autonomous conversational agents in online dating platforms by analyzing data from two large-scale surve...
AI
On the Fragility of Self-Improving Agents: Variance, Task Order, and Underspecification
Researchers have re-evaluated memory-based self-improving agents that learn and improve over time by maintaining a textual memory bank. They found tha...
AI
Potential of ChatGPT in predicting stock market trends based on Twitter Sentiment Analysis
Researchers investigated whether ChatGPT can use Twitter sentiment analysis to predict stock market trends. They analyzed tweets about Microsoft and G...
AI
Intent-Driven Dynamic Chunking: Segmenting Documents to Reflect Predicted Information Needs
Researchers have developed a new approach to breaking down long documents into smaller segments called Intent-Driven Dynamic Chunking (IDC). IDC uses ...
AI
The Working Set of a Coding Agent: Coherence Debt in Repository-Scale Tasks
Researchers have studied how coding agents manage coherence debt in repository-scale tasks. They model this as reconstructing a coupled-fact graph, wh...
AI
A Framework for Using and Evaluating LLMs as Surrogate Experts in Security Surveys: Reliability, Bias, and Implications
A new framework has been proposed to evaluate the reliability of using large language models (LLMs) as substitutes for human experts in security surve...
AI
What If AI Carried Her Imagination? Black Girls as Creators in an AI Storytelling Weekend Program
Researchers from various institutions developed a seven-weekend AI storytelling program for Black girls aged 10-12. The program was grounded in Afrofu...
AI
CityReal: Human-Aligned Urban Behavior and City Dynamics Simulation with Large-Scale LLM Agents
CityReal is a framework for simulating human behavior in cities using large language models. Unlike previous methods that rely on few-shot prompting, ...
AI
QuantumNovelty: A Skill-Orchestrating Language Agent for Referee-Style Review and Patentability Screening of Quantum Papers and Patents
Researchers have developed QuantumNovelty, an open-source language agent that can generate and review quantum science papers and patents. The system u...
AI
AI, Brain Death Detection, and Islamic Law
Researchers from various fields have come together to address a pressing issue at the intersection of clinical medicine, AI ethics, and Islamic jurisp...