About
Research & Development
AI Agents Step into the Newsroom: A New Benchmark for Journalistic Tasks
TLDR: NEWSAGENT is a new benchmark that evaluates AI agents on realistic newswriting tasks, requiring them to iteratively search, select, and edit multimodal information...
Research & Development
Unlocking Collective AI: The SuperBrain Framework for Human-LLM Co-Evolution
TLDR: The SuperBrain framework proposes a novel collective intelligence system where individual "Subclass Brains" (personalized human-LLM dyads) co-evolve through iterative feedback loops and then...
Research & Development
Enhancing Language Models for Graph Tasks with Targeted Context
TLDR: This paper introduces a framework called "structured context injection" to improve Large Language Models' (LLMs) ability to solve graph-related problems without fine-tuning. By...
Research & Development
L-MARS: A Multi-Agent System for Precise Legal Question Answering
TLDR: L-MARS (Legal Multi-Agent Workflow with Orchestrated Reasoning and Agentic Search) is a novel AI system designed to significantly reduce hallucinations and uncertainty in...
Research & Development
A Novel Dynamic Programming Approach to Optimizing Sharpe Ratio in Sequential Decision Making
TLDR: Researchers have developed the first dynamic programming-based algorithms, SRPI and SRPI+, to globally optimize the Sharpe ratio in Markov Decision Processes (MDPs). They...
Research & Development
Optimizing AI for Complex Games: Tailoring Deep MCCFR Strategies to Game Scale
TLDR: This paper introduces Robust Deep MCCFR, a framework designed to address theoretical risks like non-stationary targets, action support collapse, and variance explosion when...