About
Research & Development
RAD: Enhancing Decision-Making in Offline Reinforcement Learning Through Dynamic Trajectory Retrieval
TLDR: RAD (Retrieval High-quAlity Demonstrations) is a novel framework for offline reinforcement learning that addresses limitations of sparse datasets and poor generalization. It combines...
Research & Development
Optimizing Business Processes: A New Approach to Activity Batching
TLDR: This research paper introduces a Pareto optimization approach for activity batching policies in business processes. It proposes 19 heuristic interventions to balance waiting...
Research & Development
StarCraft II AI Learns Flexible Tactics with New Language-Driven System
TLDR: TacticCraft introduces an adapter-based method for StarCraft II AI agents to adapt their strategies based on natural language tactical directives. By freezing a...
Research & Development
Bridging AI and Clinical Practice: A New Model for Diagnostic Oversight
TLDR: A new research paper introduces 'guardrailed-AMIE' (g-AMIE), an AI system designed for diagnostic dialogue under asynchronous physician oversight. In a virtual study, g-AMIE...
Research & Development
Automating Gas Savings in Blockchain Contracts
TLDR: GasAgent is a multi-agent AI framework that automates the optimization of smart contract Gas fees. It uses four specialized agents (Seeker, Innovator, Executor,...
Research & Development
LLMs Learn to Think Smarter with Hierarchical Budget Policy Optimization
TLDR: Hierarchical Budget Policy Optimization (HBPO) is a new reinforcement learning framework that teaches large language models (LLMs) to adapt their reasoning depth based...