About
Research & Development
Navigating the Unknown: How AI Agents Learn Without Knowing Their Own Past Actions
TLDR: This research compares "action-aware" and "action-unaware" AI agents within the Active Inference framework. Action-aware agents know their past actions, while action-unaware agents must...
Research & Development
Learning from Real-World Feedback: A New Approach for Training Language Models
TLDR: RLNVR (Reinforcement Learning from Non-Verified Real-World Rewards) is a framework that enables language models to learn from noisy, unverified real-world feedback, such as...
Research & Development
New Framework Improves Industrial Fault Diagnosis with Hierarchical Knowledge
TLDR: A new framework, Hierarchical Knowledge Guided (HKG), improves fault intensity diagnosis in industrial systems by explicitly incorporating hierarchical relationships between fault classes. Unlike...
Research & Development
Boosting LLM Logical Reasoning with Structured Chain-of-Thought
TLDR: A new method called Symbolic-Aided Chain-of-Thought (CoT) improves large language models' logical reasoning by integrating lightweight symbolic representations into prompts. This approach structures...
Research & Development
Enhancing Microservice Troubleshooting with GALA’s AI-Powered Root Cause Analysis
TLDR: GALA is a new framework that uses a combination of statistical causal inference and an iterative workflow of Large Language Model (LLM) agents...
Research & Development
Boosting Information Extraction: A New AI Workflow Combines Language Models with Logic
TLDR: A novel workflow integrates Large Language Models (LLMs) with Answer Set Programming (ASP) to enhance Joint Entity-Relation Extraction (JERE). This approach leverages LLMs...