ruleGreen / RandomReading

This is a repo to record my random reading history, i will also write some sparks about the paper randomly

Random Reading

This is a repo to record my random reading history, i will also write some sparks about the paper randomly

Chain-of-X

• [Chain-of-code]

Language Agents

• CogAgent: A Visual Language Model for GUI Agents Tsinghua, multi-modal agent

• Webarena: A REALISTIC WEB ENVIRONMENT FOR BUILDING AUTONOMOUS AGENTS

• AndroidEnv: A Reinforcement Learning Platform for Android

• VirtualHome: Simulating Household Activities via Programs

• [A Collaborative Multi-agent Reinforcement Learning Framework for Dialog Action Decomposition]

Tool Learning

• Tool-Augmented Reward modeling teach reward model to use tools

• ViperGPT: Visual Inference via Python Execution for Reasoning CV

• Confucius: Iterative Tool Learning from Introspection Feedback by Easy-to-Difficult Curriculum AAAI 2024

Alignment

• Alignment for Honesty

Ability Distillation

Model Level -- from larger model to small model

• Personalised Distillation: Empowering Open-Sourced LLMs with Adaptive Learning for Code Generation