MozerWang/AMPO
[ICLR 2026] Adaptive Social Learning via Mode Policy Optimization for Language Agents
This project helps AI developers and researchers create language agents that can adapt their thinking based on social interactions. It takes existing large language models and training data as input and produces agents capable of more nuanced, context-aware responses, ranging from intuitive to deeply deliberative. The primary users are those building advanced conversational AI, simulated social environments, or complex multi-agent systems.
Use this if you are developing language agents for social simulations or interactive AI and need them to exhibit flexible, human-like reasoning and response capabilities.
Not ideal if you are looking for a simple plug-and-play chatbot solution without needing to delve into advanced adaptive policy optimization and training.
Stars
48
Forks
5
Language
Python
License
Apache-2.0
Category
Last pushed
Feb 02, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/MozerWang/AMPO"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
xrsrke/toolformer
Implementation of Toolformer: Language Models Can Teach Themselves to Use Tools
real-stanford/reflect
[CoRL 2023] REFLECT: Summarizing Robot Experiences for Failure Explanation and Correction
nsidn98/LLaMAR
Code for our paper LLaMAR: LM-based Long-Horizon Planner for Multi-Agent Robotics
BatsResearch/planetarium
Dataset and benchmark for assessing LLMs in translating natural language descriptions of...
WayneMao/RoboMatrix
The Official Implementation of RoboMatrix