Yifan-Song793/ETO
Trial and Error: Exploration-Based Trajectory Optimization of LLM Agents (ACL 2024 Main Conference)
This project helps developers improve the performance of their Large Language Model (LLM) agents by learning from their mistakes. It takes an existing LLM agent and its interactions, including both successful and failed attempts at tasks, and outputs an optimized agent that makes fewer errors and solves problems more efficiently. Developers building sophisticated AI agents for complex, interactive tasks would use this.
159 stars. No commits in the last 6 months.
Use this if you want to enhance your LLM agent's ability to navigate and solve problems, especially when it frequently encounters challenges or fails to complete tasks.
Not ideal if you are a non-developer looking for a ready-to-use LLM agent for everyday tasks, as this is a technical framework for agent training and optimization.
Stars
159
Forks
15
Language
Python
License
—
Category
Last pushed
Oct 30, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/Yifan-Song793/ETO"
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
MozerWang/AMPO
[ICLR 2026] Adaptive Social Learning via Mode Policy Optimization for Language Agents
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...