BOLAA: Benchmarking and Orchestrating LLM-augmented Autonomous Agents
The massive successes of large language models (LLMs) encourage the emerging exploration of LLM-augmented Autonomous Agents (LAAs).
Tags：Paper and LLMsBenchmarking Decision MakingPricing Type
- Pricing Type: Free
- Price Range Start($):
GitHub Link
The GitHub link is https://github.com/salesforce/bolaa
Introduce
The GitHub repository “salesforce/BOLAA” contains code and resources related to the BOLAA paper. This initial release is in response to numerous requests and will be continually updated and cleaned. To set up, install “fastchat” for local open-source language model usage. Provide OPENAI API KEY in configurations for web and HotpotQA agents. Additionally, there are instructions for setting up web agent and HotpotQA agent environments. The paper and code are attributed to the authors, and acknowledgment is given to the ReAct code and Langchain for the LLM API. Testing was performed using WebShop and HotPotQA.
The massive successes of large language models (LLMs) encourage the emerging exploration of LLM-augmented Autonomous Agents (LAAs).
Content
other agent options can be found in test_webagent.sh other agent options commands can be found in test_hotpotqa.sh If you find our paper or code useful, please cite
Related
Based on the modeling method, we present FocusFlow, a framework consisting of 1) a mix loss function combined with a classic photometric loss function and our proposed Conditional Point Control Loss (CPCL) function for diverse point-wise supervision; 2) a conditioned controlling model which substitutes the conventional feature encoder by our proposed Condition Control Encoder (CCE).
In the pursuit of promoting the expressiveness of GNNs for tail nodes, we explore how the deficiency of structural information deteriorates the performance of tail nodes and propose a general Structural Augmentation based taIL nOde Representation learning framework, dubbed as SAILOR, which can jointly learn to augment the graph structure and extract more informative representations for tail nodes.
