--- license: apache-2.0 datasets: - ai2lumos/lumos_unified_plan_iterative language: - en tags: - language-agent - web-agent - question-answering - maths - reasoning - planning --- # 🪄 Lumos: Language Agents with Unified Formats, Modular Design, and Open-Source LLMs

🌐[Website]   📝[Paper]   🤗[Data]   🤗[Model]  

We introduce 🪄**Lumos**, Language Agents with **Unified** Formats, **Modular** Design, and **Open-Source** LLMs. **Lumos** unifies a suite of complex interactive tasks and achieves competitive performance with GPT-4/3.5-based and larger open-source agents. **Lumos** has following features: * 🧩 **Modular Architecture**: - **Lumos** consists of planning, grounding, and execution modules built based on LLAMA-2-7B. * 🌍 **Diverse Training Data**: - **Lumos** is trained with ~40K high-quality annotations from ground-truth reasoning steps in existing benchmarks with GPT-4. * 🚀 **Competitive Performance**: - 🚀 **Lumos** outperforms **GPT-4/3.5-based** agents on complex QA and web agent tasks, and **larger open agents** on maths tasks. - 🚀 **Lumos** performs better than open agent baseline formulations including **chain-of-thoughts** and **unmodularized** training. - 🚀 **Lumos** surpasses larger open LLM agents and domain-specific agents on an unseen task, WebShop. ## Model Overview `lumos_unified_plan_iterative` is a **planning** module checkpoint finetuned on **complex QA**, **web agent** and **maths** tasks in **Lumos-Iterative (Lumos-I)** formulation. The training annotation is shown below: | Training Data | Number | |---|---| |[`lumos_unified_plan_iterative`](https://huggingface.co/datasets/ai2lumos/lumos_unified_plan_iterative)|39827| ## Citation If you find this work is relevant with your research, please feel free to cite our work! ``` @article{yin2023lumos, title={Lumos: Towards Language Agents that are Unified, Modular, and Open Source}, author={Yin, Da and Brahman, Faeze and Ravichander, Abhilasha and Chandu, Khyathi and Chang, Kai-Wei and Choi, Yejin and Lin, Bill Yuchen}, year={2023} } ```